计算机应用 ›› 2014, Vol. 34 ›› Issue (8): 2438-2441.DOI: 10.11772/j.issn.1001-9081.2014.08.2438

• 行业与领域应用 • 上一篇    下一篇

基于二次奇异值分解和最小二乘支持向量机的轴承故障诊断方法

李葵1,2,范玉刚1,2,吴建德1,2   

  1. 1. 昆明理工大学 信息工程与自动化学院,昆明650500
    2. 云南省矿物管道输送工程技术研究中心,昆明650500
  • 收稿日期:2014-01-13 修回日期:2014-03-09 出版日期:2014-08-01 发布日期:2014-08-10
  • 通讯作者: 李葵
  • 作者简介:李葵(1989-),男,湖南岳阳人,硕士研究生,主要研究方向:信号处理、模式识别、机械故障诊断;范玉刚(1973-),男,山东威海人,副教授,博士,主要研究方向:基于机器学习的智能信息处理、数据挖掘;吴建德(1979-),男,云南保山人,教授,博士,主要研究方向:矿物管道输送实时检测与控制、工业过程数据分析与建模。
  • 基金资助:

    国家自然科学基金资助项目;云南省科技计划项目;云南省中青年学术和技术带头人后备人才培养计划项目

Bearing fault diagnosis method based on dual singular value decomposition and least squares support vector machine

LI Kui1,2,FAN Yugang1,2,WU Jiande1,2   

  1. 1. Engineering Research Center for Mineral Pipeline Transportation of Yunnan, Kunming Yunnan 650500, China
    2. School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China;
  • Received:2014-01-13 Revised:2014-03-09 Online:2014-08-01 Published:2014-08-10
  • Contact: LI Kui

摘要:

为了解决奇异值分解(SVD)对不同信号分解的有效奇异值个数不同,而影响故障识别准确性的难题,提出了基于二次SVD和最小二乘支持向量机(LS-SVM)的故障诊断方法。该方法利用奇异值曲率谱自适应选择有效奇异值重构信号,进行二次SVD处理,获得相同个数的正交分量,求解其能量熵,并构造故障特征向量,用于LS-SVM分类模型故障识别。将该方法应用于轴承故障诊断,与利用特定个数的主奇异值作为特征向量的方法相比,准确度提高了13.34%,表明了该方法的可行性和有效性。

Abstract:

In order to solve the difficult problem that the different number of singular values affects the accuracy of fault identification, caused by Singular Value Decomposition (SVD) for different signals. A fault diagnosis method based on dual SVD and Least Squares Support Vector Machine (LS-SVM) was put forward. The proposed method could adaptively choose effective singular values by using the curvature spectrum of singular values for reconstructing a signal. SVD was carried out again to acquire the same number of orthogonal components and its energy entropy was calculated to construct the feature vector. Finally, it could be used in the LS-SVM classification model for fault identification. Compared with the method of using limited principal singular values as feature vector, the results show that the proposed method applied to the bearing fault diagnosis improves the accuracy of 13.34%. Also, it is feasible and valid.

中图分类号: