The assessment of Coal burst risk (CBR) is the premise of bump disaster prevention and control. It is the implementation criterion to guide various rock burst prevention and control measures. The existing static prediction and evaluation methods for CBR cannot be effectively combined with the results of underground dynamic monitoring. This study proposed a mining-induced seismicity information quantification method based on the fractal theory. Deep learning methods were used to construct a deep learning framework of coal burst risk (DLFR) based on the fractal dimension of microseismic information. Gray correlation analysis (GRA), information gain ratio (IGR), and Pearson correlation coefficient are used to screen and compare factors. Statistical evaluation indicators such as macro-F1, accuracy rate, and fitness curve were used to evaluate model performance. Taking the Gaojiapu coal mine as a case study, the performance of deep learning models such as BP Neural Network (BP), Support Vector Machine (SVM) and its optimized model based on particle swarm optimization (PSO) algorithm under this framework is discussed. The research results' reliability and validity are verified by comparing the predicted results with the actual results. The research results show that the prediction results of CBR in DLFR are consistent with the actual results, and the model is reliable and effective. The mining-induced seismicity quantification can solve the problem of insufficient training samples for the CBR. With this, different pressure relief measures can be formulated based on the results of the CBR predictions to achieve "graded" precise prevention and control.
The magnitude and direction of the in-situ stress field significantly influence the Geodynamic disaster. Taking the Gaojiapu Coal Mine in the northwest Binchang mining area as the study area, the distribution law of the in-situ stress field and its relationship with microseismic events were analyzed and discussed through field geological investigation, in-situ measurement, and numerical simulation. The results show that: (1) The Maximum horizontal principal stress (MaxHPS) is mainly concentrated in the turning end of the fold, the axis of the syncline, the undulation end of the anticline, the footwall of the fault, and the two ends of the fault. (2) The MaxHPS in the footwall area of the fault is greater than that in the hanging wall area. (3) The MaxHPS at the axial part of the syncline is greater than that at the wing part, and the MaxHPS at the wing part is greater than that at the anticline. (4) In areas with high MaxHPS and Lateral pressure coefficient (LPC), the frequency of high-energy microseismic events is high. (5) The 105J high-energy microseismic events more easily occur in areas with MaxHPS greater than 38 MPa and LPC greater than 1.50.
The new Shanghai No. 1 Coal Mine is located in arid and semiarid area of northwest China, which is characterized by scarce rainfall, intense evaporation, and limited water resources. High-intensity coal mining has caused severe damage to groundwater resources. The Baotashan sandstone aquifer of the Jurassic system has abundant water resources, and they are stored in the floor strata of mining coal seams. This poses the risk of high-pressure build-up and water inrush hazards during the mining of coal. To avoid these, the Baotashan sandstone aquifer needs to be drained and depressurized, which can result in a huge waste of water resources. Thus, taking the New Shanghai No. 1 Coal Mine as the basis for the case study, the impact of coal mining on the underground water resources was quantified. Large-scale water release tests were performed under the shaft to determine the hydrogeological properties of the Baotashan sandstone aquifer and a three-dimensional numerical model of the groundwater system was established. The dynamic phenomenon of water drainage was simulated and the drained water discharge was predicted under the condition of safe mining.
10 June 2024 in Bulletin of Engineering Geology and the Environment