[1]袁 涛,张尚斌,何清波.时变奇异值分解在轴承故障特征提取中的应用研究[J].机械与电子,2017,(06):8-11.
　YUAN Tao,ZHANG Shangbin,HE Qingbo.Application of Time-varying Singular Value Decomposition in Feature Extraction of Bearing Fault[J].Machinery & Electronics,2017,(06):8-11.
点击复制

时变奇异值分解在轴承故障特征提取中的应用研究
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2017年06期
页码:
8-11
栏目:
设计与研究
出版日期:
2017-06-24

文章信息/Info

Title:
Application of Time-varying Singular Value Decomposition in Feature Extraction of Bearing Fault
文章编号:
1001-2257(2017)06-0008-04
作者:
袁 涛; 张尚斌; 何清波
(中国科学技术大学精密机械与精密仪器系,安徽 合肥 230026)
Author(s):
YUAN Tao;  ZHANG Shangbin;  HE Qingbo
(Department of Precision Machinery and Precision Instrumentation,University of Science and Technology of China,Hefei 230026, China)
关键词:
轴承故障诊断;  奇异值分解;  时变奇异值分解;  特征提取
Keywords:
bearing fault diagnosis;  singular value decomposition;  time-varying singular value decomposition(TSVD);  feature extraction
分类号:
TH165.3
文献标志码:
A
摘要:
针对滚动轴承的故障识别问题,在奇异值分解的基础上,提出了一种时变奇异值分解方法来提取轴承故障的频谱特征。在信号上加滑窗后,对滑窗内的每一段信号都进行奇异值分解,构建出一个时变奇异值矩阵,其每一行为时变奇异值序列。时变奇异值序列不仅具有良好的周期性,其频率还与原信号的周期成分相对应。实验结果表明,该方法相比于传统方法在轴承故障特征提取方面具有明显优势。
Abstract:
Aiming at the identification of bearing faults, this paper proposes a time-varying singular value decomposition method to extract the spectral feature of bearing faults. The proposed method employs the singular value decomposition to each signal segment realized by a sliding window, and then stores the singular values in a time-varying singular value matrix, each row of which is a time-varying singular value sequence(TSVS). The TSVS has good periodicity, and its frequency is related to the periodic component of the original signal. The experimental results show that the proposed method has significant advantages over the traditional one in feature extraction of bearing faults.

参考文献/References:

[1] 马益书,黄亚宇,吴政. 基于包络分析的滚动轴承故障诊断研究[J]. 机械与电子,2016,34(1): 63-66.
[2] 苏文胜,王奉涛,张志新,等. EMD降噪和谱峭度法在滚动轴承早期故障诊断中的应用[J]. 振动与冲击,2010,29(3): 18-21.
[3] LU S,HE Q,KONG F. Stochastic resonance with Woods–Saxon potential for rolling element bearing fault diagnosis[J]. Mechanical Systems and Signal Processing,2014,45(2): 488-503.
[4] 赵学智,叶邦彦,陈统坚. 奇异值差分谱理论及其在车床主轴箱故障诊断中的应用[J].机械工程学报,2010,46(1):100-108.
[5] YANG W X,PETER W T. Development of an advanced noise reduction method for vibration analysis based on singular value decomposition[J]. Ndt & E International,2003,36(6): 419-432.
[6] LIU F,HE Q,KONG F,et al. Doppler effect reduction based on time-domain interpolation resampling for wayside acoustic defective bearing detector system[J]. Mechanical Systems and Signal Processing,2014,46(2): 253-271.

相似文献/References:

[1]王 云,徐彦伟,何可承,等.基于信息融合和 SA-CNN 的轴承故障诊断[J].机械与电子,2024,42(07):3.
　WANG Yun,XU Yanwei,HE Kecheng,et al.Bearing Fault Diagnosis Method Based on Information Fusion and Self-attention Convolutional Neural Network[J].Machinery & Electronics,2024,42(06):3.

备注/Memo

备注/Memo:
收稿日期:2017-03-10
基金项目:国家自然科学基金资助项目(51475441)
作者简介:袁 涛(1991-),男,四川成都人,硕士研究生,研究方向为设备状态监测与故障诊断; 张尚斌(1989-)男,山西太原人,博士研究生,研究方向为设备状态监测与故障诊断; 何清波(1980-),男,河南濮阳人,副教授,研究方向为机械系统动态监控、诊断与预知性维护等。
更新日期/Last Update: 2017-06-25