基于FFT与CS-SVM的滚动轴承故障诊断  

Fault Diagnosis of Rolling Bearing Based on FFT and CS-SVM

作　　者：解晓婷 李少波[1] 杨观赐[1] 刘国凯[1] 姚雪梅[1] XIE Xiao-ting;LI Shao-bo;YANG Guan-ci;LIU Guo-kai;YAO Xue-mei(Key Laboratory of Advanced Manufacturing Technology,Ministry of Education,Guizhou University,Guiyang 550025,China)

机构地区：[1]贵州大学现代制造技术教育部重点实验室,贵阳550025

出　　处：《组合机床与自动化加工技术》2019年第4期90-94,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金(51475097);工信部智能制造示范项目(工信部联装[2016]213号)

摘　　要：针对滚动轴承故障信号强噪声背景和非线性等特点,为精确识别滚动轴承的故障特征频率并精准分类,提出了一种基于Hanning窗插值快速傅里叶变换并利用布谷鸟算法优化支持向量机的滚动轴承故障诊断新方法。采用Hanning窗对得到的频域信号进行加窗处理并求得样本特征的均方根特征值;经过布谷鸟算法优化后的支持向量机(CS-SVM)对样本数据进行故障诊断分类。通过凯斯西储大学的轴承故障振动信号数据进行的实验,验证了该混合智能诊断方法的有效性和优势,结果表明:所提出的方法可以对轴承故障准确进行分类。In view of the strong noise background and nonlinearity of the rolling bearing fault signal, a new method of rolling bearing fault diagnosis based on Hanning window interpolation fast Fourier transform and using the cuckoo algorithm to optimize support vector machine is proposed to accurately identify the fault characteristic frequency of rolling bearings. The Hanning window is used to deal with the frequency domain signals, and the root mean square eigenvalues of the samples are obtained. The support vector machine(CS-SVM), which is optimized by the cuckoo algorithm, classifying the sample data for fault diagnosis. The effectiveness and advantages of the hybrid intelligent diagnosis method are verified by the test of the bearing fault vibration signal data of Case Western Reserve University. The results show that the proposed method can accurately classify bearing faults.

关 键 词：滚动轴承 HANNING窗 快速傅里叶变换 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化] TG113.25[金属学及工艺—物理冶金]