首页 | 本学科首页   官方微博 | 高级检索  
     

基于支持向量机的齿轮故障诊断方法研究
引用本文:王凯,张永祥,李军.基于支持向量机的齿轮故障诊断方法研究[J].振动与冲击,2006,25(6):97-99.
作者姓名:王凯  张永祥  李军
作者单位:海军工程大学,航舶与动力学院,武汉,430033
摘    要:故障样本的不足从一定程度上制约了基于知识的方法在实际故障诊断中的应用,针对这一问题,利用支持向量机在小样本情况下具有较强分类能力的特点,提出了一种基于支持向量机的齿轮故障诊断方法。该方法采用小波变换对齿轮的振动信号进行处理来构造特征向量,并直接输入到支持向量机的多故障分类器中进行故障识别。试验结果表明该方法是有效、可行的,且在小样本情况下比BP神经网络具有更高的诊断精度。

关 键 词:支持向量机  齿轮  故障诊断  多故障分类器
收稿时间:11 24 2005 12:00AM
修稿时间:01 9 2006 12:00AM

Study on Diagnosis Method of Gear Fault Based on Support Vector Machine
Wang Kai,Zhang Yongxiang,Li Jun.Study on Diagnosis Method of Gear Fault Based on Support Vector Machine[J].Journal of Vibration and Shock,2006,25(6):97-99.
Authors:Wang Kai  Zhang Yongxiang  Li Jun
Abstract:Lack of fault samples restricts application of methods based on knowledge in practical fault diagnosis to a certain extent.In order to solve this problem,a diagnosis method of gear fault based on a support vector machine is proposed with advantage that a support vector machine has strong classification ability with fewer samples taker.According to this method,feature vectors are extracted from gear vibration signals after wavelet transform and they are input into a multiple-fault classifier of the support vector machine for fault identification.The test shows that this method is effective and feasible, and has higher diagnosis precision than BP neural network in cases of fewer samples.
Keywords:support vector machine  gear  fault diagnosis  multiple-fault classifier
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号