《计算机应用研究》|Application Research of Computers

基于离散小波变换和随机森林的轴承故障诊断研究

Research on bearing fault diagnosis based on discrete wavelet transform and random forest

免费全文下载 (已被下载 次)  
获取PDF全文
作者 彭成,王松松,贺婧,李凤娟
机构 1.湖南工业大学 计算机学院,湖南 株洲 412007;2.中南大学 自动化学院,长沙 410083
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)01-020-0101-05
DOI 10.19734/j.issn.1001-3695.2019.09.0633
摘要 针对不同工况下数据特征选择困难和单一分类器在滚动轴承故障诊断中识别率较低等问题,提出了一种基于离散小波变换和随机森林相结合的滚动轴承故障诊断方法。该方法首先利用离散小波变换分解振动信号,得到<i>n</i>层近似系数;然后创新性地采用sigmoid熵构造出<i>n</i>维特征向量,sigmoid熵能较好地提取非平稳信号的特征,提高诊断准确率;最后采用随机森林对滚动轴承不同故障信号进行分类。实验采用西储凯斯大学轴承数据中心网站提供的轴承数据,与传统分类器(KNN和SVM)以及单个分类回归树CART进行对比分析,结果表明该方法具有更好的诊断效果。
关键词 滚动轴承; 故障诊断; 离散小波变换; 随机森林; sigmoid熵
基金项目 国家自然科学基金资助项目(61871432,61771492)
湖南省自然科学基金资助项目(2020JJ4275,2019JJ6008,2019JJ60054)
湖南省研究生创新计划资助项目(CX20190847)
本文URL http://www.arocmag.com/article/01-2021-01-020.html
英文标题 Research on bearing fault diagnosis based on discrete wavelet transform and random forest
作者英文名 Peng Cheng, Wang Songsong, He Jing, Li Fengjuan
机构英文名 1.School of Computer Science,Hunan University of Technology,Zhuzhou Hunan 412007,China;2.School of Automation,Central South University,Changsha 410083,China
英文摘要 Aiming at the difficulty of data feature selection under different working conditions and the low recognition rate of single classifier in rolling bearing fault diagnosis, this paper proposed a rolling bearing fault diagnosis algorithm based on discrete wavelet transform and random forest. Firstly the proposed method decomposed the vibration signal by discrete wavelet transform to get <i>n</i>-layer approximate coefficients. Then, it used the sigmoid entropy to construct <i>n</i>-dimensional eigenvectors innovatively. The sigmoid entropy could extract the features of non-stationary signals better and improve the diagnostic accuracy. Finally this paper used random forest to diagnose different fault signals of rolling bearing. It used the bearing data provided by the bearing data center website of Case Western Reserve University for experiments. Comparing with the results of traditional classifier(KNN and SVM) and single classification regression tree CART, this method has better diagnostic results.
英文关键词 rolling bearing; fault diagnosis; discrete wavelet transform; random forest; sigmoid entropy
参考文献 查看稿件参考文献
 
收稿日期 2019/9/27
修回日期 2019/11/11
页码 101-105
中图分类号 TP183;TH17
文献标志码 A