作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于小波包熵与SVM的导轨摩擦磨损状态识别

任瑶1,2,李国富1,应小刚1,王晓丹1   

  1. (1.宁波大学 机械工程与力学学院,浙江 宁波 315211; 2.浙江省零件轧制成形技术研究重点实验室,浙江 宁波 315211)
  • 收稿日期:2015-11-09 出版日期:2016-11-15 发布日期:2016-11-15
  • 作者简介:任瑶(1990—),男,硕士研究生,主研方向为信号分析、机电测控;李国富(通讯作者),教授;应小刚,工程师;王晓丹,本科生。
  • 基金资助:
    浙江省自然科学项目“小型海洋作业船舶应用绿色能源的关键技术研究”(LY12E09001);宁波市自然科学基金“摆动叶片式海浪能发电装置性能研究”(2015A610150);宁波市重点学科项目“叶片及其加工过程研究”(XKl15D223)。

Guideway Friction and Wear State Recognition Based on Wavelet Package Entropy and SVM

REN Yao  1,2,LI Guofu  1,YING Xiaogang  1,WANG Xiaodan  1   

  1. (1.Faculty of Mechanical Engineering and Mechanics,Ningbo University,Ningbo,Zhejiang 315211,China; 2.Zhejiang Provincial Key Lab of Part Rolling Technology,Ningbo,Zhejiang 315211,China)
  • Received:2015-11-09 Online:2016-11-15 Published:2016-11-15

摘要: 针对摩擦振动和噪声信号较难获得、信号抗干扰能力差以及生产中难以得到大量摩损状态样本的情况,提出小波包熵和支持向量机(SVM)相结合的机床导轨摩擦磨损状态识别方法。该方法通过小波包分解方法将信号分解到独立相邻的节点频带中,设计对比实验获得导轨摩擦信息特征频带对应的小波包节点序列,以该序列小波包能量熵值建立特征向量作为SVM的输入参数。实验结果表明,以多项式核函数和径向基核函数建立的SVM分类器平均识别率分别达到72.2%和83.3%,具有较好的预测推广能力及较高的识别准确率。

关键词: 摩擦振动, 信号处理, 小波包分解, 支持向量机, 状态识别

Abstract: The frictional vibration and noise signal are difficult to obtain,signal anti-interference ability is poor,and a large number of samples in the production are difficult to obtain.In view of this a scheme for recognition of friction and wear state of machine tool guide based on wavelet package entropy and Support Vector Machine(SVM) is put forward in this paper.Signal is decomposed into independent adjacent node band by wavelet packet decomposition.Comparative experiment is designed to obtain wavelet packet node sequences corresponding to the guide rail friction characteristic frequency band.The feature vectors are established by the sequence of wavelet packet energy entropy which are as the input parameters of the SVM.Experimental results show that the average recognition rates of the SVM classifier which is established through polynomial kernel function and radial basis kernel function can reach 72.2% and 83.3% separately,which has good prediction generalization ability and high recognition accuracy.

Key words: frictional vibration, signal processing, wavelet packet decomposition, Support Vector Machine(SVM), state recognition

中图分类号: