Search

The paper reviewed the development of Coal Science and Technology in the past 50 years which promoted and witnessed the progress and innovation practice of the coal mining technology and equipment in China. Furthermore, the innovation process from coal mine mechanization to coal mine intelligence was expounded and the research and development of coal machine equipment technology which supports the reform of coal development process was analyzed emphatically. Finally, the paper summarized the iterative development of smart coal mine and put forward some ideas for future development trends. Coal mining technology has experienced four major technological changes from blasting mining, ordinary mechanized mining, comprehensive mechanized mining, intelligent mining, through continuous independent research and development and innovation, to achieve great progress in coal productivity. Research and development of coal machinery equipment supports the reform of coal development technology. Hydraulic support is the core of fully mechanized mining. The innovation of supporting theory, design method, frame structure and manufacturing technology supported the breakthrough of hydraulic support products from low-end to high-end. Significant progress has been made in the short board technology for coal mining machines such as manufacturing process, model adaptability, monitoring system and so on. The full series of coal mining machines from 0.8 to 9 m could meet the requirements of efficient production of Chinese coal mines, and the intelligent level was constantly improving. The key technologies of large volume and long distance working face scraper conveyor were constantly broken through. The 450 m ultra-long working face scraper conveyor with large volume runs reliably. The intelligent frequency conversion integrated machine drives instead of traditional CST and other drives, saving energy by nearly 30%. Innovations such as permanent magnet direct drive, arylon belt, and belt conveyor without foundation for large volume belt conveyor showed significant advantages in energy saving, reliability, and intelligence. Electro-hydraulic control and unmanned intelligent mining control technology develop rapidly, and the domestic SAC hydraulic support electro-hydraulic control system, SAM face automation system and SAP intelligent liquid supply system were widely used. To solve the problem of mining imbalance, it had developed the “driving and anchor machine + anchoring and breaking + large-span reloading” intellectualized driving and anchor machine, boom-type roadheader + temporary support system and TBM full face hard rock tunneling system. Intelligent frequency conversion energy-saving transmission supports energy saving in mines, comprehensive domestic innovation of coal machinery equipment and rapid improvement of intelligent manufacturing capacity. More than 30 kinds of coal mine robots had been developed and applied in NingTiaoTa coal mine of Shaanxi coal, achieving good results. The intelligent technology of coal mine developed rapidly and iteratively. This paper analyzed the classification and correlation of coal mine data flow, proposed the overall technical framework of smart coal mine and the basic data processing theory of “hierarchical extraction- association analysis-virtual-real mapping”, summarized the coupling and iterative development progress of smart coal mine system and the construction progress of smart coal mine technical standard system, and finally puts forward the development idea of intelligent coal mine. It is necessary to build a data value ecology based on “coal intelligence cloud”, push forward the research and development of intelligent mining technology and equipment under complex conditions and coal mine robot cluster. Furth more a coal mine intelligence ecology that integrates system intelligence and human wisdom should be built, which could boost the high-quality development of enterprises.

Coal is the main energy source in China, which is also an important guarantee for the safety and stability of the national power supply as well as economic development. However, the coal combustion process for power generation will produce a large amount of fly ash, and the long-term piling of fly ash solid waste will seriously pollute the soil, water, atmosphere, and ecological environment, on the contrary, the fly ash can be used as a raw material for the prevention and control of coal spontaneous combustion disasters in mines. However, the current application of fly ash in the field of mine fire prevention was certainly limited, such as small amount of scattered utilization, low technical content, low added value, etc. The current scale of harmless pre-treatment and fire prevention and utilization of fly ash is still unable to meet the requirements of the national “carbon peaking and carbon neutrality” target for solid waste resource utilization and green mine construction. For further promote the efficient, high-value, and large-scale utilization of fly ash to realize the rapid development of fly ash-based fire prevention materials and technologies, this paper summarizes the principle, classification, latest development, and application effects of fly ash slurry, fly ash gel, fly ash foam and other fire prevention technologies. Based on the above analysis, this paper condenses three key problems that need to be solved, such as the separation of hazardous substances and valuable components in fly ash solid waste, the precipitation and plugging of pipes during long-distance transportation of highly concentrated fly ash slurry, and the law of seepage and accumulation of fly ash-based fire prevention materials in the goaf. In order to improve the effectiveness of fly ash solid waste in preventing spontaneous combustion of coal and to meet the national requirements for green mines as well as intelligent mine construction under the “carbon neutrality and emission peak” target, this paper proposes the development direction of “Long-lasting for fire prevention-Synergistic carbon sequestration – Intelligent control” for fly ash solid waste in the field of fire prevention technology. Future research will focus on the low-cost and long-lasting fire prevention fly ash solid waste-based materials, integrated fly ash fire prevention technology with mineralized CO2 sequestration and fire prevention, and intelligent fly ash fire prevention material application systems, which will promote the high-value and large-scale reuse of fly ash waste in the field of fire prevention, finally improving the efficiency of preventing and controlling of spontaneous combustion disasters in coal mines, and ensuring the safe and efficient mining.

Cultivated land is the foundation of food security, while coal guarantees the security of the energy. The coal-cropland overlapped area accounts for approximate 42.7% of the total cultivated land area in China, making it become a prominent contradiction between the extensive mining and cultivated land protection. How to realize the coordinated development of the coal mining and the cultivated land protection is an urgent problem in coal-cropland overlapped areas. This paper analyzes the research status and existing issues of the coordinated development between mining and cultivated land protection from the following three aspects: the damage mechanism of subsidence land in plain coal-cropland overlapped areas, the damage degree evaluation of subsidence land induced by mining, the control technology for the mining subsidence. Then, considering the characteristics of the cultivated land, such as the extensive protection-needed area and the high deformation tolerance, a new technical approach of controlling regional rock strata and surface deformation in green mining is proposed by combining source control and restoration. The corresponding prediction and control design methods of surface deformation are established. Additionally, the key research directions for the coordination of coal mining and cultivated land protection in the plain coal-cropland overlapped areas are pointed out, including the driving mechanism of cultivated land damage induced by mining in the plain area, protection thresholds for the quality of the cultivated land in subsidence areas, theories and methods of the subsidence coordinated control of the green mining facing the cultivated land protection. The main objective of this paper is to promote the coordinated development of the green mining and the cultivated land protection in the plain coal-cropland overlapped areas.

This paper analyzes the outstanding technical weaknesses in the intelligent construction of coal mines in China. This paper puts forward 12 innovative research and development directions, including intelligent system design, information infrastructure, intelligent geological support, intelligent mining and transportation, intelligent safety prediction and early warning, intelligent power supply and intelligent water affairs, intelligent washing, intelligent parks, intelligent open-pit coal mines, intelligent well construction, intelligent equipment and robots, and emergency rescue and supervision. 46 coal mine intelligent innovation teams have been established, forming the strongest team of coal mine intelligent innovation. The target collaboration, organization collaboration, knowledge collaboration and business collaboration models of the innovation chain and industry chain are established. Relying on 136 provincial experimental platforms, this study takes the lead in obtaining a number of innovative achievements in the important technical direction of the intelligent coal mine. This paper provides technical support for the construction of intelligent coal mine in our country. This study puts forward 9 key breakthrough directions to continuously promote the intelligent construction of coal mines and improve the technical equipment support capacity. It is suggested to continuously build the intelligent support technology system of coal mine, accelerate the construction of the intelligent technology standard system of coal mine and the construction benefit evaluation system, and accelerate the research and application of the intelligent 'MineCloud' of coal mine. It is suggested to develop complete sets of intelligent mining process equipment for large mining height caving coal, strengthen the research and development of intelligent fast heading technology and equipment, and develop highly reliable and stable intelligent mine sensors. It is suggested to accelerate the research and development of key technologies of coal mine robot cluster, accelerate the construction of intelligent washing complete equipment and process package development, and strengthen the advanced and mature intelligent process and the stability and high reliability of core equipment in open-pit coal mines.

The problem of low detection accuracy of driving displacement exists in the driving process of anchor digging robots. In order to solve the above problem, taking the supporting bolt as the positioning benchmark, by analyzing the distance relationship between the anchor digging robot and the supporting bolt, the positioning model of 'anchor digging robot-supported anchor' is established. This paper proposes a binocular vision-based displacement detection method for anchor digging robots. Due to the complexity of the underground coal mine environment, the disparity map obtained by using the traditional Census transform algorithm has limitations. By analyzing the binocular vision ranging principle, an improved Census transform algorithm is proposed to obtain the disparity map of the anchor and the depth information of the anchor image. This paper presents a method of anchor feature recognition and positioning, and uses edge detection algorithm to extract the anchor contour in disparity map. The minimum circumscribed rectangle and the maximum circumscribed rectangle algorithm are used to frame the anchor outline and extract the pixel coordinates of anchor feature points. By analyzing coordinate conversion relationships, the pixel coordinates of feature points are converted to world coordinates. By using the least square method, the spatial coordinates of feature points are fitted into a straight line. The plane parallel to the roadway section is established through the straight line. The distance between the binocular camera and the plane is calculated, and then the distance between the anchor digging robot and the plane is obtained. A mobile robot platform is set up to carry out the displacement detection experiment of the anchor digging robot. The results show the following points. The improved Census transform algorithm reduces the mismatch rate from 19.85% to 11.52%, which is 41.96% lower than the traditional Census transform algorithm. The method of anchor feature point recognition and positioning can effectively extract the spatial coordinates of anchor feature points. The distance between the camera and the three parallel sections is 3 010.428, 2 215.910, 1 415.127 mm respectively through straight line fitting. In the robot positioning experiment, the real calculated displacement is compared with the theoretical displacement. The results show that the real calculated displacement curve coincides with the theoretical displacement curve basically. The error between the theoretical displacement and the calculated displacement is less than 20 mm. The autonomous, accurate and real-time displacement detection of the anchor digging robot can be realized.

