Shanxi Yangcheng Yangtai Group Xiaoxi Coal Industry Co., Ltd.

为解决在煤矿开采设备运行中,设备故障频发常导致非计划性停机,影响生产效率问题,采用时序对齐技术处理设备监测数据,基于长短期记忆(LSTM)网络构建故障预测模型,通过对国家能源集团神东煤炭集团公司上湾煤矿的采煤机数据分析,选取与故障密切相关的因素,进行模型训练与测试。实验结果显示,模型能有效预测采煤机的过热跳闸故障,达到26min的超前预警,显著提升了设备的安全性与可靠性,对于提高煤矿开采设备的故障预警能力具有重要意义。

To solve the problem of frequent equipment failures leading to unplanned shutdowns and affecting production efficiency in coal mining equipment operation, time-series alignment technology is used to process equipment monitoring data. A fault prediction model is constructed based on Long Short Term Memory (LSTM) network. By analyzing the data of the coal mining machine in Shangwan Coal Mine of Shendong Coal Group Company of National Energy Group, factors closely related to the faults are selected for model training and testing. The experimental results show that the model can effectively predict the overheating trip fault of the coal mining machine, achieving a 26 min advance early warning, significantly improving the safety and reliability of the equipment, and is of great significance for improving the fault early warning capability of coal mining equipment.