Method for EMR and AE interference signal identification in coal rock mining based on recurrent neural networks

Abstract

Electromagnetic radiation (EMR) and acoustic emission (AE) are popular geophysical methods for monitoring and providing early warnings about coal rock burst disasters. In the underground mining process, personnel activities and electromechanical equipment produce EMR and AE interference signals that affect the accuracy of EMR and AE monitoring. Currently, these signals are usually identified and filtered based on their time sequence and amplitude characteristics, but the identification and filtering methods need to be further improved. Advancements in the deep learning algorithms provide an opportunity to develop a new identification and filtering method. In this study, a method for identifying EMR and AE interference signals on the basis of deep learning algorithms is proposed. The proposed method, which is based on bidirectional long short-term memory recurrent neural networks and Fourier transform, intelligently identifies and filters EMR and AE signal sequences by analyzing numerous EMR and AE interference signals along with other signals. The results show that the proposed method can respond positively to EMR and AE interferences and accurately eliminate EMR and AE interference signals. It can significantly improve the reliability of EMR and AE monitoring data and effectively monitor rock burst disasters.