形态小波与模糊熵在齿轮故障分类中应用  

Application of Morphological Wavelet and Fuzzy Entropy in Gear Fault Classification

作　　者：丁伟[1] 张志刚[2] 姚练红 黄捷 DING Wei;ZHANG Zhigang;YAO Lianhong;HUANG Jie(School of Intelligent Manufacturing and Automotive, Chongqing College of Electronic Engineering, Chongqing 401331, China;Key Laboratory of Advanced Manufacturing Technology for Automobile Parts, Ministry of Education, Chongqing University of Technology, Chongqing 400054, China;Chongqing Qing Shan Industrial Technology Center, Chongqing 402761, China)

机构地区：[1]重庆电子工程职业学院智能制造与汽车学院,重庆401331 [2]重庆理工大学汽车零部件先进制造技术教育部重点实验室,重庆400054 [3]重庆青山工业有限责任公司技术中心,重庆402761

出　　处：《兵器装备工程学报》2020年第9期232-235,241,共5页Journal of Ordnance Equipment Engineering

基　　金：重庆市教委科学技术研究项目(KJ1602902)。

摘　　要：针对样本熵相似性度量函数的突变问题,提出了一种新的基于模糊熵的齿轮故障分类方法。采用形态Haar小波对实测变速器齿轮振动信号进行降噪预处理;然后利用模糊熵作为齿轮故障的特征值进行提取,包括齿轮正常、齿面轻度磨损、齿面中度磨损和断齿等4种工况的振动信号。最后依据不同的故障对应不同的模糊熵分布,对各种故障状态进行分类,同时对比了未降噪信号的模糊熵分布。结果表明形态小波与模糊熵结合能有效提高变速器齿轮故障分类能力。Focusing on the mutation difficulty of sample entropy similarity measure function,a gear failure character extraction way based on fuzzy entropy was introduced.The definition of morphological wavelet was introduced,and the morphological Haar wavelet was used to pre-process the measured gear vibration signal on transmission.Then,the fuzzy entropy was used as the eigenvalue of gear fault to extract the vibration signal,which included four working conditions:normal,slight-worn,medium-worn and broken teeth.According to different faults corresponding to different fuzzy entropy distributions,the various fault states were classified,and the fuzzy entropy distributions of non-denoised signals were compared.The example of gear fault recognition proved that the combination of morphological wavelet and fuzzy entropy could effectively improve the ability of gear fault classification.

关 键 词：形态小波 模糊熵 变速器 齿轮 故障分类 

分 类 号：TN911[电子电信—通信与信息系统]