Roadway dust cleaning robot can effectively solve the problem of coal mine roadway dust accumulation. However, there is no relatively mature product to achieve 'automatic dust accumulation monitoring-autonomous/semi-autonomous movement-adaptive dust cleaning operation'. This paper analyzes the research status of three kinds of dust cleaning equipment developed at home and abroad, which are wheel-rail type roadway dust cleaning device, explosion-proof sprinkler and tunnel dust cleaning vehicle with chassis and hydraulic mechanical arm. It is pointed out that the wheel-rail type roadway dust cleaning device does not contain power system. The dust-cleaning effect of roadway wall dust is limited. The explosion-proof sprinkler has its own power, which can realize full section dust reduction of the trackless long roadway. However, the jet water surface is wide, and it is unable to deal with local areas with serious dust accumulation such as roadway walls and pipelines. Tunnel dust cleaning vehicle can solve the problem of dust accumulation in long-distance tunnels. However, manual driving and operation are still required, and it is impossible to realize tunnel dust accumulation monitoring and adaptive dust cleaning. Based on the above analysis, it is pointed out that in order to realize 'automatic dust accumulation monitoring-autonomous/semi-autonomous movement-adaptive dust cleaning operation', the research should be carried out from the aspects of dust accumulation monitoring, structure design and control of dust cleaning device, and optimization strategy of dust cleaning mode. It is pointed out that the main technical problems faced by the above research include the common problems of coal mine robots such as explosion-proof safety design, underground precise positioning, and long-distance wireless communication. The problems also include the characteristic problems of roadway dust cleaning robot such as dust monitoring, adaptive dust cleaning, and vehicle arm coordinative operation. In view of the characteristic problem of the roadway dust cleaning robot, this paper puts forward the corresponding key technologies. ① It is suggested to research and develop a multi-sensor fusion monitoring technology based on the weighing method, laser method and image method to realize long-term monitoring of dust cleaning in coal mine roadway and dynamic evaluation of dust cleaning effect. ② It is suggested to develop dust cleaning structure based on explosion-proof mechanical arm and 'wind-water-brush' linkage dust cleaning device to realize adaptive dust cleaning. ③ It is suggested to establish a unified workspace for vehicle chassis and mechanical arm. It is suggested to develop small deviation automatic compensation and flexible obstacle avoidance technology for roadway dust cleaning robot based on torque control. The vehicle arm coordination of the roadway dust cleaning robot in the dynamic scene is realized.

In order to fully understand the current research situation in field of deep coal mining, took the relevant literature of web of science database from 2003 to 2021 as a sample, this paper made an in-depth analysis on the number of papers issued, research institutions, countries, authors, literature citations, keywords and disciplines.The results showed that China's research level is at the forefront of the world in terms of the number of papers issued, research institutions and national levels; Chinese scholars pay high attention to this field in terms of the author; highly cited documents are mostly engineering and technical studies in terms of literature citation; from the perspective of keyword development and evolution, the keywords in this field mainly focus on model, rock, numerical simulation, mechanism and stress, model and numerical simulation will be the important research methods in this field in the future.From the perspective of discipline development and evolution, disciplines in this field mainly focus on engineering, geology, multidisciplinary geoscience, energy and fuel, environmental science and ecology, sustainable development will become the hot research directions in the future.

The paper analyzes the image characteristics of the thrown coal and rock when rock burst and coal and gas outburst occur. ① The coal and rock thrown out during rock burst and coal and gas outburst are mainly black, but the underground equipment of the coal mine is generally not black. Therefore, nonblack mining equipment can be used as the background and color cameras can be used to identify coal and rock. ② The normal coal falling speed, the moving speed of shearer, roadheader, and the moving speed of underground personnel and vehicles are far less than the speed of coal and rock thrown out in the event of rock burst and coal and gas outburst. Therefore, according to the speed characteristics, the interference from normal coal falling, movement of equipment such as shearer and roadheader, and movement of underground personnel and vehicles can be eliminated. ③ The explosion of gas and coal dust will also cause the objects in the roadway to have a high speed in a short time, accompanied by high brightness. But the rock burst and coal and gas outburst will not produce high brightness. Therefore, according to the average image brightness, the interference of gas and coal dust explosion can be eliminated. The paper proposes a color camera set method. The camera of the heading face should be set at the roof of the heading roadway or near the roof on both sides of the heading roadway. The camera of the working face should be set on the top of the hydraulic support. The paper puts forward a coal mine rock burst and coal and gas outburst perception alarm method based on color image. ① The color camera with fill light shall be set at the roof of the heading roadway or near the roof on both sides of the heading roadway, and at the top of the hydraulic support of the working face. The nonblack mining equipment is used as the background. ② The method monitors and identifies whether the color of the color image has changed greatly. ③ If the image color changes significantly, the average brightness of the image is identified, otherwise the monitoring of the identified image color change continues. ④ If the average brightness of the image is less than the set brightness threshold, the movement speed of the object causing a large change in the image color is identified, otherwise the monitoring of the identified image color change continues. ⑤ If the movement speed of the object is greater than the set speed threshold value, the methane concentration in the monitoring area is identified, otherwise the monitoring of the identified image color change continues. ⑥ If the methane concentration rises rapidly or reaches the alarm value, the coal and gas outburst alarm will be given. Otherwise, the rock burst alarm will be given. The method has the advantages of non-contact, wide monitoring range, low cost, convenient use and maintenance.

In view of the problems posed by low pozzolanic activity and large water requirement of normal consistency in the direct light calcinating of electronic fluorine-containing sludge as cement admixture, this paper uses coal gangue as a supplementary silicon and aluminum source of electronic fluorine-containing sludge to mix electronic fluorine-containing sludge and coal gangue and then to prepare cement admixture by light calcinating. This paper studied the effect of cement admixture prepared by light calcinating electronic fluorine-containing mixed with sludge coal gangue on cement properties through strength activity index, mechanical properties of cement, water requirement of normal consistency, setting time, particle size, X-ray diffraction and scanning electron microscopy. The results show that compared with direct light calcinating of electronic fluorine-containing sludge to prepare cement admixture, light calcinating of electronic fluorine-containing sludge mixed with coal gangue can improve the particle gradation of cement and reduce the water requirement of normal consistency of cement. It can significantly improve the activity of cement admixture and the strength of ordinary portland cement. Significantly extending the initial setting time and shorten the final setting time of cement.

In the process of intelligent coal mine construction, there are problems such as the 'data island' phenomenon, low data quality, lack of data governance system, and insufficient data empowerment. In order to solve the above problems, this paper analyzes the basic requirements of intelligent coal mine big data governance. This paper studies the key technologies of intelligent coal mines such as data acquisition and storage, data cleaning and standardization, data asset planning, data sharing and exchange. Combined with the field practice of data governance in Xiaobaodang Coal Mine, the overall technical architecture of intelligent coal mine big data governance based on the Industrial Internet system is proposed. The architecture functions correspond to the basic requirements of intelligent coal mine big data governance. It realizes the access, integration and fusion of multi-source heterogeneous perception data downward, provides data services for the development of various coal mine intelligent applications upward, and sediment various business indicators and model algorithms of coal mines in the middle, forming important data assets for coal mines. Unified access to to data form various coal mine systems is achieved through data access storage services based on different data access protocols. The necessary protocol conversion and data preprocessing are realized during the access process. The data processing is achieved through data cleaning and standardization services to improve data quality. The data is transformed into systematic data assets by adopting a hierarchical governance architecture. Finally, data assets are provided to other systems through standard interfaces through data sharing services, achieving the implementation of data value. The practical application of intelligent coal mine data governance achievements in different business scenarios is demonstrated from the perspective of coal mine single system application, mine-level application and company-level system application. After unified data governance, intelligent coal mine big data can achieve data fusion applications. It can break data islands, improve data quality, form coal mine unique data assets, and provide important value for coal mine production and operation.

Some key targets will be missed when using coal-gangue image recognition technology to recognize coal-gangue. Compared with the image target recognition model, the video target recognition model is closer to the requirements of the coal-gangue recognition and separation scene. The coal-gangue features in the video data can be extracted more widely and deeply. However, the influence of frame repetition, frame similarity and contingency of key frame on the model performance is not considered in the current coal-gangue video target recognition technology. In order to solve the above problems, this paper proposes an aggregation enhanced coal-gangue video recognition model based on long and short-term storage (LSS) model. Firstly, the key frames and non-key frames are used to screen the massive information. Multi-frame aggregation is carried out on the video frame sequence of the coal-gangue. The feature information of the key frame and the adjacent frame is aggregated through temporal relation networks (TRN), and a long-term video frame and a short-term video frame are established. The calculation amount of the model is reduced while the key feature information is not lost. Secondly, the feature weights among the long-term video frames, the short-term video frames and the keyframes are reallocated by using an attention mechanism that integrates semantic similarity weights, learnable weights and region of interest (ROI) similarity weights. Finally, the LSS module is designed to store the effective features of long-term video frames and short-term video frames. The module fuses them in the key frame recognition to enhance the characterization capability of the key frame features, so as to realize coal-gangue recognition. The model is tested based on the coal-gangue video data set in Zaoquan Coal Preparation Plant. The results show that in comparison with the memory enhanced global-local aggregation (MEGA) network, the flow-guided feature aggregation for video object detection (FGFA), the relation distillation networks (RDN) and deep feature flow for video recognition (DFF) model for video recognition, the mean average precision of the aggregation enhanced coal-gangue video recognition model based on LSS is 77.12 % and better than that of other models. The recognition precision of the modes is negatively correlated with the moving speed of the target in the video. The recognition precision of the model in this paper is 83.82% for the slow-moving target detection, and the performance is the best.

