基于WT-DBN的车轴疲劳裂纹的故障诊断  

Fault Diagnosis of Axle Fatigue Crack Based on WT-DBN

作　　者：林丽[1] 田颖[1] LIN Li;TIAN Ying(School of Locomotive and Rolling Stock Engineering,Dalian Jiaotong University,Dalian Liaoning 116028,China)

机构地区：[1]大连交通大学机车车辆工程学院,辽宁大连116028

出　　处：《机械研究与应用》2023年第3期41-45,共5页Mechanical Research & Application

摘　　要：列车车轴的工作环境复杂,当车轴产生疲劳裂纹时,用现有方法监测裂纹信号的故障信息存在不准确、不全面等问题。针对这一问题,提出一种小波变换与深度信念网络(DBN)相结合的新型诊断方法,以此来实现对车轴疲劳裂纹的故障诊断,试验结果表明:该方法不仅能够从信号数据中自适应地挖掘可用的故障特征,而且诊断准确率可以达到99.0%。The working environment of train axle is complex;when the axle produces fatigue crack,the fault information of crack signal monitored by the existing methods is inaccurate and incomplete.In view of this problem,a new diagnostic method combining wavelet transform and deep belief network(DBN)is proposed to realize the fault diagnosis of axle fatigue crack.The test results show that this method can not only adaptively extract the available fault features from the signal data,but also obtain the diagnostic accuracy of 99.0%.

关 键 词：特征提取 小波变换 故障诊断 深度信念网络 

分 类 号：U226.81[交通运输工程—道路与铁道工程]