基于样本熵和决策树调节算法轴承故障识别.PDF

安徽农业大学学报, 2017, 44(5): 936-940 Journal of Anhui Agricultural University [DOI] 10.13610/ki.1672-352x018 网络出版时间：2017/10/17 10:48:40 [URL] /kcms/detail/34.1162.S1048.036.html 基于样本熵与决策树调节算法的轴承故障识别 李六杏，周黄丽 (安徽经济管理学院信息工程系，合肥 230031) 摘 要：轴承故障是导致机器发生事故的重要原因之一。为更好地识别出故障类型，使用一种包络样本熵和决策 树门限值自适应调节算法相结合的方法。首先将信号分解成若干 IMF 之和，选取包含丰富故障信息的 IMF 求其包络 信号的样本熵，最后通过决策树自适应调节门限值准确判断出轴承故障类型。分析结果表明，该方法不仅可以通过反 馈减少运算量，而且能够通过决策树门限值的自适应调节来提高轴承故障的识别率，综合识别率可达到 96.75%。 关键词：包络样本熵；决策树；轴承故障；自适应调节；门限值 中图分类号：TP206 文献标识码：A 文章编号：1672352X (2017)05093605 Based on sample entropy and decision tree algorithm for regulation of bearing fault diagnosis LI Luxing, ZHOU Huangli (Department of Information Engineering, Anhui Institute of Economic Management, Hefei 230031) Abstract: Bearing failure is one of the important reasons for machine accidents. To better identify fault types, this paper used a method which combines envelope sample entropy with decision tree gate limit value adaptive adjustment algorithm. We firstly decomposed the signal into several IMFs and selected the sample entropy of the envelope signal from the IMF which contains a number of diagnostic information, and then, the type of bearing failure was accurately determined by decision tree adaptive adjustment gate limit value.Analysis results showed that this method can not only reduce the computational complexity through the feedback, but also improve the recognition rate of bearing failure through the decision tree threshold adaptive adjustment. Comprehensive recog- nition rate can reach 96.75%. Key words: envelope sample entropy;decision tree;bearing failure;adaptive adjustment;gate limit value 轴承发生故障时产生的信号通常为非平稳信 本研究使用包络样本熵和决策树门限值自适应 号，如何将轴承故障的特征信息从非平稳信号中提