基于DPMM-CHMM的机械设备性能退化评估研究

PDF(806 KB)

振动与冲击 ›› 2017, Vol. 36 ›› Issue (23) : 170-174.

论文

季云王恒朱龙彪刘肖

作者信息 +

Performance degradation assessment for mechanical equipment based on DPMM-CHMM

JI Yun WANG Heng ZHU LongBiao LIU Xiao

Author information +

文章历史 +

摘要

针对传统的HMM模型状态数必须预先设定的不足，提出了一种基于DPMM-CHMM的机械设备性能退化评估方法。该方法利用DPMM模型的自动聚类功能，实现了模型结构根据观测数据的自适应变化和动态调整，获得设备运行过程中的最优退化状态数，并结合CHMM良好的分析和建模能力，得到设备退化状态转移路径，实现机械设备运行过程中的退化状态识别和性能评估，并利用滚动轴承全寿命数据进行了应用研究。结果表明，该方法可以有效地识别轴承运行中的不同退化状态，为基于状态的设备维修提供了理论指导。

Abstract

Aiming at the deficiency of the traditional HMM model, the performance degradation evaluation method for mechanical equipment based on DPMM-CHMM was proposed. With this new method, the automatic clustering function of DPMM model was adopted to realize adaptive changes and dynamic adjustment of a structure model according to the observed data to get the optimal degradation state number in the operation process of mechanical equipment. With good analysis and modeling capabilities of CHMM, the equipment degradation state transition path was obtained to realize the degradation state recognition and performance assessment of mechanical equipment in its operation process. Rolling bearing whole life data were studied, the results showed that the proposed method is feasible, it provides a theoretical guidance for the maintenance of mechanical equipment based on its state.

导出引用

季云王恒朱龙彪刘肖. 基于DPMM-CHMM的机械设备性能退化评估研究[J]. 振动与冲击, 2017, 36(23): 170-174

JI Yun WANG Heng ZHU LongBiao LIU Xiao. Performance degradation assessment for mechanical equipment based on DPMM-CHMM[J]. Journal of Vibration and Shock, 2017, 36(23): 170-174

参考文献

[1] 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.
[2] Qinming Liu, Ming Dong, Ying Peng. A novel method for online health prognosis of equipment based on hidden semi-Markov model using sequential Monte Carlo methods [J]. Mechanical Systems and Signal Processing, 2012, 32: 331-348
[3] 刘新民,刘冠军,邱静.基于HMM-SVM的故障诊断模型及应用[J].仪器仪表学报,2006,27(1):20-26.
LIU XinMin, LIU GuanJun, QIU Jin. The fault diagnosis model and application based on HMM-SVM [J]. Chinese Journal of Scientific Instrument, 2006, 27(1):20-26.
[4] 张继军,马登武,张金春. 基于HMM的电子设备状态监测与健康评估[J]. 系统工程与电子技术,2013,08:1692-1696.
ZHANG JiJun, MA DengWu, ZHANG JinChun. State of electronic equipment inspection and health assessment based on HMM [J]. Journal of Systems Engineering and Electronics, 2013, 35(8):1692-1695.
[5] 曾庆虎.机械动力传动系统关键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.
[6] 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.
[7] 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.
[8] 周建英,王飞跃,曾大军. 分层Dirichlet过程及其应用综述[J]. 自动化学报,2011,37(4):
389-407.
ZHOU JianYing, WANG FeiYue, ZENG DaJun. Review on Hierarchical Dirichlet processes and application [J].Acta Automatica Sinica, 2011, 37(4):389-407
[9] Teh Y W, Jordan M I, Beal M J,et al. Hierarchical Dirichlet processes. Journal of the American Statistical Association, 2006, 101(476): 1566-1581.
[10] Xu T B, Zhang Z F, Yu P S, Long B. Dirichlet process based evolutionary clustering. In: Proceedings of the 8th IEEE International Conference on Data Mining. Pisa, Italy: IEEE, 2008. 648-657.
[11] 梅素玉,王飞,周水庚. 狄利克雷过程混合模型、扩展模型及应用[J].科学通报,2012,57(34):
3243-3257.
MEI SuYu, WANG Fei, ZHOU ShuiGeng. Dirichlet processes Mixture Model、extended model and application[J].Chinese Science Bulletin, 2012, 57(34):3243-3257.
[12] J. Lee, H. Qiu, G. Yu, J. Lin, and Rexnord Technical Services. 'Bearing Data Set', IMS, University of Cincinnati. NASA Ames Prognostics Data Repository[DB/OL].http://ti.
arc.nasa.gov/project/prognostic-data-repository