基于HDP-HMM的机械设备故障预测方法研究

王恒,周易文,瞿家明,季云

振动与冲击 ›› 2019, Vol. 38 ›› Issue (8) : 173-179.

PDF(1432 KB)
PDF(1432 KB)
振动与冲击 ›› 2019, Vol. 38 ›› Issue (8) : 173-179.
论文

基于HDP-HMM的机械设备故障预测方法研究

  • 王恒,周易文,瞿家明,季云
作者信息 +

A prognostic method of mechanical equipment based on HDP-HMM

  • WANG Heng, ZHOU Yiwen, QU Jiaming,JI Yun
Author information +
文章历史 +

摘要

针对隐马尔科夫模型状态数必须预先设定的不足,提出了一种基于分层狄利克雷过程—隐马尔科夫模型(HDP-HMM)的机械设备故障预测方法。该算法通过构造HDP作为HMM参数的先验分布,利用HDP分层共享和自动聚类的优点,实现了模型结构动态更新,获得设备运行过程中的隐状态数;基于HDP-HMM所建立的退化状态动态转移关系,确定设备早期故障点和功能故障点,实现设备的健康等级评估和故障预测。利用美国USFI/UCR智能维护系统中心提供的滚动轴承全寿命数据进行了应用研究。结果表明,针对多观测序列,HDP-HMM能有效实现组合聚类,识别结果不依赖于算法初始参数的选择,具有较强的鲁棒性。与基于K-S检验的退化评估算法比较表明,HDP-HMM更能有效描述设备实际退化过程。

Abstract

Aimed at the deficiency of the Hidden Markov model whose hidden states must be determined in advance, a prognostics method of mechanical equipment based on the Hierarchical Dirichlet Process-Hidden Markov model (HDP-HMM) was proposed.By constructing HDP as the prior distribution of HMM, the structure of HMM was dynamically adjusted and the state number during the operation of the equipment degradation was obtained according to hierarchical sharing and automatic clustering of HDP.Based on the dynamic transition state relationship established by HDP-HMM, the early failure point and functional failure point of the equipment were determined, and the health grade evaluation and prognostics of the equipment were realized.The application of life data of rolling bearings provided by the USFI/UCR intelligent maintenance system center was studied.The results show that HDP-HMM can effectively achieve the combination clustering for multiple observation sequences and the recognition results do not depend on the choice of initial parameters of the algorithm which has strong robustness.Compared with the K-S test algorithm of degradation assessment, HDP-HMM can describe the actual degradation process of the equipment more effectively.

关键词

分层狄利克雷过程-隐马尔科夫模型 / 退化状态 / 故障预测

Key words

Hierarchical Dirichlet Process-Hidden Markov model / degradation state / prognostics

引用本文

导出引用
王恒,周易文,瞿家明,季云. 基于HDP-HMM的机械设备故障预测方法研究[J]. 振动与冲击, 2019, 38(8): 173-179
WANG Heng, ZHOU Yiwen, QU Jiaming,JI Yun. A prognostic method of mechanical equipment based on HDP-HMM[J]. Journal of Vibration and Shock, 2019, 38(8): 173-179

参考文献

[1] 曾声奎,Pecht M,吴际.故障预测与健康管理技术(PHM)的现状与发展[J].航空学报,2005, 26(5):610-616
[2] ZIO E. Reliability engineering: old problems and new challenges [J]. Reliability engineering and Safety, 2009, 94(2):125-141
[3] Heng A, Zhang S, Tan A C C, et al. Rotating machinery prognostics: state of the art, challenges and opportunities [J]. Mechanical Systems and Signal Processing, 2009, 23(3):724-739
[4] 季云,王恒,朱龙彪等.基于HMM的机械设备运行状态评估与故障预测研究综述[J].机械强度,2017,39( 3) : 511-517
JI Yun,WANG Heng,ZHU Longbiao,et al. Review on operation state assessment and prognostics for mechanical equipment based on Hidden Markov model[J].Journal of Mechanical Strength, 2017, 39(3): 511-517
[5] Peng Y, Dong M. A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction [J]. Mechanical System and Signal Processing, 2011, 25 (1):237-252
[6] 张西宁,雷威,李兵. 主分量分析和隐马尔科夫模型结合的轴承监测诊断方法[J]. 西安交通大学学报,2017,(06):y1-y8
ZHANG Xining,LEI Wei,LI Bin.Bearing Fault
Detection and Diagnosis Method Based on Principal Component Analysis and Hidden Markov Model [J]. Journal of Xi’an Jiao Tong University,2017,(06):y1-y8
[7] 袁洪芳,张任,王华庆.基于 HMM 与改进距离测度法的齿轮箱故障诊断[J].振动与冲击,
2014, 33(14):89-94
YUAN Hongfang,ZHANG Ren,WANG Hua
qing.Fault diagnosis of gearbox based on HMM and improved distance measure[J]. Journal of Vibration and Shock, 2014, 33(14):89-94
[8] 曾庆虎. 机械传动系统关键零部件故障预测技术研究[D]:[博士学位论文].长沙:国防科学技术大学,2010:65-72
[9] 滕红智,赵建民,贾希胜,等. 基于CHMM的齿轮箱状态识别研究[J]. 振动与冲击,2012,31 (5):92-96
TENG Hongzhi, ZHAO Jianmin, JIA Xisheng, et al. Research on the state identification of gear box based on CHMM [J]. Journal of Vibration and Shock, 2012, 31(5):92-96
[10] 张星辉,康建设,高存明,等.基于MoG-HMM 的齿轮箱状态识别与剩余使用寿命预测研究[J].振动与冲击, 2013, 32(15):20-25
ZHANG Xinghui, KANG Jianshe, GAO Cunming,et al. Research of gear box state identification and residual service life prediction based on MoG-HMM [J]. Journal of Vibration and Shock, 2013, 32(15):20-25
[11] 周东华,魏慕恒,司小胜.工业过程异常检测、寿命预测与维修决策的研究进展[J].自动化学报,2013, 39(6):711-722
ZHOU Donghua ,WEI Muheng,Si Xiaosheng.A Survey on Anomaly Detection, Life Prediction and Maintenance Decision for Industrial Processes[J]. Acta automatica sinica, 2013, 39(6):711-722
[12] 姜万录, 杨凯, 董克岩,等. 基于CHMM的轴承性能退化程度综合评估方法研究[J]. 仪器仪表学报, 2016, 37(9):2014-2021
JIANG Wanlu, YANG Kai, DONG Keyan,et,al. Research on comprehensive evaluation method of bearing performance degradation based on CHMM[J]. Journal of instrumentation,
2016, 37(9): 2014-2021
[13] Teh Y W, Jordan M I, Beal M J, Blei D M. Hierarchical Dirichlet processes. Journal of the American Statistical Association, 2006, 101(476): 1566−1581
[14] Fox E B, Sudderth E B, Jordan M I, Willsky A S. An HDPHMM for systems with state persistence. In: Proceedings of the 25th International Conference on Machine Learning. New York, USA: ACM, 2008. 312−219
[15] 王恒,马海波,黄希,等. 基于Kolmogrov-Smirnov检验和LS-SVM的机械设备故障预测[J]. 中南大学学报(自然科学版),2016,47(6):1924-1929
WANG Heng,MA Haibo,HUANG Xi,et al. Research on fault prediction of mechanical equipment based on Kolmogrov-Smirnov and LS-SVM [J].Journal of Central southUniversity, 2016, 47(6):1925-1929

PDF(1432 KB)

Accesses

Citation

Detail

段落导航
相关文章

/