Microseismic monitoring is an important tool for predicting and preventing rock burst incidents in mines, as it provides precursor information on rock burst. To improve the prediction accuracy of microseismic events in rock burst mines, the working face of the Hegang Junde coal mine is selected as the research object, and the research data will consist of the microseismic monitoring data from this working face over the past 4 years, adopts expert system and temporal energy data mining method to fuse and analyze the mine pressure manifestation regularity and microseismic data, and the "noise reduction" data model is established. By comparing the MEA-BP and traditional BP neural network models, the results of the study show that the prediction accuracy of the MEA-BP neural network model was higher than that of the BP neural network. The absolute and relative errors of the MEA-BP neural network were reduced by 247.24 J and 46.6%, respectively. Combined with the online monitoring data of the KJ550 rock burst, the MEA-BP neural network proved to be more effective in microseismic energy prediction and improved the accuracy of microseismic event prediction in rock burst mines.

微地震监测可以提供岩爆前兆信息，是预测和预防矿山岩爆事故的重要工具。为提高岩爆矿井微震事件的预测精度，选取鹤岗骏德煤矿工作面作为研究对象，研究数据包括该工作面近4年的微震监测数据，采用专家系统和时间能量数据挖掘方法，对矿井压力表现规律和微地震数据进行融合分析，建立“降噪”数据模型。通过比较MEA-BP与传统BP神经网络模型，研究结果表明MEA-BP神经网络模型的预测精度高于BP神经网络。MEA-BP 神经网络的绝对误差和相对误差分别减少了 247.24 J 和 46.6%。结合KJ550岩爆在线监测数据，证明MEA-BP神经网络在微震能量预测方面更加有效，提高了岩爆矿井微震事件预测的准确性。