基于同步压缩小波变换和CNN的滚动轴承故障诊断  

Fault diagnosis of rolling bearing based on synchrosqueezed wavelet transform and CNN

作　　者：唐纪凯 卢一相[1,2] 柏壮壮 高清维 TANG Jikai;LU Yixiang;BAI Zhuangzhuang;GAO Qingwei(School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China;Key Laboratory of Intelligent Computing and Signal Processing,Anhui University,Hefei 230601,China)

机构地区：[1]安徽大学电气工程与自动化学院,安徽合肥230601 [2]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230601

出　　处：《传感器与微系统》2022年第6期130-133,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61402004,61370110);安徽省教育厅重点资助项目(KJ2018A0012)。

摘　　要：以智能诊断为出发点,提出一种基于同步压缩小波变换(SWT)和卷积神经网络(CNN)的诊断方法。首先,对振动信号进行SWT获得时频图,随机划分为训练和测试集;然后,利用CNN强大的特征提取能力提取时频图特征;最后,利用SoftMax层进行故障模式的自动诊断。实验结果表明:该方法在滚动轴承的故障诊断中具有较高的可靠性。An intelligent diagnosis method based on synchronous compression transformation and convolutional neural network(CNN)is proposed.Firstly,the vibration signals are compressed and transformed synchronously to obtain time-frequency graphs,which are randomly divided into training and test sets.Then,the powerful feature extraction capability of CNN is used to extract time-frequency map features.Finally,SoftMax layer is used for automatic diagnosis of fault mode.The experimental results show that this method has high reliability in fault diagnosis of rolling bearings.

关 键 词：滚动轴承 故障诊断 同步压缩小波变换 卷积神经网络 

分 类 号：TH133[机械工程—机械制造及自动化] TP391[自动化与计算机技术—计算机应用技术]