基于时变自回归参数模型的滚动轴承智能故障诊断

中国机械工程 ›› 2010, Vol. 21 ›› Issue (22): 2657-2661,2704.

基于时变自回归参数模型的滚动轴承智能故障诊断

李健宝1;彭涛2

1.湖南工业大学,株洲,412008

2.中南大学,长沙,410083

出版日期:2010-11-25 发布日期:2010-12-01
基金资助:
国家自然科学基金资助项目(60774069)；中国博士后科学基金资助项目(20070410462)；省部级重点基金资助项目(9140A17051010BQ0104)；湖南省教育厅科技计划项目(07C005)
National Natural Science Foundation of China（No. 60774069）;

Supported by China Postdoctoral Science Foundation（No. 20070410462）;
Hunan Provincial Science and Technology Program of Ministry of Education of China（No. 07C005）

Intelligent Fault Diagnosis of Rolling Bearings Based on Time-varying Autoregressive Model 

Li Jianbao1;Peng Tao2

1.Hunan University of Technology,Zhuzhou,412008

2.Central South University,Changsha,410083

Online:2010-11-25 Published:2010-12-01
Supported by:

National Natural Science Foundation of China（No. 60774069）;

Supported by China Postdoctoral Science Foundation（No. 20070410462）;
Hunan Provincial Science and Technology Program of Ministry of Education of China（No. 07C005）

摘要/Abstract

摘要：

轴承运行时的振动信号是典型的非线性非平稳时间序列，对其建立时变自回归参数模型，可以较好地表征轴承振动的非平稳特征。在对轴承振动信号时变自回归模型的时变参数进行大量实验分析研究的基础上，提取均值作为表征轴承运行状态的特征参数，并输入支持向量机分类器进行故障识别与分类，实现滚动轴承的智能故障诊断。实验结果表明，该故障诊断方法可以有效准确地识别滚动轴承的运行状态。

关键词:

故障诊断, 时变自回归参数模型, 特征提取, 滚动轴承

Abstract:

The vibration signals of a bearing are typical nonlinear and non-stationary time series,and the non-stationary can be preferably characterized by establishing their time-varying autoregressive(TVAR) model. After adopting large numbers of experimental analysis to the parameters of the TVAR of the vibration signals, the means of time-varying autoregressive parameters can be extracted as the feature vectors of the bearing’s run state, and were input to support vector machine (SVM) classifier to recognize and classify the fault patterns, then an intelligent fault diagnosis was realized. The

experimental results show the effectiveness and accuracy of the proposed approach for recognizing the states of rolling bearings. 

Key words: fault diagnosis, time-varying autoregressive model, feature extract, rolling bearing

中图分类号:

TP206

李健宝, 彭涛.

基于时变自回归参数模型的滚动轴承智能故障诊断

[J]. 中国机械工程, 2010, 21(22): 2657-2661,2704.

LI Jian-Bao, BANG Chao.

Intelligent Fault Diagnosis of Rolling Bearings Based on Time-varying Autoregressive Model 

[J]. China Mechanical Engineering, 2010, 21(22): 2657-2661,2704.

参考文献

[1]吴今培,孙德山编著.现代数据分析[M],2006:284.
[2]Chen Z S,Yang Y M,Hu Z,et al. Detecting and Predicting Early Faults of Complex Rotating Machinery Based on Cyclostationary Time Series Model[J]. Journal of Vibration and Acoustics, 2006,128 (5) : 666-671.
[3]Zhan Y M, Mechefske Gearbox Deteriorateion C K. Robust Detection of Using Compromised Autoregressive Modeling and Kolmogorov- Smirnov Test Statistic- Part I : Compromised Autoregressive Modeling with the Aid of Hypothesis Tests and Simulation Analysis[J]. Mechanical System and Signal Processing, 2007,21 : 1953-1982.
[4]王胜春[1,2],韩捷[2],李志农[2],李剑峰[3].基于TVAR的自适应时频分析及在故障诊断中的应用[J].轴承,2007(6):28-31.
[5]Wang G F,Luo Z G,Qin X D,et al. Fault Identification and Classification of Rolling Element Bearing Based on Time--varying Autoregressive Spectrum [J]. Mechanical System and Signal Processing, 2008,22:934-947.
[6]张龙[1],熊国良[2],柳和生[3],邹慧君[1],陈慧[2].基于时变自回归模型与支持向量机的旋转机械故障诊断方法[J].中国电机工程学报,2007,27(9):99-103.
[7]Pally R K, Louis Beex A A. Modeling of Time--varying Instantaneous Frequency in a Finitely Correlated Environment[C]//In 16th International Conference on Digital Signal Processing. Santorini, 2009:1165-1170.
[8]McCormick A C, Nandi A K. Cyclostationarity in Rotating Machine Vibrations [J].Mechanical System and Signal Processing. 1998,12 : 225-242.
[9]Capdessus C, Sidahmed M, Lacoume J L. Cyclostationarity Processes:Application in Gear Faults Early Diagnosis[J]. Mechanical System and Signal Processing, 2000 ,14: 371-385.
[10]张海勇,李勘.非平稳随机信号的参数模型分析方法[J].系统工程与电子技术,2003,25(3):386-390.
[11]Girault J M, Ossant F. Time--varying Autoregressive Spectral Estimation for Ultrasound Attenuation in Tissue Characterization[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control,1998,45(3) :650-659.
[12]Zhan Y M,Jardine A K S. Adaptive Autoregressive Modeling of Nonstationary Vibration Signals Under Distinct Gear States. Part 1 : Modeling[J]. Journal of Sound and Vibration, 2005, 286: 429- 450.
[13]杨正友[1],彭涛[1].基于振动信号分析和支持向量机的滚动轴承故障诊断[J].湖南工业大学学报,2009,23(1):96-99.
[14]Case Western Reserve University. Bearing Data Center[EB/OL]. [2010-02-10]. http://www. eecs. cwru. edu/laboratory/bearing/weleome_ overview. htm.

[1]	罗洁思, 于德介, 史美丽. 基于SVD和线调频小波路径追踪的转速波动齿轮箱故障诊断 [J]. J4, 201016, 21(16): 1947-1951.
[2]	许鹏, 方舟, 王平, 耿明, 许勇. 基于脉冲漏磁暂态特征的缺陷量化评估方法[J]. 中国机械工程, 2021, 32(07): 860-866,881.
[3]	江志农1;王子嘉1;张进杰2;黄翼飞3;茆志伟2. 基于能量算子梯度邻域特征提取的核电应急柴油发电机组故障诊断方法[J]. 中国机械工程, 2021, 32(05): 617-623.
[4]	唐贵基;李楠楠;王晓龙. 综合改进奇异谱分解和奇异值分解的齿轮故障特征提取方法[J]. 中国机械工程, 2020, 31(24): 2988-2996.
[5]	万书亭;彭勃;王晓龙. 基于双时域变换和稀疏编码收缩的滚动轴承早期故障诊断方法[J]. 中国机械工程, 2020, 31(23): 2829-2836.
[6]	何彦1;凌俊杰1;王禹林2;李育锋1;吴鹏程1;肖圳1. 基于长短时记忆卷积神经网络的刀具磨损在线监测模型[J]. 中国机械工程, 2020, 31(16): 1959-1967.
[7]	余石龙, 鲍劲松, 李婕, 张启华. 基于误差注意力的晶圆制造数据异常检测[J]. 中国机械工程, 2020, 31(14): 1686-1692.
[8]	姜少飞;邬天骥;彭翔;李吉泉;李治;孙涛. 基于XGBoost特征提取的数据驱动故障诊断方法[J]. 中国机械工程, 2020, 31(10): 1232-1239.
[9]	刘朋;任工昌;杨力鹏;胡小龙. 基于斜率差的激光雷达环境特征提取方法[J]. 中国机械工程, 2019, 30(14): 1679-1683.
[10]	江志农1;茆志伟1;王子嘉2;包彬彬3;张进杰2. 基于振动监测的应急柴油机启动性能分析方法[J]. 中国机械工程, 2019, 30(08): 912-918.
[11]	段晨东;张荣. 基于改进经验小波变换的机车轴承故障诊断[J]. 中国机械工程, 2019, 30(06): 631-637.
[12]	金棋, 王友仁, 王俊. [设备健康管理]基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法[J]. 中国机械工程, 2019, 30(02): 196-204.
[13]	陈保家, 刘浩涛, 徐超, 陈法法, 肖文荣, 赵春华. [设备健康管理]深度置信网络在齿轮故障诊断中的应用[J]. 中国机械工程, 2019, 30(02): 205-211.
[14]	杨宇;李鑫;潘海洋;程军圣. 基于非线性模式分解的旋转机械复合故障特征提取方法[J]. 中国机械工程, 2018, 29(24): 2947-2953.
[15]	李丹阳, 张轲, 许如清, 罗志峰, 吴佳谦, 桂豪, . [供应链调度]无反射板激光导航机器人地图创建的特征提取[J]. 中国机械工程, 2018, 29(22): 2733-2739.