Electromagnetic radiation interference signal recognition in coal rock mining based on recurrent neural networks

Abstract

The electromagnetic radiation (EMR) method is a promising geophysical method used to monitor and provide early warnings of coal rock burst disasters. In the underground mining process, personnel activities and electromechanical equipment produce EMR interference signals that affect the accuracy of EMR monitoring. Existing methods for identifying EMR interference signals mainly use the time and amplitude characteristics of the signals. However, these methods need further improvement. The recent advancements in deep learning provide an opportunity to develop a new method for identifying and filtering EMR interference signals. We have developed a method for EMR interference signal recognition based on deep-learning algorithms. The method uses bidirectional long short-term memory recurrent neural networks and the Fourier transform to analyze numerous EMR interference signals along with other signals to intelligently identify and filter EMR signal sequences. The results indicate that our method can respond positively to EMR interferences and accurately eliminate EMR interference signals. The method can significantly improve the reliability of EMR monitoring data and effectively monitor rock burst disasters.