基于LMD能量熵的齿轮箱故障诊断研究  

Research on Gearbox Fault Diagnosis Based on LMD Energy Entropy

作　　者：徐乐[1,2] 李伟 张博[2] 朱玉斌 郎超男[1] Xu Le;Li Wei;Zhang Bo;Zhu Yubin;Lang Chaonan(Engineering Training Center,Jiangsu Normal University,Xuzhou 221116,China;School of Mechatronic Engineering,China University of Mining and Technology,Xuzhou 221116,China)

机构地区：[1]江苏师范大学工程实训中心,江苏徐州221116 [2]中国矿业大学机电工程学院,江苏徐州221116

出　　处：《机械传动》2022年第10期24-29,共6页Journal of Mechanical Transmission

基　　金：国家重点研发计划项目(SQ2019YFB200140);国家自然科学基金(51475455)。

摘　　要：针对小样本情况下齿轮箱复合故障特征难以识别的问题,提出了基于局部均值分解(Local mean decomposition,LMD)能量熵的齿轮箱故障诊断方法。利用LMD方法对齿轮箱振动信号进行处理,得到若干个PF分量;利用不同状态下齿轮箱振动信号在频域区间内分布不均的特性,计算出分量能量在频域区间离散的值,即LMD能量熵;通过不同状态下LMD能量熵的分布进行了齿轮箱故障分类。结果显示,在小样本情况下,基于LMD能量熵方法能够精确地对齿轮箱故障类型进行特征提取和故障诊断,也表明了该方法对齿轮箱故障诊断的优越性。Aiming at the problem that it is difficult to identify the composite fault characteristics of gear-boxes in the case of small samples,a local mean decomposition(LMD)gearbox fault diagnosis method based onenergy entropy is proposed.The LMD method is used to process the gearbox vibration signal to obtain several PFcomponents;the dispersion value of component energy in the frequency domain is calculated using the unevendistribution of gearbox vibration signals in different states,which is the LMD energy entropy;the gearbox faultclassification is carried out through the distribution of LMD energy entropy in different states.The experimentalresults show that in the case of small samples,the feature extraction and fault diagnosis of gearbox fault typescan be accurately carried out based on the LMD energy entropy method,which also shows the superiority of thismethod in gearbox fault diagnosis.

关 键 词：齿轮箱 局部均值分解 能量熵 故障诊断 

分 类 号：TH132.41[机械工程—机械制造及自动化]