Intelligent fault prediction with wavelet-SVM fusion in coal mine

Abstract

Fault prediction in coal mining is crucial for safety, and recent technological advancements are steering this field towards supervised intelligent interpretation, moving beyond traditional human-machine interaction. Currently, support vector machine (SVM) predictions often rely on seismic attribute data; however, the poor quality of some fault data characteristics hampers their predictive capability. To localize the fault based on original seismic data and improve SVM prediction we propose the W-SVM algorithm, which integrates wavelet transform and SVM. Through wavelet transform, we localize fault features in seismic data, which are then used for SVM prediction. Validation using real data confirms the feasibility of the W-SVM approach. The W-SVM model successfully identifies 34 known faults. Beyond achieving high prediction accuracy, the model exhibits improved stability and generalization. The difference among the evaluation metrics for training, validation, and testing is within 5%. Moreover, this study localizes the response of faults through wavelet transform, simplifies the dataset preparation process, improves computational efficiency, and increases overall applicability. This advancement further promotes the development of intelligent identification of faults in coal mines.