Coal-based energy structure of China has not only guaranteed energy supply, but also brought a lot of fly ash, because of the low utilization rate of fly ash has caused serious environmental pollution and farmland occupation problems, especially in Northwest China. At present, the extraction of useful components has become a research hotspot of high-value utilization of fly ash, especially the extraction of amorphous silicon in it an important means to improve the value of resource utilization of fly ash. In this paper, two main processes of extracting amorphous silicon from fly a share described, namely alkali leaching and acid leaching. The principle and characteristics of the process are analyzed and the application of products by silicon extraction in the insulation material, silica black, molecular sieve, filling of paper and rubber is discussed. Compared with the products of traditional silicon-based, the various of silicon-based products prepared by fly ash have the advantages of better performance, lower cost and more wider application, which can be regarded as an effective way to realize the high-value, fine and cascade utilization of fly ash.

Due to the exploitation of mineral resources in the deep underground space, it is more and more important to study the variation trend of deep in-situ stress field. In recent years the researches have updated many in-situ stress data. It is necessary to improve the existing estimation methods on this account. Based on the basic theory of elasticity and spherical shell model, this paper studied the effect of gravitational body force varying with depth and internal pressure, and obtained the theoretical formula of macro in-situ stress distribution; Employing the latest and widely distributed measured data, this paper fitted the crustal physical parameters in the theoretical formula, and obtained the fitting formula of vertical in-situ stress and average horizontal in-situ stress varying with depth. The results show that: the distribution of crustal stresses with depth is no longer linear on the macroscopic scale of the Earth; however, within the current depth range of human activities, basically the average in-situ stresses vary linearly with depth, which is closest to the results of the Dinnick hypothesis at γ=22 kN/m3 and λ=0.9; with the increase of depth, the average lateral pressure coefficient gradually approaches 1, which is closer to the measured data than the envelope proposed by Brown and Hoek; the high pressure in the crust will cause horizontal tensile stress, but the compressive stress generated by gravity is higher and therefore the vertical and horizontal in-situ stress in the whole crust are compressive stress. The research results provide a theoretical prediction model for the estimation of crustal stress distribution trend, especially in deep underground space.

Based on the fracture mechanics theory of the isotropic Hoek-Brown strength criterion, this paper established the initiation conditions of the bifurcated microcrack along bedding which begins with the meso-fracture mechanism of laminated rocks. Then the author substituted the critical angle which indicates that the initial crack most likely causes the fracture of the rock into above established conditions and derived the anisotropy expression of the parameter m1 for the weak plane of bedding leading to the crack deflection. Through introducing the correction coefficient for the mixed fracture of the rock along the bedding and the matrix, this paper obtained the anisotropic modified model of Hoek-Brown strength criterion. Compared with the established anisotropic Hoek-Brown model and shale triaxial test results, the validity of the model was proved. The modified model inherits the fracture mechanics analysis of the isotropic Hoek-Brown strength criterion for the selection of rock failure characteristic quantity, and reflects the microscopic failure mechanism of the rock, also considers the effect of bedding anisotropy. The parameters in the modified criterion have a clear physical meaning. The parameter m in the model is related to the angle of the bedding plane, the tensile strength, compressive strength and friction coefficient of bedding and matrix. The change in the friction coefficient of the bedding plane will cause the position of the minimum value of m and the rock strength characteristics changed.

Rock heterogeneity (such as mineral inclusions, micro-cracks, micro-voids and other microstructures) significantly affects its nonlinear mechanical behavior and failure process. This paper utilizes the Fast Fourier transform-based(FFT) numerical method which does not require meshing of complex microstructure but directly obtains the microstructure of heterogeneous materials through the pixels of the image. In addition, the method can be naturally combined with digital image processing (DIP). An actual-microstructure-based FFT method is thereby developed to simulate the elastoplastic behavior of the heterogeneous rocks under external load. The influence of microstructure on the nonlinear behavior is discussed as well as the internal relationship between the microstructure and the macroscopic mechanical properties. The results show that the real-microstructure-based FFT method can well predict the nonlinear behavior before and after the peak strength of the rocks under different depths and confining pressures. The shape, size and distribution of microstructure directly determine the distribution of stress field in clay rock. The actual-microstructure-based FFT method proposed in this paper can reasonably consider the rock heterogeneity, and provides an important tool for studying the influence of the rock microstructure characteristics on the nonlinear mechanical behavior.

This paper analyses the development status and technical characteristics of intelligent and networked technologies for conventional ground automatic driving. This paper also analyses the coal mine environmental characteristics, such as no GNSS (global navigation satellite system) signal coverage, low roadway illumination, lots of obstructions and obstacles and ubiquitous coal dust. In the context of the above technical and environmental characteristics, this study puts forward the key technologies of automatic driving research in underground coal mine. The technologies include mobile high-precision positioning technology without GNSS, laser radar technology, underground obstacle detection technology based on millimeter wave radar, underground low illumination video real-time enhancement and characteristic matching technology, underground environment high-precision map technology, underground autonomous vehicle decision planning technology, underground autonomous vehicle control execution technology, underground 5G communication technology and C-V2X direct connection communication technology. It is pointed out that the application of automatic driving in underground coal mine has the advantages of significant demand for fewer people or no people, clear operation management subject, closed scene, fixed route, slow speed, controllable permeability, good 5G construction foundation, easy open interface, etc. The reference architecture of 'human-vehicle-roadway-cloud' coal mine underground network connected automatic driving system is constructed. The system includes underground automatic driving vehicle, roadway infrastructure, personnel, coal mine cloud/edge computing platform and coal mine automatic driving application service platform. This paper designs the coal mine automatic driving vehicle architecture, which includes perception positioning system, network connected collaborative system, vehicle-mounted operating system and vehicle basic components. This paper puts forward three stages of the evolution of the network connected automatic driving in underground coal mines. The first stage is remote control and automatic driving, which realizes the transfer of vehicle drivers from underground to ground. The second stage is the automatic driving of vehicles with emergency takeover boundary. The vehicles are mainly driven by automatic driving, and remote emergency takeover is used as a safety guarantee method. The third stage is 'human-vehicle-roadway-cloud' collaborative control, the underground autonomous vehicles operate safely, efficiently and autonomously to realize highly unmanned intelligent transportation.

This paper introduces the development and application status of intelligent auxiliary transportation technology in open-pit coal mine and underground coal mines at home and abroad. The intelligent auxiliary transportation system of open-pit coal mine has realized the functions of unmanned driving, automatic loading, automatic unloading, active obstacle avoidance and intelligent dispatching of mining trucks in fixed sections. And the system has achieved good application results in engineering practice. At present, the auxiliary transportation intelligence of underground coal mine is still in the development stage of single machine intelligence of equipment. The intelligent auxiliary transportation system integrating vehicle scheduling, operation status monitoring, traffic command, material control and other functions has not yet been formed. The main problems of intelligent auxiliary transportation system in underground coal mine are analyzed. The underground positioning system has low precision and poor real-time performance. The dispatching system function lacks effective integration. The driving assistance system module is not perfect. The unmanned driving technology lags behind and the test conditions are lacking. Based on the relevant requirements of intelligent auxiliary transportation in Coal Mine Intelligent Construction Guide (2021 edition), this paper puts forward the overall goal of the construction of intelligent auxiliary transportation. According to the overall goal, the intelligent coal mine auxiliary transportation system framework is designed. ① Coding and centralized loading transportation of materials realizes the whole process information management and control of materials from storage, coding, loading, transportation, unloading and recycling. ② Automatic loading and unloading and automatic connection realizes the automatic transfer and connection of materials among rail locomotives, monorail cranes, trackless and other different auxiliary transportation modes. ③ Accurate positioning and intelligent navigation achieves accurate real-time positioning, route planning and real-time navigation of personnel and transportation equipment. ④ Intelligent vehicle dispatching realizes the functions of auxiliary transportation comprehensive information display, data transmission, status monitoring, dispatching command and health management. ⑤ Driving assistance system builds several intelligent subsystems, such as anti fatigue driving warning, 360° panoramic look around monitoring, collision prevention, traffic sign identification, auxiliary braking for downhill driving, adaptive lighting, etc. Driving assistance system improves the safety of locomotive operation. ⑥ The auxiliary operation robot realizes the robot automatic operation of underground auxiliary operation scenes. The auxiliary operation robot reduces the number of personnel and improves the overall automation level of auxiliary operation. ⑦ Unmanned driving realizes the normal unmanned driving operation of locomotives in underground coal mine. The research can provide reference for the construction and development of intelligent auxiliary transportation system.

As one of the most important factors in the production process of open-pit mine, the intelligence of transportation is an important research content of the whole intelligence technology of mine. This paper introduces the composition and classification of the transportation system in open-pit mine. It is clarified that the intelligent transportation system in open-pit mine takes the efficient transportation of coal and rock in open-pit mine as the application scenario and the intelligent transportation equipment as the core carrier. The digital technologies such as the Internet of things, cloud computing, big data, artificial intelligence, and mobile Internet are integrated with the operating principles and technological requirements of the open-pit mine transportation system. The autonomous collaborative and efficient operation system of equipment, environment and materials in the transportation system is established. And the real-time, accurate and efficient transportation integrated management system that plays a role in a wide range is further established. The components of the intelligent transportation system in open-pit mine mainly include infrastructure, transportation tools and computing technology. It is pointed out that the difference between the traditional transportation system and the intelligent transportation system in open-pit mine lies in that the intelligent transportation system takes improving the safety and efficiency of field production operation as the goal. The service object is changed from the original production management personnel to the production operating personnel. The research and application status of intelligent transportation system in open-pit mine in China are summarized from five aspects, including intelligent infrastructure, intelligent equipment, intelligent management and control, intelligent maintenance and intelligent design. The key technologies of the truck transportation system and the belt conveyor transportation system in the open-pit mine to realize the intelligence are analyzed in this paper. The key technologies of intelligent truck transportation include environment perception technology for complex road conditions in mines, line control transformation technology for unmanned driving truck, multi-objective intelligent scheduling technology, and intelligent collaboration technology for manned-unmanned mixed equipment group. The key technologies of intelligent belt conveyor transportation include autonomous traverse technology of belt conveyor in working face, transportation technology of self-moving large-angle belt conveyor, operation control technology of belt conveyor, on-line status detection technology of belt conveyor, intelligent inspection technology of belt conveyor, unmanned maintenance technology of belt conveyor, intelligent management and control platform of belt conveyor transportation system. It is pointed out that the development trend of intelligent transportation in open-pit mine is continuous, unmanned, low-carbon, efficient coordination and intrinsic safety.

