基于隐马尔科夫模型的滚动轴承性能衰退评估

doi:10.3969/j.issn.1674-0696.2021.02.19

重庆交通大学学报（自然科学版） ›› 2021, Vol. 40 ›› Issue (02): 123-128.DOI: 10.3969/j.issn.1674-0696.2021.02.19

基于隐马尔科夫模型的滚动轴承性能衰退评估

郝刚1,2，金涛1

(1. 海军工程大学动力工程学院，湖北武汉 430033； 2. 武汉城市职业学院机电工程学院，湖北武汉 430064)

收稿日期:2019-06-20 修回日期:2019-09-02 出版日期:2021-02-16 发布日期:2021-02-16
作者简介:郝刚（1988—），男，湖北英山人，博士研究生，主要从事可靠性与安全性方面的研究。E-mail：hghaogang@126.com 通信作者：金涛（1966—），男，上海人，教授，博士，主要从事可靠性与安全性、舰船生命力方面的研究。E-mail：ginandtonic@163.com
基金资助:
国家自然科学基金资助项目（51409255）；海军装备部预先研究基金资助项目（4010404010103）

Performance Degradation Assessment of Rolling Bearings Based on Hidden Markov Model

HAO Gang1, 2, JIN Tao1

(1. School of Power Engineering, Naval University of Engineering, Wuhan 430033, Hubei, China; 2. School of Mechanical and Electrical Automation, Wuhan City Vocational College, Wuhan 430064, Hubei, China)

Received:2019-06-20 Revised:2019-09-02 Online:2021-02-16 Published:2021-02-16

摘要/Abstract

摘要： 针对滚动轴承全寿命周期内健康状态的变迁和性能衰退的识别和评估问题，引入隐马尔科夫模型（hidden Markov model，HMM），利用Baum-Welch算法对滚动轴承全寿命周期振动信号数据进行建模，利用Viterbi算法解算和检验模型，最后通过Forward-Backward算法计算测试数据的概率分布；通过校验数据概率分布的隐含序列和观测序列分别表示状态变迁概率和性能衰退评估结果。研究结果表明：该方法能够快速解算滚动轴承状态迁移的概率分布，有效识别性能衰退状态，为预防性维修提供参考。

关键词: 车辆工程, 隐马尔科夫模型, 滚动轴承, 性能衰退, 状态迁移

Abstract: In order to identify and evaluate the changes of health status and performance degradation of rolling bearings in the whole life cycle, the Hidden Markov Model (HMM) was introduced. The Baum-Welch algorithm was used to model the vibration signal data of rolling bearing in whole life cycle, and Viterbi algorithm was used to solve and test the model. Finally, the Forward-Backward algorithm was used to calculate the probability distribution of the test data. The hidden sequence and observation sequence of the data probability distribution were verified to represent the state transition probability and performance degradation evaluation results respectively. The results show that the proposed method can quickly calculate the probability distribution of rolling bearing state transition, effectively identify the performance degradation state, and provide reference for preventive maintenance.

Key words: vehicle engineering, Hidden Markov Model (HMM), rolling bearing, performance degradation, state transition

中图分类号:

U472.9
TH17

郝刚1,2，金涛1. 基于隐马尔科夫模型的滚动轴承性能衰退评估[J]. 重庆交通大学学报（自然科学版）, 2021, 40(02): 123-128.

HAO Gang1, 2, JIN Tao1. Performance Degradation Assessment of Rolling Bearings Based on Hidden Markov Model[J]. Journal of Chongqing Jiaotong University(Natural Science), 2021, 40(02): 123-128.

