基于LMD-PSO-ELM的轴承故障诊断与识别

doi:10.3969/j.issn.2095-2198.2022.05.007

摘要
参考文献
相关文章
推荐阅读
Metrics

下载:

PDF (2402KB)
输出: BibTeX | EndNote (RIS)

摘要

针对滚动轴承故障诊断与识别困难的问题，提出了一种将局部均值分解（LMD）、粒子群优化算法（PSO）、极限学习机（ELM）相结合的故障诊断与识别的方法.首先，通过LMD将振动信号分解成一系列从高频到低频的乘积分量（PF）；其次，计算每个PF分量与原始信号的相关性系数，选择相关性大的PF分量累加作为特征分量，并且将特征分量组成特征向量；最后，使用PSO-ELM网络模型对训练集与测试集进行训练.通过对西储大学轴承数据的仿真，验证了LMD在对信号分解后模态混叠程度较经验模态分解（EMD）更低.将该方法用于某型号线切割机床滚动轴承上，对3种不同状态的滚动轴承进行故障诊断与识别，并将EMD-PSO-ELM与LMD-PSO-ELM方法进行对比，实验结果表明：LMD-PSO-ELM不仅能够识别滚动轴承的故障类型，并且识别的准确率大幅提高.

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	（）
	作者相关文章

关键词: 粒子群优化算法')" href="#">

粒子群优化算法极限学习机局部均值分解故障诊断神经网络

Abstract:

Aiming at the difficulty of fault diagnosis and recognition of rolling bearing,a fault diagnosis and recognition method was proposed based on the combination of local mean decomposition (LMD),particle swarm optimization (PSO) and extreme learning machine (ELM)Firstly,the vibration signal is decomposed into a series of product components (PF) from high frequency to low frequency by LMDSecondly,the correlation coefficients between each PF component and the original signal were calculated,and the PF components with high correlation were selected as the feature components,and the feature components were composed of feature vectorsFinally,PSO-ELM network model was used to train the training set and test setThe simulation of bearing data from Western Reserve University verifies that the degree of mode aliasing is lower in LMD than that of empirical mode decomposition (EMD)The method was applied to the rolling bearings of a certain type of linear cutting machine tool,and the rolling bearings of three different states were diagnosed and recognizedThe EMD-PSO-ELM method was compared with LMD-PSO-ELM methodThe experimental results show that LMD-PSO-ELM can not only identify the fault types of rolling bearings,but also greatly improve the accuracy of identification.

Key words: particle swarm optimization algorithm')" href="#">

particle swarm optimization algorithm ultimate learning machine local average decomposition ault diagnosis neural network

出版日期: 2022-10-30 发布日期: 2024-03-22 整期出版日期: 2022-10-30

ZTFLH:	TH133
	33

基金资助:

国家自然科学基金项目（U1708254）

通讯作者: 张金萍

作者简介: 高云峰（1996—），男，河北承德人，硕士研究生在读，主要从事故障诊断和信号处理的研究.

引用本文:

高云峰, 张金萍.

基于LMD-PSO-ELM的轴承故障诊断与识别 [J]. 沈阳化工大学学报, 2022, 36(5): 428-437.
GAO Yun-feng, ZHANG Jin-ping.

Bearing Fault Diagnosis and Identification Based on LMD-PSO-ELM . Journal of Shenyang University of Chemical Technology, 2022, 36(5): 428-437.

链接本文:

https://xuebao.syuct.edu.cn/CN/10.3969/j.issn.2095-2198.2022.05.007 或 https://xuebao.syuct.edu.cn/CN/Y2022/V36/I5/428

［1］张金萍,王宇雁,王婉莹.EEMD与小波包在液压管道振动信号研究［J］.沈阳化工大学学报,2019，33(3):245-250.

［2］SMITH J S .The Local Mean Decomposition and Its Application to EEG Perception Data［J］.Journal of the Royal Society Interface,2005,2(5):443-454.

［3］HUANG G B,ZHOU H M,DING X J,et al.Extreme Learning Machine for Regression and Multiclass Classification［J］.IEEE Transactions on Systems，Man，and Cybernetics，Part B（Cybernetics），2012，42（2）：513-529.

［4］齐咏生,樊佶,刘利强,等.基于形态学分形和极限学习机的风电机组轴承故障诊断［J］.太阳能学报,2020,41(6):102-112.

［5］YI L Z,ZHAO J,YU W X,et al.Catenary Fault Identification Based on PSO-ELM［J］.Journal of Physics:Conference Series,2019,1302（3）:032017.

［6］秦琼,刘树洁,赖旭,等.GA优化ELM神经网络的风电场测风数据插补［J］.太阳能学报,2018,39(8):2125-2132.

［7］张立智，徐卫晓，井陆阳，等.基于EMD-SVD和CNN的旋转机械故障诊断［J］.振动.测试与诊断,2020,40(6):1063-1070，1228.

［8］CHENG J S,ZHANG K,YANG Y .An Order Tracking Technique for the Gear Fault Diagnosis Using Local Mean Decomposition Method［J］.Mechanism and Machine Theory,2012,55:67-76.

［9］陈保家，何正嘉，陈雪峰，等.机车故障诊断的局域均值分解解调方法［J］.西安交通大学学报，2010，44（5）：40-44.

［10］LIANG N Y,SARATCHANDRAN P,HUANG G B,et al.Classification of Mental Tasks from EEG Signals Using Extreme Learning Machine［J］.International Journal of Neural Systems,2006,16(1):29-38.

［11］范伟，田丽，汪晨，等.基于PSO-ELM模型的短期电力系统负荷预测［J］.新余学院学报，2017，22（5）：20-23.

［12］TIAN Y，MA J，LU C,et al.Rolling Bearing Fault Diagnosis Under Variable Conditions Using LMD-SVD and Extreme Learning Machine［J］.Mechanism and Machine Theory,2015,90:175-186.

［13］GAO Y Y,YU D J.Total Variation on Horizontal Visibility Graph and Its Application to Rolling Bearing Fault Diagnosis［J］.Mechanism and Machine Theory,2020,147:103768.

[1]	高巍, 张奥南, 李大舟, 王淮中. 基于淘宝广告数据的点击概率预估模型研究 [J]. 沈阳化工大学学报, 2022, 36(5): 461-467.
[2]	王军, 张志驰. WSN中基于BP神经网络的数据融合算法优化 [J]. 沈阳化工大学学报, 2022, 36(5): 453-460.
[3]	诗雨桐, 袁德成. 基于深度学习的面部微表情识别 [J]. 沈阳化工大学学报, 2021, 35(4): 380-384.
[4]	李元, 杨东昇, 李大舟. 基于二维卷积神经网络高层数据特征学习的过程故障检测[J]. 沈阳化工大学学报, 2021, 35(3): 256-264.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed