Bearing Fault Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model

doi:10.7652/xjtuxb201706001

您当前的位置：

首页 >

文章列表页 >

Bearing Fault Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model

更新时间：2025-07-09

- Bearing Fault Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model
- Vol. 51, Issue 6, Pages: 1-7+109(2017)
- 作者机构：
  
  西安交通大学机械制造系统工程国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201706001
  CLC： TH17
- Online First：10 June 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
Bearing Fault Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model[J]. 2017, 51(6): 1-7+109.
DOI：

Bearing Fault Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model[J]. 2017, 51(6): 1-7+109. DOI： 10.7652/xjtuxb201706001.

摘要

为了快速识别轴承的故障模式以及性能退化状态

提出了一种基于主分量分析和隐马尔科夫模型的轴承监测诊断方法。该方法首先提取了轴承振动信号的混合域故障特征集

使用主分量分析对混合域故障特征集降维

然后使用降维后的特征训练隐马尔科夫模型

最后用降维后的测试样本测试模型的性能

根据隐马尔科夫模型输出的对数似然概率

确定轴承故障模式以及轴承的性能退化状态。开展了不同状态滚动轴承振动测试实验

数据分析结果表明

提出的方法诊断准确率均能达到100%

相比基于补偿距离选择特征降维及隐马尔科夫模型诊断方法

最高将分类离散度提高123.74%

并且在轴承的性能退化实验中

提出的方法能在故障早期给出故障预警

证明了该方法的有效性和准确性。

Abstract

Aiming at accurately and rapidly recognizing bearing fault pattern and performance degradation

a bearing fault detection and diagnosis method based on principal component analysis and hidden Markov model is proposed. The mixed domain fault feature set of bearing vibration signal

which corresponds to different bearing conditions

is extracted with principal component analysis to reduce the dimension of the feature set

then hidden Markov models are trained with part of the reduced feature set. The performances of trained models are verified with the remaining parts in this feature set. The bearing fault patterns are recognized and bearing performance degradation is assessed by comparing the logarithmic likelihood probability value of the hidden Markov models. Experiments under different bearing conditions are carried out

vibration signals are collected

and the correct classification rate of the proposed method reaches 100%. Compared with the compensation distance evaluation based feature dimension reducing technique and hidden Markov model

the classification dispersion of the proposed method is increased by 123.74%. In the bearing performance degradation monitoring

the proposed method exhibits better effectiveness and accuracy for early bearing degradation warning.

关键词

Keywords

references

屈粱生, 何正嘉. 机械故障诊断学 [M]. 上海: 上海科学技术出版社, 1986: 81.

PATIL M S, MATHEW J, RAJENDRAKUMAR P K. Bearing signature analysis as a medium for fault detection: a review [J]. Journal of Tribology, 2008, 130(1): 014001

苏祖强. 基于泛化流形学习的风电机组传动系统早期故障诊断方法研究 [D]. 重庆: 重庆大学, 2015: 17-18.

蒋会明, 陈进, 董广明, 等. 基于集成隐马尔可夫模型的轴承故障诊断 [J]. 振动与冲击, 2014, 33(10): 92-96.

JIANG Huiming, CHEN Jin, DONG Guangming, et al. Integrated HMM-based bearing fault diagnosis [J]. Journal of Vibration and Shock, 2014, 33(10): 92-96.

ZHOU H, CHEN J, DONG G, et al. Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model [J]. Mechanical Systems and Signal Processing, 2016, 66: 568-581.

LIU T, CHEN J, ZHOU X N, et al. Bearing performance degradation assessment using linear discriminant analysis and coupled HMM [J]. Journal of Physics: Conference Series, 2012, 364(1): 12028-12039.

雷亚国, 何正嘉, 訾艳阳. 基于混合智能新模型的故障诊断 [J]. 机械工程学报, 2008, 44(7): 112-117.

LEI Yaguo, HE Zhengjia, ZI Yanyang. Fault diagnosis based on novel hybrid intelligent model [J]. Chinese Journal of Mechanical Engineering, 2008, 44(7): 112-117.

CHEN P, TANIGUCHI M, TOYOTA T, et al. Fault diagnosis method for machinery in unsteady operating condition by instantaneous power spectrum and genetic programming [J]. Mechanical Systems Signal Processing, 2005, 19(1): 175-194.

屈梁生, 张西宁, 沈玉娣. 机械故障诊断理论与方法 [M]. 西安: 西安交通大学出版社, 2009: 170-172.

RABINER L R. A tutorial on hidden Markov models and selected applications in speech recognition [J]. Proceedings of the IEEE, 1989, 77(2): 257-286.

WINGER L L R. Linearly constrained generalized Lloyd algorithm for reduced codebook vector quantization [J]. IEEE Transactions on Signal Processing, 2001, 49(7): 1501-1509.

周徐宁. 基于特征加权连续隐马尔可夫模型的故障诊断方法研究 [D]. 上海: 上海交通大学, 2012: 70-71.

QIU H, LEE J, LIN J, et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics [J]. Journal of Sound and Vibration, 2006, 289(4): 1066-1090.

郝维娜,令锋超,刘志刚,等.轴承滚珠面型误差激光干涉测量系统的研究.2016,50(6):83-89.[doi:10.7652/xjtuxb2016 06013]

张平,张小栋,董晓妮,等.滑动轴承润滑油膜厚度光纤动态精密检测模型.2016,50(5):45-50.[doi:10.7652/xjtuxb 201605007]

贺王鹏,訾艳阳,陈彬强.冲击特征受控极小化通用稀疏表示及其在机械故障诊断中的应用.2016,50(4):94-99.[doi:10.7652/xjtuxb201604015]

耿涛,孟庆丰,贾谦,等.薄衬层结构滑动轴承润滑膜厚度的超声检测方法.2014,48(8):80-85.[doi:10.7652/xjtuxb 201408014]

张浩,张进华,朱永生,等.外隔圈不平行度对轴承性能影响的数值分析.2014,48(8):86-90.[doi:10.7652/xjtuxb2014 08015]

陈汝刚,席光,陈韬.掌上透平弹性箔片动压气体轴承的试验研究.2014,48(7):1-4.[doi:10.7652/xjtuxb201407001]

王楠,孟庆丰,张雪冰,等.多沟槽水润滑橡胶轴承水膜压力的无线测试方法.2013,47(3):1-6.[doi:10.7652/xjtuxb 201303001]

付新哲,张优云,朱永生.滚动轴承故障诊断的案例推理方法.2011,45(11):79-84.[doi:10.7652/xjtuxb201111015]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Quality Detection of Wire Bonding Using Ultrasonic Electrical Signal of Piezoelectric Transducer

Adaptive Genetic Particle Swarm Algorithm for Optimization Hidden Markov Models with Applications

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

I/O Performance Modeling and Prediction Method for Large-Scale Parallel Applications Using Machine Learning

Related Author

冯武卫

孟庆丰

谢友柏

杨雨薇

张雯雯

Related Institution

Theory of Lubrication and Bearing Institute, Xi'an Jiaotong University

⁰