Rare earth, as an important industrial raw material, has been listed in the strategic materials list by many countries. In recent years, with the development of new energy and other technologies, the demand for rare earth is increasing, so various developed countries have launched a rare earth secondary resources comprehensive utilization research work. In this paper, Based on tracking and analyzing a large number of books and papers, the present situation of comprehensive utilization of rare earth secondary resources at home and abroad and the existing problems in domestic rare earth secondary resources are summarized from three aspects: the present situation of rare earth secondary resources industry in major developed countries, the situation of rare earth secondary resources recovery in China and the existing problems in China. The research direction of rare earth secondary resources in the next step is pointed out.

In order to obtain the fracture development characteristics of the working face with extra-large mining height under the condition of thick overburden and medium mining depth in mining areas in China's western regions, this paper adopted a comparative study by combining empirical equations, numerical simulation and field measurement in the panel 12401 of the Shangwan coal mine.The results show that the empirical equations drawn from data from the typical geological conditions of mining areas in eastern and western China are difficult to apply to this panel with extra-large mining height, thick overburden and medium buried depth.The prediction values of the empirical equations based on data from the geological condition in the western mining regions are generally higher, which are significantly smaller in the eastern mining regions.The value predicted by the numerical simulation based on the damage constitutive model is closer to the measured value than those derived from using empirical equations, with a relative error of less than 5 %.The paper obtained the characteristics of the water-conducting fracture zone development: due to the existence of soft and hard rock in the overburden, the water-conducting fracture zone develops upward as a step, and the shape changes from "arch"(three-dimensional "shell") to "saddle"(three-dimensional "basin shape") with the variation of mining degree.

Data is the core resource to promote the development of intelligent coal mine technology, innovation of application mode and improvement of market competitiveness. Data governance is the key bottleneck for the development of smart mine from primary stage to advanced stage. However, at present, there is no consensus on the concept connotation, development goal and key technologies of data governance for smart mine. In order to solve the above problems, this paper analyzes the important position of data governance in the construction of smart mines, and defines the concept and connotation of data governance for smart mine. Data governance for smart mine is guided by the governance concept of 'precipitation, reuse, sharing and collaboration'. All departments within the coal enterprise work together with industry and government regulatory departments to formulate data standards and management specifications. The data structure and data transmission link of coal enterprises are reshaped to break through the data barriers of smart mines and ensure data quality and data security. The smart mine technology linkage and business collaboration mechanism are built to realize the process of digital-driven decision-making and flexible production. This paper discusses the development goal of data governance for smart mine from three aspects, including overall goal, development strategy and phased tasks. It is pointed out that the key point of data governance for smart mine is to solve the problem of information isolated island in the process of smart mine construction. Therefore, the data sharing and business collaboration are realized so as to make smart mine become an organic whole to promote the value enhancement of coal enterprises. Smart mine data governance needs to properly handle the five aspects relationships, including local coordination and overall coordination, physical integration and logical integration, intelligent business system and data governance platform, group-level data governance platform and mine-level data governance platform, and local processing and cloud processing. It is proposed that smart mine data governance needs to break through six key technologies, including data standard, global data modeling, data aggregation, data development, data management and data center architecture.

Through the analysis and processing of monitoring data, the prognostics health management (PHM) technology for mine inverter power devices can extract signal characteristics, locate the open circuit fault position of power devices, predict the life of power devices and improve the safety and reliability of mine inverter. This paper introduces the principle and research status of signal characteristics extraction method in PHM technology, including coordinate transformation method, spectrum analysis method, wavelet analysis method, empirical mode decomposition method. This paper introduces the principle and research status of power device open circuit fault diagnosis method in PHM technology, including state estimation method, neural network method, support vector machine method. This paper introduces the principle and research status of power device life prediction method in PHM technology, including analytical model method, physical model method, data-driven method. The above methods are compared from five aspects, including implementation difficulty, timeliness, immunity, accuracy and data demand. The signal characteristic extraction method is single. There is open-circuit fault of multiple power devices of mine inverter. The life prediction of power devices based on data-driven method fails to consider the variable working conditions of inverter. In order to solve the above problems, the research directions of PHM technology for mine inverter power devices are proposed. The directions include signal characteristic extraction based on multi-method fusion, open-circuit fault diagnosis of multiple power devices based on intelligent algorithm, fault-tolerant control and health management, and power device life prediction under variable working conditions.

In order to accurately identify mine microseismic signals, this paper proposes a VGG4-CNN deep learning network model suitable for identifying mine microseismic signals. The model is written in Python language and built based on the PyTorch deep learning network architecture framework. Based on the time-domain characteristics of the microseismic signals of 9 types of events such as rock fracture, blasting operations, and background noise in the mine production process, VGG4-CNN has realized the supervised learning training and classification recognition application of 3 835 sets of mine microseismic signal data. The research results show that the recognition accuracy of the VGG4-CNN neural network constructed in this paper is as high as 94 %. This model does not require denoising of the original waveform signal and is more robust than other models. The implementation can be performed by a medium-level GPU to meet engineering requirements.

Coal is the guarantee energy in China, and its dominant position in energy will not change for a period of time in the future. Coal intelligent mining will show a rapid development trend and enter into a new stage of development. Through induction and analysis, the great significance, development law, contradiction, construction method and future development direction of intelligent construction of coal mine are summarized in this paper. This paper systematically expounds the reform process of coal mining technology and management mode in China, and summarizes the five stages of manual mining, ordinary mining, comprehensive mechanized mining, automatic mining, primary intelligent mining, as well as the corresponding technical modes. Breaking through the intelligent research ideas such as traditional coal roadheader mining, this paper puts forward 10 characteristics of medium and high-level intelligent mining technology of coal, namely, complete transparency of coal mine, comprehensive intelligence of perception, high-end intelligence of equipment, real-time reliability of network, integrated platform control, intelligent analysis of data, group collaboration intelligence, professional team employees, dynamic decision-making intelligence, disaster prevention and control matching, and gives the definition, characteristics, content and function of each characteristic. Based on the premise of medium and high-level intelligent technology, the corresponding ‘1+1’ management and control mode of coal mine mining is conceived, that is, one level is set in one coal mine, and a new flat platform management and control mode of ‘one command and control center+one professional team’ is constructed. Therefore, the mode can promote the reform of production mode, match the requirements of corresponding mining mode in the future intelligent rapid development and realize the real meaning of reducing personnel, increasing safety and improving efficiency. Finally, the further development of intelligent mining technology and mode in coal mine is prospected.

The existing research only analyzes the rock burst appearance characteristics under specific conditions, lacks research on the rock burst appearance induced by coal pillar under the condition of thick and hard roof. In order to solve this problem, taking I010203 working face of a mine in Xinjiang as the research object, the paper analyzes the characteristics and causes of working face rock burst under the condition of thick and hard roof multi-seam mining by means of field monitoring and numerical simulation. By analyzing the spatial distribution law of microseismic and large energy events monitored on site, the distribution characteristics of support pressure, and the distribution characteristics of surrounding rock stress during the mining of the working face simulated by numerical simulation, this paper obtained the following results. The stress concentration and the microseismic event density in the transport roadway area of the working face are higher than those in the return air roadway area. And the stress concentration and microseismic event density in the roof and coal seam area are higher than those in the floor area. Based on the above results, the causes of coal pillar rock burst appearance in the mining process of I010203 working face are analyzed by using rock burst caused by dynamic and static combined load theory. ① It is easy to produce lateral overhanging roof above the coal pillar in the transport roadway section. The sudden breaking of the long overhanging roof generates a large amount of dynamic loads. At the same time, a large amount of static loads accumulate on the coal pillars and the roof during the mining process. When the superposition of the two exceeds the critical load, it may cause the rock burst appearance of the working face or a large energy event. The mining process of the I010203 working face mainly includes the main controlling factors such as coal pillar concentrated stress, overlying roof and surrounding rock supporting stress. Therefore, it is easy to produce coal pillar type and thick hard roof caving type rock burst appearance. ② When the mining position of the working face gradually approaches the boundary of the ‘knife shape’ goaf, the boundary stress is transferred downward to the I010203 working face, which leads to the further increase of the rock burst risk of the I010203 working face.

