基于最小二乘支持向量机的滚动轴承故障诊断  

Bearing Fault Diagnosis Using Wavelet Packet Transform and Least Square Support Vector Machines

作　　者：万书亭[1] 佟海侠[1] 董炳辉 

机构地区：[1]华北电力大学机械工程系,保定071003 [2]河北省第二建筑工程公司,石家庄050011

出　　处：《振动．测试与诊断》2010年第2期149-152,共4页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金资助项目(编号:50677017);中央部属高校基本科研业务费专项资金资助项目(编号:09MG30)

摘　　要：根据滚动轴承故障时振动信号特点,提出了一种基于小波包变换和最小二乘支持向量机(LS-SVM)相结合的滚动轴承故障诊断方法。通过对滚动轴承振动信号进行小波包分解,得到各分解节点对应频率段的重构信号以及各节点的能量,并将各节点能量组成的特征向量作为诊断模型的特征向量,输入到LS-SVM多类分类器中进行故障识别,然后在滚动轴承故障试验台上实测振动数据。分析结果表明,该方法具有较高的分类速度和较好的故障诊断正确率。A method of rolling bearing fault diagnosis using the wavelet packet transform and the least square support vector machine(LS-SVM) was proposed according to characteristics of the bearing vibration signal.The reconstructed signal of each frequency ranges and the energy of each decomposed node was obtained by decomposing the bearing vibration signal using the wavelet packet.The energy of each node was regarded as the eigenvector of diagnosis models and was input to the LS-SVM multi-classifier to recognize failures.A test was conducted and the vibration signal was measured from a rolling bearing experiment table.The result shows that the method has a faster convergence speed and a higher degree of classification precision than conventional methods.

关 键 词：小波包变换 最小二乘支持向量机 故障诊断 滚动轴承 

分 类 号：TM31[电气工程—电机] TH115[机械工程—机械设计及理论]