参考文献

［1］郝刚.数据驱动的滚动轴承性能衰退评估与健康状态预测研究［D］.武汉:华中科技大学,2014.
HAO Gang. Research on Data-Driven Performance Degradation Assessment and Health State Prediction of Rolling Bearing ［D］.Wuhan: Huazhong University of Science and
Technology, 2014.
［2］ KANKAR P K, SHARMA S C, HARSHA S P. Fault diagnosis of rolling element bearing using cyclic autocorrelation and wavelet transform ［J］. Neuro Computing,
2013, 110: 9-17.
［3］吴军,黎国强,吴超勇,等.数据驱动的滚动轴承性能衰退状态监测方法［J］.上海交通大学学报,2018,52(5):538-544.
WU Jun, LI Guoqiang, WU Chaoyong, et al. Data-driven performance degradation condition monitoring for rolling bearings ［J］. Journal of Shanghai Jiaotong
University, 2018, 52(5): 538-544.
［4］史晓雪,吴亚锋.基于AGPF的滚动轴承性能衰退趋势预测［J］.计算机测量与控制,2017,25(10):228-231.
SHI Xiaoxue, WU Yafeng. Prediction of declining performance of rolling bearing based on AGPF ［J］. Computer Measurement & Control, 2017, 25(10): 228-231.
［5］龚光鲁, 钱敏平.应用随机过程教程及其在算法与智能计算中的应用［M］.北京: 清华大学出版社, 2003:247-249.
GONG Guanglu, QIAN Minping. Applied Random Process Tutorial and Its Algorithm and Application in Intelligent Computing ［M］. Beijing: Tsinghua University Press,
2003:247-249.
［6］ RABINER L R.A tutorial on hidden Markov models and selected applications in speech recognition ［J］. Proceeding of the IEEE. 1989, 77(2): 257-286.
［7］ OMOREGBE H O, HEYNS P S. Fault detection in roller bearing operating at low speed and varying loads using Bayesian robust new hidden Markov model ［J］.
Journal of Mechanical Science and Technology, 2018, 32: 4025-4036.
［8］潘玉娜, 陈进, 李兴林. 基于模糊c-均值的设备性能退化评估方法［J］.上海交通大学学报,2009,43(11):1794-1797.
PAN Yuna, CHEN Jin, LI Xinglin. Fuzzy c-means based equipment performance degradation assessment ［j］. Journal of Shanghai Jiaotong University, 2009, 43
(11):1794-1797.
［9］吴军, 郝刚, 邓超, 等. 基于模糊C-均值聚类的轴承性能衰退评估方法［J］. 计算机集成制造系统,2015,21(4):1046-1050.
WU Jun, HAO Gang, DENG Chao, et al. Novel bearing performance degradation evaluation method based on fuzzy C-means clustering algorithm ［J］. Computer Integrated
Manufacturing Systems, 2015, 21(4): 1046-1050.
［10］朱义, 陈进. 基于HMM的设备性能退化评估方法的研究［J］. 振动与冲击, 2008,27（S）: 110-112.
ZHU Yi, CHEN Jin.Research on HMM-based equipment performance degradation assessment ［J］. Journal of Vibration and Shock, 2008, 27(S): 110-112.
［11］刘雨, 陈进, 朱义，等. 基于HMM的设备性能退化评估服务架构体系研究［J］. 矿山机械, 2009（4）: 31-35.
LIU Yu, CHEN Jin, ZHU Yi, et al. Research on services architecture system of evaluating for the equipment performance degradation based on Hidden Markov Models ［J
］. Mining & Processing Equipment,2009(4): 31-35.
［12］ LI Lin, MING Tingfeng, LIU Shuyong, et al. An effective health indicator based on two dimensional hidden Markov model ［J］. Journal of Mechanical Science
and Technology, 2017, 31: 1543-1550.
［13］ ZHANG Shuai, ZHANG Yongxiang, LI Lei, et al. Rolling elements bearings degradation indicator based on continuous Hidden Markov Model ［J］. Journal of
Failure Analysis and Prevention, 2015, 15(5): 691-696.
［14］ YING Yulong, LI Jingchao, LI Jing, et al. Study on rolling bearing on-line health status estimation approach based on vibration signals ［C］∥International
Conference on Advanced Hybrid Information Processing. Springer, 2018: 117-129.
［15］ QI Hui, DI Xiaoqiang, LI Jinqing. Map-matching algorithm based on the junction decision domain and the hidden Markov model ［J］. PLoS One, 2019, 14(5):
e0216476.
［16］ CHEN Zhen, LI Yaping, XIA Tangbin, et al. Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance
policy ［J］. Reliability Engineering and System Safety, 2017, 184: 123-136.

[1]	辛亮1,2，杜子学1，杨震2，许舟洲2. 单轴转向架跨座式单轨车辆的主动控制研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 123-127.
[2]	张东东，宗子淳，冯金芝. 基于NSGA-Ⅱ算法的两挡AMT换挡规律多目标优化[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 128-135.
[3]	李胜永1，张智华1，王胜男2，王孟2. 面向交通工具金属材料的缺损识别算法[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 136-144.
[4]	杜子学，邬浩鑫. 悬挂参数对直线电机跨座式单轨车辆气隙稳定性和运行平稳性影响[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 124-129.
[5]	邓明阳1,2，郭应时1. 电动汽车插补耦合无线充电技术的研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 130-135.
[6]	杜子学，马川翔. 车体铰接式跨座式单轨列车运行稳定性分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 122-128.
[7]	余曼,赵炜华,吴玲,李郁菡. 基于K-均值聚类和支持向量机的电动汽车行驶工况研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 129-139.
[8]	曹源文1，陈作1，赵江2，张晓强3，郑婷婷4. 多路况下轮式装载机行驶稳定性研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(05): 140-146.
[9]	杜子学，邬浩鑫，杨震. 直线电机跨座式单轨车辆曲线通过能力分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 127-132.
[10]	邓涛1，李鑫2. 智能车辆横纵向运动综合控制方法研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 133-140.
[11]	李耀华，刘洋，宋伟萍，邵攀登，任田园. 基于行驶工况的零部件耐久性测试工况构建[J]. 重庆交通大学学报（自然科学版）, 2021, 40(04): 141-146.
[12]	刘祯1,3，林鑫1,2，吴华伟1,3，叶从进1,3，耿向阳4. 基于STAR-CCM+的IGBT散热翅片结构设计研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(03): 128-134.
[13]	李军，张俊，张世义. 基于ABP-EKF算法的锂电池SOC估计[J]. 重庆交通大学学报（自然科学版）, 2021, 40(03): 135-140.
[14]	刘朝涛,狄科宏,杜子学,杨震. 跨座式单轨弓网耦合主动控制研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(02): 129-135.
[15]	隗寒冰,贺少川. 基于深度强化学习的插电式柴电混合动力汽车多目标优化控制策略[J]. 重庆交通大学学报（自然科学版）, 2021, 40(01): 44-52.

基于隐马尔科夫模型的滚动轴承性能衰退评估

Performance Degradation Assessment of Rolling Bearings Based on Hidden Markov Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics