基于柔性形态滤波和支持矢量机的滚动轴承故障诊断方法  

Fault Diagnosis Approach for Rolling Bearing Based on Support Vector Machine and Soft Morphological Filters

作　　者：于湘涛[1] 褚福磊[1] 郝如江[1] 

机构地区：[1]清华大学精密仪器与机械学系,北京100084

出　　处：《机械工程学报》2009年第7期75-80,共6页Journal of Mechanical Engineering

基　　金：国家杰出青年科学基金(50425516);国家自然科学基金重点项目(10732060);国家高技术研究发展计划(863计划;2006AA04Z438)资助项目

摘　　要：针对滚动轴承故障振动信号的强噪声背景以及现实中不易获取大量典型故障样本的特点,提出一种基于柔性形态滤波和支持矢量机(Support vector machine,SVM)的滚动轴承故障诊断方法。柔性形态滤波既可以有效地提取出信号的边缘轮廓和信号的形状特征,同时又具有稳健性;SVM具有良好的分类性能,特别在小样本、非线性及高维特征空间中具有较好的推广能力;SVM分类器的惩罚因子和核函数参数采用经典粒子群优化算法进行优化,避免传统方法对初始点和样本的依赖。首先对振动信号进行柔性形态滤波,然后提取滤波后信号的故障特征频率的归一化能量为特征矢量作为SVM分类器的输入参数,用于区分滚动轴承的外圈、内圈和滚动体故障,SVM分类器的参数采用标准粒子群优化算法进行优化。试验结果表明了方法的有效性。Based on soft morphological filters and support vector machine （SVM）, a roller bearing fault diagnosis method is proposed. It is very difficult to filter the fault vibration signals from the strong noise background because the roller bearing fault diagnosis is a problem of multi-class classification. Soft morphology filter can not only identify the features of fringe and shape of the signals but also give improved performance under certain conditions. Support vector machine has good classification performance especially in the small-sample, nonlinear and high dimensional features and so on. The penalty factors and kernel parameters of SVM are optimized by using particle swarm optimization to avoid dependence on initial parameters and training samples. Firstly, vibration signals are filtered by the soft morphological filters. Secondly, the normalized energy of the different characteristic frequencies is utilized to identify the fault features of input parameters of SVM classifier. The SVM parameters are optimized by using the canonical particle swarm optimization. The experiment results indicate that the modeling method is correct.

关 键 词：柔性形态滤波 支持矢量机 粒子群优化 特征提取 故障诊断 

分 类 号：TH165[机械工程—机械制造及自动化]