摘要
为降低机电设备运行中的故障识别误差,提高对煤矿机电设备故障检测的准确性,基于小波变换技术设计针对煤矿机电设备的故障识别方法。对机械设备的异常信号进行预处理,提取设备频段故障特征,以此为基础构建机电设备小波变换故障识别模型,采用深度神经网络(Deep Neual Networke,DNN)训练处理实现对煤矿机械设备的故障识别。通过最终的测试结果表明:对比于传统方法,所设计的小波变换故障识别方法最终得出的故障识别差值相对较小,故障识别误差较低,表明在实际识别的过程中对煤矿机电设备故障检测具有一定的准确性,有实际的应用价值。
In order to reduce the fault identification error in the operation of electromechanical equipment and improve the accuracy of fault detection of electromechanical equipment in coal mines,this paper designs a fault identification method for electromechanical equipment in coal mines based on wavelet transform technology.The abnormal signals of mechanical equipment are preprocessed,and the fault characteristics of equipment frequency band are extracted.Based on this,the wavelet transform fault identification model of mechanical and electrical equipment is constructed,and the fault identification of coal mine mechanical equipment is realized by Deep Neual Networke(DNN)training.The final test results show that compared with the traditional methods,the fault identification difference of the wavelet transform fault identification method designed in this paper is relatively small and the fault identification error is low,which indicates that in the process of actual identification,the fault detection of electromechanical equipment in coal mines has certain accuracy and practical application value.
作者
张少帅
ZHANG Shaoshuai(Shaanxi Coal Group Shenmu Ningtiaota Mining Co.,Ltd.,Yulin 719300,China)
出处
《通信电源技术》
2022年第12期13-15,共3页
Telecom Power Technology
关键词
小波变换
煤矿机电设备
故障识别
识别方法
煤矿故障
小波解析
wavelet transform
coal mine electromechanical equipment
fault identification
identification method
coal mine fault
wavelet analysis
