| 基于进化蒙特卡洛方法的特征选择在机械故障诊断中的应用 |
| |
| 引用本文： | 刘晓平,郑海起,祝天宇.基于进化蒙特卡洛方法的特征选择在机械故障诊断中的应用[J].振动与冲击,2011,30(10):98-101. |
| |
| 作者姓名： | 刘晓平 郑海起 祝天宇 |
| |
| 作者单位： | 1.军械工程学院火炮工程系, 石家庄 050003；2.武汉军械士官学校, 武汉 430075 |
| |
| 基金项目： | 国家自然科学基金资助项目(50775219) |
| |
| 摘 要： | 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。
|
| 关 键 词： | 刘晓平1 郑海起1 祝天宇2 |
Feature selection in machine fault diagnosis based on evolutionary Monte Carlo method |
| |
| LIU Xiao-ping,ZHENG Hai-qi,ZHU Tian-yu.Feature selection in machine fault diagnosis based on evolutionary Monte Carlo method[J].Journal of Vibration and Shock,2011,30(10):98-101. |
| |
| Authors: | LIU Xiao-ping ZHENG Hai-qi ZHU Tian-yu |
| |
| Affiliation: | 1. Ordnance Engineering College, Shijiazhuang, 050003; 2. Wuhan Ordnance N.C.O Academy, Wuhan 430075 |
| |
| Abstract: | 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... |
| |
| Keywords: | feature selection evolutionary Monte Carlo support vector machine(SVM) fault diagnosis |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《振动与冲击》浏览原始摘要信息 |
|
点击此处可从《振动与冲击》下载全文 |
