Search

This paper puts forward a three-layer construction framework of the geological model for the working face, and expounds the construction process of the coal seam model of the working face. The comprehensive dynamic interpretation technology is used for data fusion of geological, drilling and geophysical data. The multi-level and multi-attribute 3D dynamic geological model construction technology is used to establish the coal seam model of the working face. According to the cutting parameters of shearer and 3D geological model of coal seam, the cutting curve of shearer is generated to guide the coal cutting operation. It has been applied in the experimental working face. The data of roadway survey, cut-out survey, borehole gamma, borehole radar detection and trough wave detection are comprehensively interpreted. The 3D geological model of working face is constructed and distributed to the shearer through the centralized control system to guide the shearer to cut coal based on the coal seam model.

In view of problem that existing drilling orientation device for drilling rig can not meet actual demand in terms of measurement accuracy, cost and operability, a drilling orientation device for drilling rig was designed which combines north-seeking system based on single-axis fiber optic gyroscope with tracking system based on micro-inertial measurement unit. Basic principle of north-seeking system was introduced taking four-position north-seeking method as an example, and various errors and their resources of the north-seeking system were introduced from aspects of output error of fiber optic gyroscope, installation error, inclination error, inversion error and geophysical quantity error. A nonlinear acceleration error compensation model was established for installation error and inclination error. Kalman filter method was used to correct random drift error of fiber optic gyroscope. The experimental results show that the reduction of inclination angle, random drift error of fiber optic gyroscope, mechanism rotation error and installation error can effectively improve north-seeking accuracy of drilling orientation device and meet drilling requirements of underground coal mine.

This paper aims to achieve bedrock geologic mapping in the overburden area using big data, distributed computing, and deep learning techniques. First, the satellite Bouguer gravity anomaly with a resolution of 2'x2' in the range of E66°E96°, N40°-N55° and 1:5000000 Asia-European geological map are used to design a dataset for bedrock prediction. Then, starting from the gravity anomaly formula in the spherical coordinate system, we deduce the non-linear functional between rock density ρ and rock mineral composition m, content p, buried depth h, diagenesis time t and other variables. We analyze the feasibility of using deep neural network to approximate the above nonlinear generalization. The problem of solving deep neural network parameters is transformed into a non-convex optimization problem. We give an iterative, gradient descentbased solution algorithm for the non-convex optimization problem. Utilizing neural architecture search (NAS) and human-designed approach, we propose a geological-geophysical mapping network (GGMNet). The dataset for the network consists of both gravity anomaly and a priori geological information. The network has fast convergence speed and stable iteration during the training process. It also has better performance than a single neural network search or human-designed architectures, with the mean pixel accuracy (MAP) = 63.1% and the frequency weighted intersection over union (FWIoU) = 42.88. Finally, the GGMNet is used to predict the rock distribution of the Junggar Basin. [ABSTRACT FROM AUTHOR]

Based on Open CASCADE and Ordinary Kriging interpolation algorithm, a software development framework adding geostatistical interpolation algorithm to CAD geometry operation core for three-dimensional hydrogeological modeling is designed. Using three-dimensional graphics rendering of Open CASCADE, visual interaction, editing functions and geo-statistics interpolation function of Ordinary Kriging, we designed the hydrogeology modeling software for mine by taking Visual Studio as development tool, C++ and Python as development language, and SQLite as geological database, developed and Hydrogeo3D mine hydrogeology modeling software to realize the editable function of local details in the modeling process.