Intelligent coal mine data classification and coding is a key part of intelligent coal mine data governance and fusion sharing standard system. However, there is no perfect methodology system. It is urgent to deeply study the technical objectives, technical principles and key technical processes of intelligent coal mine data classification and coding. Based on the analysis of the core problems to be solved in the process of data classification and coding in the advanced stage goal realization of the intelligent coal mine, the essence of intelligent coal mine data classification and coding is expounded. Intelligent coal mine data classification and coding is the recognition and construction of the intelligent coal mine information world, the optimization and mapping of the intelligent coal mine consciousness world, and the transformation and description of the intelligent coal mine physical world. This paper analyzes the goal requirements of intelligent coal mine data classification and coding from three aspects of overall strategic objectives, business strategic objectives and functional strategic objectives. Intelligent coal mine data classification and coding should promote the reshaping of the business mode of coal enterprises, change the value creation driving mode, focus on key value activities, and realize the scientific organization of intelligent coal mine data. The paper proposes that the intelligent coal mine data classification and coding should follow the basic principles of scientificity, standardization, integrity, uniqueness and effectiveness. The paper also proposes the basic idea of intelligent coal mine data classification and coding. Intelligent coal mine should adopt the data classification idea of 'benchmark- expansion' two stages. In the first stage, the logical sequence of 'business domain - data domain - object - attribute - data element' is adopted to determine the classification benchmark of intelligent coal mine data. In the second stage, the logical sequence of 'intelligent application system - intelligent business system - system functions - data resources' is adopted for data classification, verification and supplement. The hierarchical coding method of line classification should be adopted for intelligent coal mine data coding. Based on the above basic ideas, it is pointed out that in general, intelligent coal mine data classification and coding needs to focus on five key steps: determining business domain, determining data domain, identifying object classes, extracting object class attributes and defining data elements.

The comprehensive control of coal mine disasters is a key problem to be solved in the process of intelligent mine construction. It is an inevitable requirement for the construction of intelligent mines to realize the normalization control of coal mine disasters with the help of digital twin technology. Based on the connotation and essence of the digital twin, this paper analyzes the recognition rule of the digital twin and puts forward the application mode of digital twin technology in coal mine disaster research combining with data interactive process of mine disaster digital twin. Real-time monitoring is carried out by coal mine underground disaster monitoring sensor. The monitoring data is uploaded to the cloud through the edge communication module and cloud communication module. The digital twin numerical simulation software is deployed in the cloud. The monitoring data uploaded by the sensor is used as the initial condition parameter, boundary condition parameter and effect verification parameter. The best optimization parameters and solutions are sought through real-time simulation analysis and continuous trial and error. When the technical means are mature in the twin world, they can be used to analyze, judge and make decisions on the best parameters and solutions for virtual entities. The decision instructions can be sent to underground actuators to control the action of disaster prevention equipment. This paper discusses the practical application of digital twin enabling disaster predictive management and control from three aspects: disaster monitoring scheme optimization, disaster rehearsal and precise planning of disaster avoidance route, and post-disaster rescue scheme formulation and accident investigation. Based on the 'cloud-pipe-edge-end' architecture of the industrial Internet, the digital twin service system for coal mine disasters is constructed. The key technologies of digital twin for mine disasters are analyzed. The technologies include intelligent sensing and execution equipment for coal mine disasters, simulation software for coal mine disasters and common support technologies. It is expected to provide reference for the construction of digital twin-enabling intelligent mines.

The gangue is wrapped by slurry in underground coal mine, which causes difficult coal-gangue recognition and sorting. The underground working space is narrow, so the equipment layout is difficult, and the diversion of coal-gangue is difficult. Therefore, developing a high-performance, highly reliable intelligent coal-gangue sorting robot is necessary. The paper analyzes the research status of coal-gangue recognition, robot trajectory plan and multi-dynamic-target multi-robot collaborative control technology of intelligent coal-gangue sorting robot. This paper points out that the coal-gangue sorting work environment is complex, and its weight and shape of coal-gangue are irregular and randomly distributed. Therefore, the three key technologies for intelligent coal-gangue sorting robot are recognition and grasping features extraction of coal-gangue in complex environment, stable and reliable grasping of coal-gangue in unstructured environment, and intelligent collaborative sorting of multi-target multi-robot. It is proposed that in order to realize the intelligent sorting of coal-gangue by the robot, further research should be carried out. The research includes the methods of coal-gangue recognition and sorting feature extraction suitable for underground, accurate positioning and synchronous tracking of dynamic targets, online trajectory planning of mechanical arms, and intelligent collaborative control of multiple mechanical arms. By soring out the above three key technologies, it can be concluded as follows. The construction and expansion of coal-gangue data set, recognition and grasping features extraction of coal-gangue are the key technologies to achieve efficient coal-gangue recognition. Precise tracking of dynamic coal-gangue, trajectory planning of synchronous tracking dynamic target of mechanical arm and fast and stable grasping of large quality targets are the key technologies to realize stable coal-gangue grasping by mechanical arms. Multi-task efficient allocation, anti-collision path planning and intelligent collaborative control are the key technologies to achieve efficient intelligent collaborative sorting of multiple mechanical arms. According to the common problems at present, this paper puts forward the solutions. In the aspect of recognition, the method of coal-gangue recognition and grasping feature extraction based on multi-mode deep learning is studied to realize fast coal-gangue recognition suitable for the underground. In the aspect of trajectory planning, the precise positioning and real-time tracking methods of dynamic coal-gangue are studied to realize the adaptive and stable grasping of dynamic coal-gangue by the robot. In the aspect of collaborative sorting, a multi-layer multiple mechanical arms collaborative control model is built to achieve efficient intelligent collaborative sorting of multiple mechanical arms in the complex environment.

The subsidence prediction method is very important for predicting the negative impact induced by coal mining.Probability integral method is an important method for mining subsidence prediction, but for irregular working face mining, its prediction accuracy needs to be improved.Aiming at this problem, the Green formula was used in this paper to transform the formula of the probability integration method, and convert the integration of the working face to the line integration of the boundary of the mining area; the boundary of working face was simplified and divided into multiple straight line segments, and each straight line segment was integrated separately; the prediction of the movement and deformation of any point on the surface and the surface subsidence basin was completed through superposition calculation; finally, an application study was carried out based on a certain example, which verified effectiveness of the method in this paper.Compared with the result of the probability integration method, the prediction accuracy of the line integral proposed in this paper was improved by 23 %.

The paper puts forward a perception and alarm method of rock burst and coal and gas outburst based on temperature. The infrared thermal imager is used to monitor the temperature of objects, and the methane sensor is used to monitor the concentration of ambient methane. When the temperature of the objects is higher than the ambient temperature of the coal mine and the temperature of the exposed coal rock, and the number, volume and area of objects that are higher than the ambient temperature and the temperature of the exposed coal rock are large, it is determined that rock burst, coal and gas outburst, mine fire or gas and coal dust explosion accidents have occurred. The temperature of the high temperature object is further determine. If it is greater than the set threshold, it is determined that a mine fire or a gas and coal dust explosion accident has occurred. Otherwise, it is determined that a rock burst or a coal and gas outburst accident has occurred. The change of methane concentration is further analyzed. If the methane concentration rises rapidly, it is determined that a coal and gas outburst accident has occurred. Otherwise, it is determined that a rock burst accident has occurred. The paper puts forward a perception and alarm method of rock burst and coal and gas outburst based on velocity. The lidar, millimeter-wave radar, ultrasonic radar, binocular vision camera are used to monitor the moving speed of objects. The methane sensors are applied to monitor the concentration of ambient methane. When the moving speed of the object is not less than the set threshold, it is determined that rock burst, coal and gas outburst or gas and coal dust explosion accident have occurred. The number, volume and area of objects with abnormal velocity is further determined. If the number of objects with abnormal velocity is small, the volume and area are small, it is determined that a gas and coal dust explosion accident has occurred. If the number of objects with abnormal velocity is large, the volume and area are large, it is determined that a rock burst or a coal and gas outburst accident has occurred. The changes of methane concentration are further analyzed. If the methane concentration increases rapidly, it is determined that a coal and gas outburst accident has occurred. Otherwise, it is determined that a rock burst accident has occurred. A multi-information fusion method for perception, alarming and judging disaster source of rock burst and coal and gas outburst is proposed. The method monitors and integrates various information such as temperature, speed, acceleration, burial depth, sound, air pressure, wind speed, wind direction, dust, methane concentration, equipment status, micro-seismic, geosound, stress, infrared radiation, electromagnetic radiation and images so as to monitor the pressure and coal and gas outbursts. The source of the disaster is determined through the magnitude of parameter changes at different locations, the sequence relationship and sensor damage.

Low-power carbon monoxide sensor is an important guarantee for safe coal mining and a key foundation for distributed wireless sensing technology. In this paper, the working principle of low-power carbon monoxide sensor is described, and the latest research progress of electrochemical and semiconductor carbon monoxide sensor is introduced. This paper analyzes their advantages and disadvantages and proposes the development direction and prospects of low-power carbon monoxide sensor. ① The electrochemical carbon monoxide sensor is mainly composed of electrodes and electrolyte. There are two-electrode structure and three-electrode structure. The two-electrode electrochemical carbon monoxide sensor has no reference electrode. It has a simple structure and is easy to be designed and manufactured. The sensor has a low cost and is suitable for the monitoring of low-concentration carbon monoxide. The three-electrode electrochemical carbon monoxide sensor introduces a reference electrode with a larger range and higher accuracy, but the cost is high. The electrochemical carbon monoxide sensor has a short response time and has the prospect of distributed wireless sensing applications. The research focus is on the preparation of platinum-carbon composite electrodes. However, the electrochemical carbon monoxide sensor still uses liquid solvent, which has the risk of liquid leakage. Moreover, it is difficult to realize micro-miniaturization. The future development trend is to avoid the use of liquid solvents, to study all solid-state electrochemical carbon monoxide sensors, and to control the porosity to shorten the response and recovery time. On the other hand, the trend is to find cheap and efficient electrode materials to reduce sensor costs. In addition, manufacturing micro-miniaturized electrochemical carbon monoxide sensor is also an important part of future work. ② The semiconductor carbon monoxide sensor can be divided into non-micro-heating plate type and micro-heating plate type. The non-micro-heating plate type carbon monoxide sensor uses a ceramic tube substrate or an alumina plate substrate. Due to the large heater size, severe heat conduction and high power consumption with usually above 100 mW, it is difficult to be used in distributed wireless sensing occasions. The micro-heating plate type carbon monoxide sensor has low thermal quality, which can greatly reduce the operating power consumption of the heater. It is also compatible with integrated circuit process. A system-on-chip carbon monoxide sensor can be obtained, which reduces the power consumption of peripheral circuits and is suitable for IoT applications. The micro-heating plate type carbon monoxide sensor is smaller than solid electrolyte electrochemical carbon monoxide sensor, and has the advantages of low cost, high sensitivity and easy on-chip integration. However, it is easily affected by humidity and the baseline is easy to drift. The future research direction is to improve the modification of sensitive materials, optimize the packaging process, and use intelligent algorithms to self-calibrate the baseline. It is proposed to use zeolite to modify sensitive materials to reduce the impact of humidity on the sensor, or use a water-repellent membrane such as polytetrafluoroethylene in the packaging process. The intelligent algorithm can use a combination of support vector machines and artificial neural networks or artificial intelligence algorithms. In the future, it is hoped that high-efficiency edge computing can be achieved to improve the efficiency and accuracy.

Most of the existing communication networks except 5G exist in the form of independent private networks. The performance of 5G wireless communication in bandwidth, delay, number of terminal connections, and reliability has been greatly improved. Accordingly, there are new changes in network architecture and networking mode. The private network scheme is no longer a single independent private network scheme. There are also hybrid private networks and virtual private networks. This paper introduces the key technologies of 5G private network, such as network slicing, mobile edge computing, 5G LAN, time-sensitive network and so on. This paper proposes three kinds of 5G private network schemes, namely virtual private network, hybrid private network and independent private network. The virtual private network has the characteristics of wide service scope, high flexibility, low cost, and short construction cycle. It is used for various applications which have wide coverage, have access terminals not fixed in time and space, and have certain service quality requirements and certain degree of data isolation requirements. The hybrid private network has short transmission path, high security, and low end-to-end delay. It can carry out a variety of flexible independent services, but privacy is weak. The independent private network provides a physical exclusive 5G private network to meet the needs of industrial users for high bandwidth, low delay, high security and high-reliability data transmission. This paper puts forward the general principles of 5G private network scheme selection in terms of safety, availability and reliability. This paper also proposes the special requirements of 5G private network in coal mine in terms of dispatching function, integration demand, independent operation and maintenance and intrinsic safety. The selection of 5G special network scheme for coal mine is proposed. In the early stage of intelligent construction of coal mine or there is no strict requirements on data confidentiality, system use convenience, system function expansion in the coal mine, the virtual private network or hybrid private network scheme can be selected. Otherwise, the independent private network scheme can be selected. It is pointed out that relatively more hybrid private network and virtual private network schemes are adopeted in coal mines at present. The hybrid private network and virtual private network will have some advantages in the future. With the gradual establishment of small core network ecology, the independent private network scheme will be recognized by more users. In a certain period in the future, the independent private network, virtual private network and hybrid private network schemes will give full play to their respective advantages. They serve the intelligent construction of coal mines in different periods and with different requirements.

When shield machine is driving for a long distance, it is often forced to stop due to obstacles or excessive wear of tools, which is one of the main risks of shield construction. In order to summarize the research progress of shield opening technology in urban metro, the paper systematically summarizes the two technical ideas of normal pressure opening and pressurized opening, and summarizes the principle, risk factors and principles of shield opening under two technical conditions. Combined with typical engineering examples, the application scope, key technology, advantages and disadvantages of conventional compressed air and saturated gas method with pressure opening technology are analyzed and summarized. The engineering application of atmospheric pressure opening technology and atmospheric pressure cutter disc tool changing technology for soil grouting and freezing reinforcement is summarized. Finally, combined with the current research progress and the development trend of large diameter underwater shield in China, the paper analyzes the technical challenges faced by the shield opening in the future, discusses the direction of further research, and provides a reference for the development of shield opening technology in China.

Active pressure relief is an important measure for source controlling of rockburst in coal mines. The current active pressure relief prevention and control method, or using the arranging holes along the roadway of the mining face, or underground in-situ hydraulic fracturing technology, has some shortcomings such as limited pressure relief protection range and constrained by the progress of pressure relief operation. When a surface hydraulic fracturing prevention system is used, it has the advantages of a wide range long-term of pressure relief, but may have the problem of high early investment, etc. Therefore, adhering to the innovative strategic ideas for pressure relief to prevent and control rock burst, which is from the source, prevention and economic efficiency, it is imperative to propose a new type of regional pressure relief source prevention technology system that is easy to practice, significant in effect, and can be comprehensively promoted. This paper proposes a new pressure relief technology system for high level whole layer pre-blasting of overlying rock. To blast higher key layers that can generate dynamic loads, the innovative high level rock tunnels, high level drilling sites, and blasting drilling arrangements are used to evenly pre-crack high level entire hard rock layers in advance, thus forming an “artificial pre-fracture layer”. This method breaks through the general limit of long drilling distance, greatly improving the pressure relief height, range, and effect of rock blasting, and can form a high-level “artificial pre-fracture layer” that covers the entire working face area or even multiple working faces before mining. The “artificial pre-fracture layer” of high level blasting first significantly weakens the weighting distance and weighting strength of the high level hard rock layer. Secondly, it also cushions and weakens the mining pressure transmitted downwards by the hard rock layer above it. Finally, it can also reduce the weighting step of the hard rock layer below it. After conducting the first “artificial pre-fracture layer” technology test for high level blasting pressure relief of overlying rock at the 3409 working face of Tingnan coal mine, the on-site measurement results show that compared to conventional blasting pressure relief areas, the average pressure strength, pressure step distance, pressure duration distance, and pressure alarm frequency of the support are significantly reduced using this method. The stress in both deep and shallow holes of the roadway is also reduced. The total energy of microseismic events and high-energy microseismic events have significantly decreased, and the intensity has significantly decreased. Microseismic events in the middle section of the working face are particularly sparse. The burst risk area obtained from seismic source CT and the high energy AE events has also been reduced, and various actual measurement methods have verified the superiority of the artificial pre-fracture layer pressure relief prevention technology for high-level blasting.

Coal seam water injection is a proactive and curative measure to prevent coal mine dust hazards and also one of the essential means to prevent and control gas protrusion, impact ground pressure, and other disasters. However, many coal seams in China are characterized by high ground stress, low porosity, and low permeability, and the traditional methods and techniques face some bottlenecks such as complex water injection, long water injection cycle, and pseudo-wetting of coal. To this end, using liquid CO2 with excellent characteristics such as low-temperature freezing, high permeability, phase change self-pressurization, acidification, and unblocking, the authors put forward a new idea of fracturing and wetting coal by liquid CO2-water circulation, developed an automatic control test system of cold dipping by liquid CO2 circulation. The influence law of liquid CO2-water cycling on the pore structure of coal was investigated using low-field nuclear magnetic resonance (LF-NMR) instrumentation, and the mechanism of change in the physical properties of coal by cyclic action was investigated using an electro-hydraulic servo-pressure experimental machine. The dust production characteristics of cyclic action on the coal crushing process were investigated using the coal rock-cutting dust production experimental system. The results show that the liquid CO2-water circulation increased the effective porosity (\begin{document}${\varphi _{{\mathrm{NF}}}} $\end{document}) of the coal, and the increase was positively correlated with the number of circulations. The bound fluid inside the coal become less, the free fluid increased, and the T2cutoff value decreased. Combined with the fractal theory, it was found that based on the fractal dimensionality, Ds of seepage porosity had prominent fractal characteristics. The primary pores of the coal underwent the “enlargement” process. Microfracture and original fracture formed a through, and the circulation increased the connectivity of the effective seepage channel and optimized the coal’s porosity network and seepage conditions. With the increase in the number of cycles, the coal’s maximum stress value (\begin{document}${\sigma _{\mathrm{c}}} $\end{document}) decayed exponentially to 4.93 MPa and the strain value (\begin{document}${\varepsilon _{\mathrm{c}}} $\end{document}) increased linearly to 2.29%, the compressive strength of the coal weakened, the deformation capacity increased, the cyclic action changed the state of the coal matrix interconnection, and the resulting freezing and expansion forces exerted extrusion on the coal exacerbated the expansion of the fissures, and the brittleness index B5 decreased by the maximum amount of 34.71%, which significantly weakened the brittleness of coal, and had a better resistance to dynamic load or impact. The weakening of the storage capacity of the coal body for the applied energy changed the form of coal destruction in the cutting process, and the whole dust production rate of the coal body cutting under the test conditions of this paper was reduced by 74%. The percentage of respiratory dust was reduced to 2%, drastically weakening the dust’s hazardousness.

Coal pillars in soft and thick coal seam are often tall and have large exposed coal walls, and the coal quality is soft with some developed cracks, which can easily cause an instability of coal pillars and make roadway maintenance difficult. This paper takes the No. 3 coal seam in the Fuyan Coal as the engineering background, based on the shear sliding block theory, explores the mechanism of coal pillar deformation and failure under mining influence, analyzes the width of the coal pillar’s limit equilibrium zone and stress distribution rules, and reveals the movement mechanism of the coal pillar’s shear sliding block. Based on this, the cooperative control strategies for coal pillar stability are proposed and verified through engineering practice. The results show that: ① by using the limit equilibrium theory and the superposition theory, the range of shear sliding block movement of the coal pillar and the vertical stress distribution law of the coal pillar are determined, and the distribution law of the safety factor of the coal pillar shear sliding block is clarified. The safety factor of the upper part of the coal pillar is small at a depth of 0−1.26 m. In the area of 1.26−3.95 m, the central part of the coal pillar has a large area of small safety factor and is vulnerable to damage from the roof. ② A cooperative control technology for coal pillar is proposed, which is based on “reinforcement anchor cable-grouting reinforcement-advance cutting roof”, and it effectively controls the deformation and bottom bulging of the coal pillar. The side cracks of the coal pillar without supporting conditions and those with original supporting conditions are reduced by 62.89% and 46.26%, respectively. The integrity of the surrounding rock of the roadway is greatly improved, forming a strong bearing structure. ③ According to the conditions of coal pillar in the thick and soft coal seam section, the design parameters of coordinated control are reasonably determined, and the prevention and control effect of coal pillar is evaluated by test monitoring. The field test results show that the cracks in coal pillar are fully filled, and the strength of coal body is increased by more than 63% after grouting. The roadway displacement, anchor cable stress, and separation layer are all within the controllable range, indicating that the cooperative control technology significantly improves the bearing capacity of the coal pillar, and effectively controls the deformation of the surrounding rock of the mine roadway, providing space guarantee for safe and efficient mining.

The construction of intelligent fully mechanized mining faces in China’s coal mines is in its early stages, and the automation technology of hydraulic support electro-hydraulic control has been widely applied. However, at present, the automation control logic of a single solidification of hydraulic supports is difficult to adapt to complex, ever-changing, and dynamic production scenarios. The actual control process in mine face still mostly adopts a collaborative approach of automation and manual intervention. In response to the demand for human-machine interaction and cooperation tasks in the complex scenarios of fully mechanized mining faces, a theoretical method and technical principle of a multimodal human-machine collaborative control system for hydraulic supports following the shearer in the middle range mining face (hereinafter referred to as hydraulic supports following) was proposed. Firstly, four human-machine collaborative modes, namely manual, division of labor, approval, and veto, were designed. Based on the factors such as coal seam geology, gas and dust, shearer speed, hydraulic support intelligence level, system status, job technical level, and task load, an AND-OR graph model for hydraulic support human-machine collaborative mode selection was constructed, which achieved a modal selection with manual or machine preferences. Then, a human-machine collaborative control decision-making mechanism for hydraulic supports following was designed. On this basis, an AI inference technology for the secondary control strategy of hydraulic supports following was proposed. Specifically, using on-site data to learn manual operation experience, a decision tree classification model for whether the hydraulic support should be secondary controlled and a Bayesian regression model for estimating the secondary control time of pulling hydraulic support were constructed. Based on the above model, a human-machine collaborative control decision-making program for the hydraulic support following was developed, which achieved human-machine collaborative control of hydraulic supports following based on AND/OR inference for modal selection and AI inference for secondary control strategy. Finally, using cloud edge end architecture software and hardware technology, a multimodal human-machine collaborative control system for hydraulic supports following was developed, which achieved the control functions such as model evolution, operational reasoning, and program execution. The system has undergone industrial trial operation on the 3404 mining face of Shaqu No.2 Mine. The result shows the efficiency of the hydraulic support following has increased by an average of 2% compared to that before. This paper forms an efficient and safe human-machine interactive decision-making mechanism for the comprehensive mining equipment group, which will provide practical theoretical methods and feasible technical paths for the development of intelligent comprehensive mining working faces.

Localization and mapping of the underground ramps is one of the key technologies for achieving unmanned driving of underground mining trucks. The underground ramp is a typical unstructured environmental feature, and the road has a certain inclination angle. However, the traditional SLAM algorithm cannot obtain accurate odometer information, which makes the accuracy of positioning and mapping difficult to meet the driving requirements of unmanned mine trucks. To overcome above problems, this paper proposes a positioning and mapping method suitable for underground ramp environments in mines by studying the laser SLAM (Simultaneous Localization And Mapping) algorithm LeGO-LOAM. Firstly, in terms of the characteristics of smooth cement walls and sparse features on both sides of the underground ramp, a manual landmark-based auxiliary enhancement positioning method is designed, effectively increase the number of point cloud features, to optimize the pose estimation results and avoid the phenomenon of mapping drift. Then, in the feature preprocessing stage, a highly efficient algorithm for extracting ground points based on the fusion of laser point cloud height difference and slope information is proposed, by improving the selection strategy of ground points, which can effectively be identified for sloped potholes, to solve the problem of large inclination angle and error in underground ramps. Next, a slope point cloud surface voxel clustering algorithm based on the CVC (Curved-Voxel Clustering) clustering algorithm is designed, using the curvature voxels and hash-based data structures to segmentation of point clouds, which significantly improve the robustness of point cloud clustering in sparse and noisy environments underground. Finally, the Scan-To-Map is used for point cloud registration, while balancing the performance and speed of point cloud alignment. The on-site experiment in an underground ramp of Shandong, Sinosteel Group proved that the proposed method has improved the accuracy by 13.15% and reduced the Z-axis error by 22.3% compared with the original algorithm. The quality of the map has been significantly improved, which can effectively solve the problem of mapping and positioning in underground autonomous driving.

Hydrogen, as an important clean energy source that can be used as an alternative to fossil energy, can reduce global greenhouse gas emissions. However, the large-scale hydrogen industry requires large reservoirs to store hydrogen, and the use of underground reservoirs to store large amounts of hydrogen has become a new topic. In this paper, 11 coal samples with different metamorphic degrees of Carboniferous-Permian in Ordos Basin, Qinshui Basin and Ningwu Basin of China were investigated. Based on the specific surface area and total pore volume, the amount of hydrogen adsorbed by coal rock was evaluated by hydrogen isothermal adsorption experiment and Langmuir model. The mechanism of hydrogen adsorption by coal rock was discussed in combination with coal quality, organic geochemistry, mineral and pore structure characteristics. The results show that the Langmuir model is suitable for the calculation and evaluation of the potential of simulating the hydrogen adsorption of coal rock. Coal rock with different metamorphic degrees has high hydrogen adsorption capacity, and the higher the metamorphic degree, the higher the organic matter abundance and the more developed micropores, the higher the hydrogen adsorption capacity. Hydrogen in coal rock is mainly physically adsorbed on the surface of coal rock by van der Waals force. With the increase of coal rock metamorphic degree, the more micropores formed by organic matter, the more pore volume and total specific surface area provided by organic matter, which increases the amount of hydrogen adsorption, and the higher pore connectivity can improve the efficiency of hydrogen entering pores and being adsorbed. The amount of hydrogen adsorbed by coal rock will increase with the increase of pressure, but due to the reasons such as intermolecular repulsion, the adsorption rate will decrease, and the hydrogen storage will reach saturation. The development of deep coal seams in China provides a good foundation for hydrogen storage in coal seams. However, due to chemical reactions, competitive adsorption and other problems, hydrogen will be lost and lost in coal-rock reservoirs. The use of high pressure for hydrogen storage or acquisition of hydrogen will cause irreversible damage to the structure of coal-rock reservoirs, which has adverse effects on the use of coal-rock reservoirs for one or more storage of hydrogen. Deep coal seams with high metamorphic degree have certain potential as hydrogen storage horizons but further research is still needed to overcome some key problems such as hydrogen loss and reservoir damage.

Electromagnetic radiation and vibration monitoring technologies are widely used in the monitoring and early warning of dynamic disasters in underground engineering, which is of great significance to the safe and efficient development of underground engineering. In-depth study of electro-seismic signals is helpful to promote the development of granite mass monitoring and early warning technology. However, the current analysis of electromagnetic radiation and vibration signals (electro-seismic) mainly focuses on the correlation and time-frequency characteristics of signals. There are few studies on the nonlinear dynamic characteristics of granite fracture electro-seismic signals, and the relevant characteristics are not yet clear. Based on this, this paper uses the combination of empirical mode signal (EMD) reconstruction and fractal theory to analyze the chaotic characteristics of electro-seismic signals of granite splitting failure, and reveals the nonlinear dynamic characteristics of electro-seismic signals. The results show that the electromagnetic radiation generated by granite splitting failure is in good agreement with the vibration signal in time, and the frequency spectrum of the electro-seismic signal generated by splitting failure is concentrated in the middle and low frequency band. The box dimension of the effective electromagnetic radiation signal of granite failure is DE=1.6006, and the box dimension of the effective vibration signal is DA=1.5948, and the frequency structure characteristics of the two are highly similar. The effective electromagnetic radiation and vibration signals of granite fracture can be obtained by the EMD decomposition and reconstruction method. It is more accurate to describe the chaotic characteristics of granite fracture electro-seismic signals by using the EMD decomposition and reconstruction to remove the interference of high frequency. The effective electromagnetic radiation on the vibration signal contains more low-frequency and high-energy signals than the original signal, which characterizes the propagation of small cracks. The non-uniformity of the reconstructed electro-seismic signal is significantly higher than that of the initial signal, and the frequency relationship of different energy signals decreases. The reconstructed effective electro-seismic signal is mainly low-frequency and high-energy signals, but the non-uniformity of the vibration signal is greater than that of electromagnetic radiation.

In order to solve the problem that most of the existing mine-used smart phones only have the functions of voice calls, video photos, data transmission and so on, and do not have the functions of precise positioning, position coordinate display, message linkage, an identification card based on UWB technology is designed. The identification card realizes two-way data communication with the smart phone through low-power bluetooth. The identification card completes the precise positioning with the UWB station using the TOF positioning algorithm, obtains the position coordinate information, sends it to the smart phone through the low-power bluetooth (BLE), and displays the current specific position coordinates through the mine GIS roadway map on the smart phone APP. This paper introduces the key technologies of the identification card in detail, including mine roadway position coordinate model, precise positioning algorithm, message linkage reliable transmission mechanism, low power consumption sleep technology. The test results show that the positioning accuracy of the identification card is less than ± 0.3 meters, the positioning distance can reach 400 meters, the message linkage transmission delay is less than 2 seconds, the position coordinate display is accurate, the sleep current of the positioning module is less than 25 uA, and the average current meets the low power consumption design requirements.

The study on impact tendency of coal body containing gas under unloading damage plays a key role in exploring the formation mechanism of coal and gas combined rock burst in deep underground mine. In order to explore the influence of unloading action on impact tendency of coal body containing gas, this paper carried out cyclic loading and unloading of coal body containing gas with varying upper limit under different unloading amplitude conditions. The test results show that: gas has a deterioration effect on mechanical properties of coal. Under 9 MPa confining pressure, the average compressive strength of coal specimens under 1 MPa and 2 MPa methane action decreases by 11.2% and 18.7%, respectively. Under the unloading amplitude of 3 MPa and 6 MPa, the compressive strength σc decreases by 12.6% and 36.5%, and the residual elastic energy index CEF decreases by 10.4% and 16.7%, respectively. For coal containing 1 MPa gas, σc decreases by 13.5% and 39.8%, and CEF decreases by 15.9% and 43.6%, respectively. For coal containing 2 MPa gas, σc decreases by 16.7% and 47.2%, and CEF decreases by 20.3% and 48.5%, respectively. With the increase of unloading range, the mechanical property of coal specimen decreases continuously, and the gas action will further aggravate the unloading deterioration degree, and the deterioration degree will gradually deepen with the increase of gas pressure. In addition, pressure relief can effectively reduce the impact tendency of coal body. Meanwhile, the deterioration degree of impact tendency index of coal body containing gas after unloading is higher than that of original coal specimen, and with the increase of gas pressure, the reduction degree of residual elastic energy index is higher.

Coal particles carried by the gas extraction flow are easy to be deposited in the mining-induced fracture, which seriously reduces the flow rate of gas extraction. Mastering the deposition characteristics of particles in the fracture is an important basis for improving the flow rate of gas extraction. In this paper, we carried out a particle transport and deposition experiment in the fracture with a shrinkage, and studied the particle deposition bed evolution law after crossing the shrinkage under the influence of the gas extraction flow. In addition, we analyzed the influence of the gas velocity and shrinkage structure parameter on the particle deposition law of the back end of the shrinkage of the fracture and the local resistance of the gas flow. The results show that the granular sedimentary bed at the back end of the fracture shrinkage shows two kinds of evolution patterns. When the particle deposition bed is distributed in a “V” shape along the airflow direction, the deposition height of the granular deposition bed shows an evolution pattern of rapid increase followed by a slow decrease. When the depositional zone is a “Ʌ” shaped deposition along the direction of flow, the depositional height shows an evolutionary pattern of slow increase and then slow decrease. In addition, with the development of the particle bed in the fracture, the local resistance changes at the back end of the fracture shrinkage can be divided into the initial stabilization stage, the rapid development stage and the final stabilization stage. The evolution time of the initial stabilization stage is shortened with the increase of the pumping rate or the decrease of the shrinkage ratio. The evolution time of the rapid development stage is shortened with the increase of the pumping rate or the increase of the shrinkage ratio.

The surface cracks caused by mining have a significant impact on the safety production of coal mines. Utilizing unmanned aerial vehicle (UAV) image recognition to identify the development characteristics of cracks in coal mining subsidence areas holds practical value. In this paper, an improved YOLOv7 model for intelligent recognition of mining-induced cracks is proposed. It incorporates the GAM global attention mechanism into the backbone network of the model to reduce the loss of feature information during the image convolution process. Additionally, depth-wise separable convolutions are introduced to replace the ordinary convolutions in the backbone network, which reduces the size of the image feature map without causing feature loss during the convolution process. Furthermore, GIOU_Loss is further used to improve the network boundary frame loss function, which improves the small target identification ability of the model. For the experiments, a training dataset for mining-induced crack recognition was created using the LabelImg image annotation software, containing 2 143 images with a resolution of 5 472×3 648 pixels. After initial preprocessing of the UAV images in the subsidence area to construct a digital orthophoto model (DOM), the DOM was further cropped using a sliding window of size 640×640 for feature recognition. The experimental results demonstrate that the improved YOLOv7 model exhibits significant improvements in the recognition performance and missed detections of dense, small-sized, and vegetation-covered crack images. The average precision (mAP) reaches 0.84.

In order to quantitatively analyze the risk caused by each operational step of coal mine blasting and comprehensively and objectively assess its risk, with the help of Monte Carlo method, this paper establishes a risk assessment model of coal mine blasting operation steps, makes cumulative probability distribution of the behavioral risk consequence value of the operation process, and finally determines the risk size and risk level of each operation step based on the mean result of Monte Carlo simulation and the overall risk result of the operation process, and puts forward the measures for the control of the occurrence of such unsafe behaviors. The results of the study show that the order of risk of the blasting operation process is in the following order: clearing the items into the warehouse, loading, linkage, guarding, safety inspection after detonation, receiving and checking the blasting items, detonation, delivery of blasting items, acceptance of the task of blasting, preoperational safety inspection, pre-detonation safety inspection, sealing the holes.

At present, the detection of mining subsidence basins by interferometric synthetic aperture radar (InSAR) mainly relies on underground mining data or human visual interpretation. To solve this problem, this paper proposes a deformation basin detection network (DBD-Net) for large-scale InSAR interferograms. At the same time, in order to train the network, a sample database of mining subsidence basins is established by using real differential interferogram data and simulated interferogram data. In Shendong Mining Area and Yanzhou Mining Area, three differential interference images with different time baselines were selected to verify the network performance. The results show that the detection accuracy of deformation basin detection network (DBD-Net) in large-scale InSAR interferograms for mining subsidence basins is 81.87%. Most of the missed and false detection areas are areas with serious noise pollution and unclear characteristics.

To enrich the research methods for studying the development law of bed separation, this paper takes the upper 08 working face of 221 in Shilawusu Mine as the research object, and comprehensively determines the location of bed separation through distributed optical fiber (BOTDR) and fixed-point optical fiber. The particle flow code (PFC2D) is used to study the pattern of the separation layer development under the conditions of large mining height and large mining depth. The results show that, as the working face advances away from the cutting hole, the separated layer develops intermittently from the bottom to the bottom of the key layer, and the depth of separation layer development is around 440 m, 396 m, 376 m, 331 m, 321 m and 296 m, and the layer stops at the bottom of the main key layer of coarse sandstone. The overburden transport mainly goes through the stages of subsidence of the lower key layer, rapid subsidence of the upper sub-key layer, development of overburden movement towards the bottom of the main key layer of coarse sandstone, and transport of the main key layer. The separated layer position is proportional to the advancement distance of the working face, and the development of the separated layer is mainly divided into three stages, which are gestation (Ⅰ)-accelerated expansion (Ⅱ)- compression stage (Ⅲ).

Spontaneous combustion of coal in goaf is one of the main factors inducing mine fire, which accounts for 90% of mine fire. In order to achieve accurate prevention and control of spontaneous combustion in goaf, it is necessary to accurately obtain the high temperature point temperature in goaf. Based on Yanbei Coal Mine as the engineering background, this paper analyzes the index gases produced during the oxidation and heating process of coal samples, establishes the index system of coal spontaneous combustion temperature prediction, and then carries out the research of multi-index gas coal spontaneous combustion temperature prediction based on deep learning. Firstly, the coal samples collected from Yanbei Coal Mine were tested for coal oxidation and temperature rise. According to the experimental results, they were divided into single gas index and compound gas index. The change law of each index with temperature rise was analyzed, and the appropriate index was determined as the prediction index of coal spontaneous combustion temperature. The prediction index of coal spontaneous combustion temperature is processed by multi-source data processing method, the data is cleaned by Cook distance method and multiple interpolation method, and the prediction index system of coal spontaneous combustion temperature is established by grey correlation analysis method. Elman neural network was used to build a prediction model, and after determining the model structure and hyper-parameters, a prediction model of coal spontaneous combustion temperature was established to obtain an accurate prediction of the temperature in the process of coal oxidation and heating.

Knowledge graph is an indispensable part of cognitive intelligence research.Aiming at the problem that the traditional analysis method of stope mine pressure hazard events has insufficient expression of the stress time and space evolution process and the relationship between hazard evolution and risk prevention and control in the coal mining process, this paper proposes a knowledge graph representation method that based on the entire life cycle of stope for mining pressure hazard events.Firstly, from the perspective of geological disasters, the dynamic characteristics of stress and distribution in stope were analyzed.The dynamic correlation of various nodes in mine pressure geological disasters was established, and a knowledge graph representation method for mine pressure geological disasters considering spatiotemporal processes was proposed.Secondly, from the perspective of accidents, the evolution of hazard and the process of risk prevention and control in mine pressure accidents were analyzed.The evolution of hazard and preventive measures were integrated into the knowledge graph representation model.Finally, Neo4j was used to build the knowledge graph of mine pressure hazard events.The results indicate that the knowledge graph constructed based on this representation method not only depicts the spatiotemporal evolution processes of different objects in disaster events but also describes the coupling evolution process of hazards and corresponding risk prevention and control measures.This provides an intelligent research pathway for the prevention and control of mining pressure hazards in intelligent mining.

Using aeolian sand(AS)for backfilling can realize local material extraction and turn waste into treasurethe, and realize coordination of green mining and AS control.The AS filling mining is mainly applied to the backfilling of goaf under Highway, backfilling mining of coal mine and metal mine.Grouting and sand injection in the goaf, solid backfilling mining, high water backfilling mining and cemented backfilling mining are developed.Long wall backfilling mining, strip backfilling mining and roadway backfilling mining are adopted.The research on the properties of cemented AS backfilling materials focused on slurry fluidity and backfill strength.In this paper, the rheological properties of cemented AS slurry with different proportions and curing times are analyzed, and cemented AS backfills are toughened by using polypropylene fiber.The results showed that the rheological parameters of cemented AS slurry increased with the curing time, and the addition of fiber significantly improved the brittleness characteristics of cemented AS backfills.