华南理工大学学报(自然科学版) ›› 2012, Vol. 40 ›› Issue (7): 78-82,89.

• 机械工程 • 上一篇    下一篇

基于ARMA模型双谱分布与FCM方法的轴承故障识别

徐红波1 陈国华1† 王新华2   

  1. 1.华南理工大学 机械与汽车工程学院,广东 广州 510640; 2.广州市特种机电设备检测研究院,广东 广州 510180
  • 收稿日期:2012-03-09 修回日期:2012-04-18 出版日期:2012-07-25 发布日期:2012-06-01
  • 通信作者: 陈国华(1967-) ,男,教授,博士生导师,主要从事过程装备动态可靠性随机模拟与风险评价研究. E-mail: mmghchen@scut.edu.cn E-mail:xuhongbo19801980@163.com
  • 作者简介:徐红波(1980-) ,男,博士生,主要从事过程装备安全可靠性技术研究.
  • 基金资助:

    国家科技支撑计划项目( 2009BAK58B02)

Fault Identification of Bearings Based on Bispectrum Distribution of ARMA Model and FCM Method

Xu Hong-boChen Guo-huaWang Xin-hua2   

  1. 1. School of Mechanical and Automotive Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China; 2. Guangzhou Academy of Special Equipment Inspection & Testing,Guangzhou 510180,Guangdong,China
  • Received:2012-03-09 Revised:2012-04-18 Online:2012-07-25 Published:2012-06-01
  • Contact: 陈国华(1967-) ,男,教授,博士生导师,主要从事过程装备动态可靠性随机模拟与风险评价研究. E-mail: mmghchen@scut.edu.cn E-mail:xuhongbo19801980@163.com
  • About author:徐红波(1980-) ,男,博士生,主要从事过程装备安全可靠性技术研究.
  • Supported by:

    国家科技支撑计划项目( 2009BAK58B02)

摘要: 针对滚动轴承信号非线性和非高斯性的特点,提出了基于自回归滑动平均( ARMA)模型双谱分布特征与模糊c 均值( FCM) 聚类分析的故障识别方法.首先,利用经验模态分解改善信号,对获得的信号主分量建立ARMA 模型; 然后,对ARMA 模型进行双谱分析;最后,以阈值化的双谱分布二值图为特征向量,借助FCM 聚类算法构建类模板与最近邻模板分类器,实现故障识别.滚动轴承实例诊断结果表明,该方法能准确地判断轴承的实际性态,是一种有效的故障识别方法.

关键词: 故障识别, 轴承, ARMA 模型, 双谱, 模糊c 均值

Abstract:

According to the nonlinear and non-Guassian characteristics of vibration signals of rolling bearings,a novel fault identification method based on the bispectrum distribution feature of auto-regressive moving average ( ARMA) model and on the cluster analysis of fuzzy c-means ( FCM) method is proposed. In this method,first,original vibration signals are modulated via the empirical mode decomposition ( EMD),and an ARMA model of principal
signal components is established. Then,a bispectrum estimation of the ARMA model is implemented. Finally,the binary images extracted from the bispectrum distribution are taken as the feature vectors and are used to construct a classifier of the class templates and the smallest-distance templates via the FCM clustering,thus implementing the fault identification successfully. Application results in the fault diagnosis of rolling bearings demonstrate that the proposed method is effective because it can accurately determine the actual conditions of rolling bearings.

Key words: fault identification, bearing, ARMA model, bispectrum, fuzzy c-means

中图分类号: