Search

Featured Application: The XGBoost–GR–stacking gas outburst early warning model established in this article demonstrates high accuracy and practical performance, making it suitable for gas outburst risk warning in mining safety. To improve the accuracy of gas outburst early warning, this paper proposes a gas outburst risk warning model based on XGBoost–GR–stacking. The statistic is based on gas outburst data from 26 mines and establishes a data generation model based on XGBoost. The obtained virtual datasets are analyzed through visualization analysis and ROC curve analysis with respect to the original data. If the augmented data has an ROC area under the curve of 1, it indicates good predictive performance of the augmented data. Grey correlation analysis is used to calculate the grey correlation degrees between each indicator and the "gas emission". The indicator groups with correlation degrees greater than 0.670 are selected as the main control factor groups based on the sorting of correlation degrees. In this study, SVM, RF, XGBoost, and GBDT are selected as the original models for stacking. The original data and virtual data with correlation degrees greater than 0.670 are used as inputs for SVM, RF, XGBoost, GBDT, and stacking fusion models. The results show that the stacking fusion model has an MAE, MSE, and R2 of 0.031, 0.031, and 0.981. Comparing the actual and predicted values for each model, the stacking fusion model achieves the highest accuracy in gas outburst prediction and the best model fitting effect. [ABSTRACT FROM AUTHOR]

In the L Area, big data techniques are employed to manage the principal controlling factors of coalbed methane (CBM) production, thereby regulating single-well output. Nonetheless, conventional data cleansing and the use of arbitrary thresholds may result in an overemphasis on certain controlling factors, compromising the design and feasibility of optimization schemes. This study introduces a novel approach that leverages raw data without data cleaning and eschews artificial threshold setting for controlling factor identification. The methodology supplements previously overlooked controlling factors, proposing a more pragmatic CBM production adjustment scheme. In addition to the initial five controlling factors, this approach incorporates three additional ones, namely, dynamic fluid level state, drainage velocity, and fracturing displacement. This study presents a practical application case study of the proposed approach, demonstrating its ability to reduce reservoir damage during the coal fracturing process and enhance output through seal adjustments. Utilizing the full spectrum of original data and minimizing human intervention thresholds enriches the information available for model training, thereby facilitating the development of a more efficacious model. [ABSTRACT FROM AUTHOR]

Using the remaining coal seams of closed coal mines for CO2 geological storage can effectively slow down the greenhouse effect and realize the redevelopment and utilization of closed coal mines. The burial depth of coal seams in closed coal mines in China covers an extensive range, and CO2 and CH4 could exist in various phases in the coal. The existing experimental objects for CO2 adsorption in coal are mainly associated with the supercritical and gaseous phases, and a research gap comparison between the CO2 adsorption characteristics in the liquid phase and those of other phases is very obvious. Herein, the isotherm adsorption experiments of CO2 and CH4 in different phases on different rank coal samples are methodically conducted in the pressure range of 0-12MPa. The experimental results indicate that the excess adsorption capacity of gaseous CO2 and CH4 (gas pressure <4MPa) rapidly raises with the growth of the adsorption pressure; however, a significant difference for the case of the medium- and high-pressure stage (>4MPa) is detectable. With the growth of the adsorption pressure, the excess adsorption capacity of the supercritical CH4 gradually reaches the maximum value and then remains stable, where the maximum experimental value is 1.009 mmol/g. While the excess adsorption capacity of CO2 near the critical pressure of liquid and supercritical state rapidly reduces and then tends to be stable. The maximum adsorption capacity is capable of touching 2.096 mmol/g, which is stable around 0.5 mmol/g. The analysis indicates that the change in the excess adsorption amount of CO2 near the critical pressure corresponds to the change in its density. The absolute adsorption capacity of CO2 and CH4 monotonically grows in the pressure range of 0-12MPa, and the absolute adsorption capacity of the same coal sample follows the following order: liquid CO2 > supercritical CO2 > CH4. The maximum adsorption capacity values for these substances in order are 2.493, 2.345, and 1.296 mmol/g. With the growth of the coal rank, the Gibbs free energy, specific surface area, and adsorption capacity of the understudied coal samples exhibit a U-shape relationship as a function of their coal ranks. [ABSTRACT FROM AUTHOR]

To improve the accuracy of gas outburst early warning, this paper proposes a gas outburst risk warning model based on XGBoost–GR–stacking. The statistic is based on gas outburst data from 26 mines and establishes a data generation model based on XGBoost. The obtained virtual datasets are analyzed through visualization analysis and ROC curve analysis with respect to the original data. If the augmented data has an ROC area under the curve of 1, it indicates good predictive performance of the augmented data. Grey correlation analysis is used to calculate the grey correlation degrees between each indicator and the “gas emission”. The indicator groups with correlation degrees greater than 0.670 are selected as the main control factor groups based on the sorting of correlation degrees. In this study, SVM, RF, XGBoost, and GBDT are selected as the original models for stacking. The original data and virtual data with correlation degrees greater than 0.670 are used as inputs for SVM, RF, XGBoost, GBDT, and stacking fusion models. The results show that the stacking fusion model has an MAE, MSE, and R2 of 0.031, 0.031, and 0.981. Comparing the actual and predicted values for each model, the stacking fusion model achieves the highest accuracy in gas outburst prediction and the best model fitting effect.

To investigate the effect of freeze-thawing of liquid nitrogen on the pore structure and adsorption behavior of coal, the pore structure of coal samples before and after freeze-thawing was characterized by low-temperature nitrogen and CO2 adsorption method, and methane isothermal adsorption experiments were carried out under different freeze-thawing times. The results show that the hysteresis index HI of coal samples decreased after freezing and thawing, and the connectivity of the pore system was improved, which is conducive to gas migration in coal. The pores between 2 nm and 100 nm increased to varying degrees after freezing and thawing, and some pores evolved into pores smaller than their own pore size or even less than 2 nm. The microporous pore size distribution has changed, with an increase in microporous pore volume and adsorption volume. With the increase of the number of liquid nitrogen treatments, the effect of liquid nitrogen treatment on the final adsorption amount of methane kept weakening, and after reaching four treatments, the effect of liquid nitrogen treatment on the final adsorption amount of coal body almost reached saturation. The Langmuir parameters VL and pL increased after the coal samples were treated with liquid nitrogen at different times, the larger the pL, the more favorable it was for the extraction of CBM.

Featured Application: It solves the bottleneck problem of the low permeability of deep coal seams and the difficulty of coalbed methane mining, greatly improves the efficiency of coalbed methane mining, and reduces the risk of coal mining, which is of great significance to the project. To solve the bottleneck problem of low deep coal seam permeability and difficult coalbed methane (CBM) mining. Combining hydraulic splitting technology and directional drilling technology, a directional hydraulic splitting enhancement method of deep CBM mining was proposed. The selection equation for the directional hydraulic splitting of deep coalbed was constructed. The numerical simulation reveals the variation in coal fractures around different split angles. The split angle under the maximum coal damage effect was obtained. It was found that the combined effect of the double crack damage disturbance region led to reciprocal stress fluctuations during crack development and, eventually, the formation of a zigzag fracture. The larger the splitting angle, the larger the fissure development length and the larger the coal-damaged area. A double crack takes 25% less time to complete propagation than a single crack. When the splitting angle is 90°, the disturbed area occupies 2/3 of the area around the borehole, and the overall fracturing effect is the best. In the application process, the new directional hydraulic splitting technology can increase CBM mining by 5.08%, greatly improve CBM mining efficiency, and reduce the coal mining risk, which is of great significance to the project. [ABSTRACT FROM AUTHOR]

In the L Area, big data techniques are employed to manage the principal controlling factors of coalbed methane (CBM) production, thereby regulating single-well output. Nonetheless, conventional data cleansing and the use of arbitrary thresholds may result in an overemphasis on certain controlling factors, compromising the design and feasibility of optimization schemes. This study introduces a novel approach that leverages raw data without data cleaning and eschews artificial threshold setting for controlling factor identification. The methodology supplements previously overlooked controlling factors, proposing a more pragmatic CBM production adjustment scheme. In addition to the initial five controlling factors, this approach incorporates three additional ones, namely, dynamic fluid level state, drainage velocity, and fracturing displacement. This study presents a practical application case study of the proposed approach, demonstrating its ability to reduce reservoir damage during the coal fracturing process and enhance output through seal adjustments. Utilizing the full spectrum of original data and minimizing human intervention thresholds enriches the information available for model training, thereby facilitating the development of a more efficacious model.

To solve the bottleneck problem of low deep coal seam permeability and difficult coalbed methane (CBM) mining. Combining hydraulic splitting technology and directional drilling technology, a directional hydraulic splitting enhancement method of deep CBM mining was proposed. The selection equation for the directional hydraulic splitting of deep coalbed was constructed. The numerical simulation reveals the variation in coal fractures around different split angles. The split angle under the maximum coal damage effect was obtained. It was found that the combined effect of the double crack damage disturbance region led to reciprocal stress fluctuations during crack development and, eventually, the formation of a zigzag fracture. The larger the splitting angle, the larger the fissure development length and the larger the coal-damaged area. A double crack takes 25% less time to complete propagation than a single crack. When the splitting angle is 90°, the disturbed area occupies 2/3 of the area around the borehole, and the overall fracturing effect is the best. In the application process, the new directional hydraulic splitting technology can increase CBM mining by 5.08%, greatly improve CBM mining efficiency, and reduce the coal mining risk, which is of great significance to the project.

Aiming at problem that traditional mechanical instrumens and hydraulic control modes cannot meet requirements of safe, accurate and efficient construction of coalbed methane truck-mounted drilling rig, an electric control system for coalbed methane truck-mounted drilling rig was designed. The system is composed of sensors, sub-console, control box and main console. The sub-console collects parameters of diesel engine and realizes control functions such as diesel engine starting and stopping, throttle adjustment and throttle switching. The control box drives solenoid valve of hydraulic system for logical control. The main console is used for driller to observe drilling parameters and operate drilling operations. The field application results show that the system can monitor and display drilling parameters of diesel engine and drilling rig in real time and accurately, and realize logical control of diesel engine operation and drilling rig, which provides guarantee for auxiliary drilling construction and improving drilling quality.

In view of problems of poor universality, inconvenient installation and weak anti-interference ability of communication existed in current remote monitoring system of drilling rig, a remote monitoring system for coalbed methane truck-mounted drilling rig was designed. The system consists of vehicle terminal, back-end server and monitoring and management platform. The vehicle terminal collects real-time running status data of drilling rig through CAN bus, and uploads the data to the back-end server through TCP/IP protocol. The monitoring and management platform adopts B/S architecture to access the back-end server data through HTTP protocol and displays running status of drilling rig. The application results verify effectiveness of the system.

Advanced premixed micro-soft abrasive coal-water jet (APMACJ) technology is a coal-breaking, anti-reflection technology that can filter reused coal-water in situ. To determine the shock effect and variation law of micro-soft abrasive coal-water jet, the shock parameters of coal-water medium with different mass concentrations was measured, and the particle size ratio of coal-water medium was analyzed. The weight of coal particles with a particle size of <0.008 mm was determined to be directly proportional to the effective shock distance, and the relationship function between them was obtained. Subsequently, the equations of the relationship between the shock pressure and the particle weight and those of the hole expansion radius and the particle weight were derived. The maximum shock pressure of the APMACJ technology was 2.8 MPa higher than that of pure water jet, which was 46% of the theoretical coal crushing pressure. The coal-water jet has higher visibility than the water jet. Unlabelled Image • The APMSACWJ system with wastewater treatment and utilization is applied in coal mining. • Measurement of coal particles micro-soft abrasive jet shock pressure. • Determine the relationship equation between shock distance and coal particle weight. • Determine the relationship between the reaming radius and the weight of coal particles. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)