电子学报 ›› 2018, Vol. 46 ›› Issue (1): 160-166.DOI: 10.3969/j.issn.0372-2112.2018.01.022

• 学术论文 • 上一篇    下一篇

基于局部频谱的滚动轴承故障特征提取方法

苏维均1,2, 杨飞1, 于重重1,2, 程晓卿2, 崔世杰1   

  1. 1. 北京工商大学计算机与信息工程学院, 北京 100048;
    2. 北京交通大学轨道交通控制与安全国家重点实验室, 北京 100044
  • 收稿日期:2016-06-20 修回日期:2016-12-09 出版日期:2018-01-25
    • 作者简介:
    • 苏维均,男,1962年4月出生于四川仁寿.2011年于北京工商大学获得硕士学位,现为北京工商大学计算机与信息工程学院研究生导师、教授.主要研究方向为智能控制与检测技术.E-mail:swj6843@163.com;杨飞,男,1992年9月出生于河北邢台.现为北京工商大学计算机与信息工程学院研究生.主要研究方向为智能控制与检测技术.E-mail:yangf0519@163.com;于重重,女,1971年8月生于辽宁丹东.2013年于北京科技大学获得博士学位.现为北京工商大学计算机与信息工程学院研究生导师、教授.主要研究方向为机器学习与数据挖掘.E-mail:chongzhy@vip.sina.com
    • 基金资助:
    • 北京市自然科学基金重点项目B类 (No.KZ201410011014); 轨道交通控制与安全国家重点实验室开放课题 (No.RCS2015K009); 北京市教委科研计划面上项目 (No.KM201510011010)

Rolling Bearing Fault Feature Extraction Method Based on Local Spectrum

SU Wei-jun1,2, YANG Fei1, YU Chong-chong1,2, CHENG Xiao-qing2, CUI Shi-jie1   

  1. 1. Department of Computer and Information Engineering, Beijing Technology and Business University, Beijing 100048, China;
    2. State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing 100044, China
  • Received:2016-06-20 Revised:2016-12-09 Online:2018-01-25 Published:2018-01-25
    • Supported by:
    • Class B Key project of Beijing Natural Science Foundation (No.KZ201410011014); Open Project of State Key Lab of Rail Traffic Control & Safety  (Beijing Jiaotong University) (No.RCS2015K009); Fundamental Research Program of Beijing Municipal Education Commission (No.KM201510011010)

摘要: 滚动轴承振动信号是非线性、非平稳信号,如何对复杂的非周期滚动轴承数据进行准确特征提取十分具有挑战性.本文提出一种基于局部频谱的轴承数据特征提取方法.该方法将预处理得到的分割点与频谱分析结合起来,构建了数据的局部化特征,确定了局部频率的定义以及时频域的构造方法,并对局部频谱进行特征提取.实验表明,该方法克服了希尔伯特变换仅适合描述窄带信号的局限性,并弥补傅里叶全局频率只对无限波动周期信号才具有明显价值的缺陷.减少虚假频率产生的同时,兼容了时域和频域的分析能力,为非线性非平稳滚动轴承时域数据的特征提取提供了一种新方法,在滚动轴承故障诊断方面有很高的实用价值.

关键词: 故障诊断, 滚动轴承, 特征提取, 局部频谱, 分割点

Abstract: The vibration signal of rolling bearing is a nonlinear and unstable signal. Therefore it is very challenging to carry out feature extraction accurately from the complicated data of non-periodic rolling bearing. This article hereby proposes a method of feature extraction based on local spectrum bearing data. This method combined the segmentation point obtained from pretreatment and the spectrum analysis, built localized feature of the data, determined the definition of the local frequency and the construction method of time-frequency domain, and implemented the feature extraction. Experiments show that this method overcame the limitation that Hilbert transform is only suitable to describe the narrowband signals. It also made up for the defects of Fourier global frequency which is only valuable to the infinite wave period signals. As a new method of feature extraction from the time domain data of the nonlinear and unstable rolling bearing, it reduces the false frequency and is compatible with the analysis of both time domain and frequency domain. It has very high practical value in the fault diagnosis of rolling bearings.

Key words: fault diagnosis, rolling bearing, feature extraction, local spectrum, segmentation point

中图分类号: