基于优化Bray-Curtis相异度和PSO算法的轴承剩余寿命预测方法研究

李权福; 贾晨; 宋冬利; 徐潇

doi:10.13890/j.issn.1000-128X.2023.03.011

您当前的位置：

首页 >

文章列表页 >

基于优化Bray-Curtis相异度和PSO算法的轴承剩余寿命预测方法研究

铁道机车车辆 | 更新时间：2024-08-02

- 基于优化Bray-Curtis相异度和PSO算法的轴承剩余寿命预测方法研究
- A study on method for bearing residual life prediction based on optimized Bray-Curtis dissimilarity and PSO algorithms
- 机车电传动 2023年第3期页码：90-96
- 作者机构：
  
  1.国能铁路装备有限责任公司，北京 100089
  2.西南交通大学轨道交通运载系统全国重点实验室，四川成都;610031
- 作者简介：
  
  贾　晨（1999—），男，硕士研究生，主要从事轴承故障诊断方面的研究；E-mail: 1012998675@qq.com
- 基金信息：
  
  国家能源集团科技创新项目(SHGF-17-54)
- DOI：10.13890/j.issn.1000-128X.2023.03.011
  中图分类号： U270.331⁺.2
- 纸质出版日期：2023-05-10，
  
  收稿日期：2023-04-14，
- 稿件说明：
扫描看全文
李权福, 贾晨, 宋冬利, 等. 基于优化Bray-Curtis相异度和PSO算法的轴承剩余寿命预测方法研究[J]. 机车电传动, 2023(3): 90-96.

LI Quanfu, JIA Chen, SONG Dongli, et al. A study on method for bearing residual life prediction based on optimized Bray-Curtis dissimilarity and PSO algorithms[J]. Electric Drive for Locomotives,2023(3): 90-96.
李权福, 贾晨, 宋冬利, 等. 基于优化Bray-Curtis相异度和PSO算法的轴承剩余寿命预测方法研究[J]. 机车电传动, 2023(3): 90-96. DOI： 10.13890/j.issn.1000-128X.2023.03.011.

LI Quanfu, JIA Chen, SONG Dongli, et al. A study on method for bearing residual life prediction based on optimized Bray-Curtis dissimilarity and PSO algorithms[J]. Electric Drive for Locomotives,2023(3): 90-96. DOI： 10.13890/j.issn.1000-128X.2023.03.011.

摘要

轴承在车辆运行过程中既承受载荷又传递载荷，工作环境非常恶劣，若发生故障，会严重威胁车辆的正常运行安全，因此对轴承开展剩余寿命预测方法研究具有重大意义。文章提出了采用稀疏自编码器和Bray-Curtis相异度相结合的方式构建新的轴承健康指标集，并利用改进后的粒子群优化（Particle Swarm Optimization

PSO）算法建立轴承退化模型，最后对测试轴承的剩余寿命进行预测。首先，将轴承健康样本及实测数据的各特征指标输入到稀疏自编码器中进行训练，提取出2种轴承特征参数，计算Bray-Curtis相异度差值作为新的健康指标；然后，基于改进后PSO算法建立轴承退化模型；最后，依据新的健康指标对实测状态下的轴承进行剩余寿命预测。结果表明：该退化模型的拟合曲线预测精度较高，其性能退化曲线与实际轴承退化情况较为接近，可以较好地预测轴承的剩余寿命。

Abstract

Bearings work under a very harsh environment since they do not only bear load but also transfer load during vehicle operation. The occurrence of failure will seriously threaten the safety of vehicles in normal operation. From this perspective

the study of the method for bearing residual life prediction is of great significance. In this paper

a new bearing health index set was set up by combining the sparse autoencoder (SAE) and the Bray-Curtis dissimilarity algorithm

and the bearing degradation model was established by using the improved particle swarm optimization (PSO) algorithm

to predict the residual life of the tested bearings. Firstly

the characteristic indexes of healthy bearing samples and measured data were inputted into the SAE for training

from which two kinds of characteristic parameters for bearing were extracted

to calculate the Bray-Curtis dissimilarity difference which was then taken as a new health index. Then

the bearing degradation model was established based on the improved PSO algorithm. Finally

the new health index was used to predict the residual life of the bearings under real measurement. The results show that the fitting curve of the model has high prediction accuracy

and the performance degradation curve is close to the actual bearing degradation

so that the model can be used to predict the bearing residual life more effectively.

关键词

Bray-Curtis相异度PSO算法退化模型剩余寿命预测

Keywords

Bray-Curtis dissimilarityPSO algorithmdegradation modelresidual life prediction

references

聂晔. 动车组转向架轴承可靠性分析与故障诊断的技术研究[D]. 长沙: 中南大学, 2011.

NIE Ye. Technical research on reliability analysis and fault diagnosis of EMU bogie bearing[D]. Changsha: Central South University, 2011.

王久健, 杨绍普, 刘永强, 等. 一种基于空间卷积长短时记忆神经网络的轴承剩余寿命预测方法[J]. 机械工程学报, 2021, 57(21): 88-95.

WANG Jiujian, YANG Shaopu, LIU Yongqiang, et al. A method of bearing remaining useful life estimation based on convolutional long short-term memory neural network[J]. Journal of Mechanical Engineering, 2021, 57(21): 88-95.

LI Zan, WANG Fengming, WANG Chengjie, et al. Reliability modeling and evaluation of lifetime delayed degradation process with nondestructive testing[J]. Reliability Engineering & System Safety, 2021, 208: 107358.

LUNDBERG G, PALMGREN A. Dynamic capacity of rolling bearings[J]. Journal of Applied Mechanics, 1949, 16(2): 165-172.

ZHANG Jianxun, DU Dangbo, SI Xiaosheng, et al. Prognostics based on stochastic degradation process: the last exit time perspective[J]. IEEE Transactions on Reliability, 2021, 70(3): 1158-1176.

WANG Biao, LEI Yaguo, LI Naipeng, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J]. IEEE Transactions on Reliability, 2020, 69(1): 401-412.

HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.

CHEN Longting, XU Guanghua, ZHANG Sicong, et al. Health indicator construction of machinery based on end-to-end trainable convolution recurrent neural networks[J]. Journal of Manufacturing Systems, 2020, 54: 1-11.

YANG Hanbo, SUN Zheng, JIANG Gedong, et al. Remaining useful life prediction for machinery by establishing scaled-corrected health indicators[J]. Measurement, 2020, 163: 108035.

耿自林. 动车组轴箱轴承剩余寿命预测方法研究[D]. 成都: 西南交通大学, 2020.

GENG Zilin. Research on prediction method of residual life of axle box bearing of EMU[D]. Chengdu: Southwest Jiaotong University, 2020.

盛兆顺, 尹琦岭. 设备状态监测与故障诊断技术及应用[M]. 北京: 化学工业出版社, 2003: 21-77.

SHENG Zhaoshun, YIN Qiling. Technology and application of equipment condition monitoring and fault diagnosis[M]. Beijing: Chemical Industry Press, 2003: 21-77.

KARACAY T, AKTURK N. Experimental diagnostics of ball bearings using statistical and spectral methods[J]. Tribology International, 2009, 42(6): 836-843.

卓鹏程, 严瑾, 郑美妹, 等. 面向滚动轴承全生命周期故障诊断的GA-OIHF Elman神经网络算法[J]. 上海交通大学学报, 2021, 55(10): 1255-1262.

ZHUO Pengcheng, YAN Jin, ZHENG Meimei, et al. GA-OIHF Elman neural network algorithm for fault diagnosis of full life cycle of rolling bearing[J]. Journal of Shanghai Jiaotong University, 2021, 55(10): 1255-1262.

范韫. 基于EMD距离的稀疏自编码器[J]. 计算机工程与科学, 2022, 44(5): 894-900.

FAN Yun. Sparse autoencoder based on earth mover distance[J]. Computer Engineering & Science, 2022, 44(5): 894-900.

张志敏, 柴变芳, 李文斌. 基于稀疏自编码器的属性网络嵌入算法[J]. 计算机工程, 2020, 46(7): 98-103.

ZHANG Zhimin, CHAI Bianfang, LI Wenbin. Attribute network embedding algorithm based on sparse auto-encoder[J]. Computer Engineering, 2020, 46(7): 98-103.

赵志宏, 李乐豪, 杨绍普, 等. 一种无监督的轴承健康指标及早期故障检测方法[J]. 中国机械工程, 2022, 33(10): 1234-1243.

ZHAO Zhihong, LI Lehao, YANG Shaopu, et al. An unsupervised bearing health indicator and early fault detection method[J]. China Mechanical Engineering, 2022, 33(10): 1234-1243.

JIN Xiaohang, SUN Yi, QUE Zijun, et al. Anomaly detection and fault prognosis for bearings[J]. IEEE Transactions on Instrumentation and Measurement, 2016, 65(9): 2046-2054.

ZHAO Bin, WANG Gang, SONG Jingyan, et al. Optimal design method of the LCLC resonant converter based on particle-swarm-optimization algorithm[J]. Journal of Electronics & Information Technology, 2021, 43(6): 1622-1629.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据