特征选择可以从原始特征集中去除冗余特征,选择出优化特征子集,提高机械故障诊断精度和诊断效率.将进化蒙特卡洛方法引入机械故障诊断的特征选择.应用支持向量机(SVM)作为故障决策器,采用Wrapper式特征子集评价标准,并采用进化蒙特卡洛算法搜索最优特征子集.运用滚动轴承故障振动信号数据对提出的方法进行验证,实验结果表明该方法是有效的.%Feature selection can eliminate redundant features in an original feature set, find an optimal subset of features and enhance classification accuracy and efficiency in machine fault diagnosis. A feature selection method based on evolutionary Monte Carlo was proposed. Support vector machine (SVM) was taken as a fault classifier, the evaluation criterion was the Wrapper model, and the evolutionary Monte Carlo was implemented for optimal feature subset selection. This method was used in feature selection of a rolling bearing fault diagnosis based on vibration signal. Experimental results indicated the proposed method is effective for feature selection in fault diagnosis.
展开▼