A novel method using adaptive hidden semi-Markov model for multi-sensor monitoring equipment health prognosis

被引：87

作者：

Liu, Qinming ^{[1
]}

Dong, Ming ^{[2
]}

Lv, Wenyuan ^{[1
]}

Geng, Xiuli ^{[1
]}

Li, Yupeng ^{[3
]}

机构：

[1] Univ Shanghai Sci & Technol, Sch Business, Dept Ind Engn, Shanghai, Peoples R China

[2] Shanghai Jiao Tong Univ, Antai Coll Econ & Management, Dept Operat Management, Shanghai 200052, Peoples R China

[3] China Univ Min & Technol, Sch Mines, Dept Ind Engn, Xuzhou, Jiangsu, Peoples R China

来源：

MECHANICAL SYSTEMS AND SIGNAL PROCESSING | 2015年 / 64-65卷

基金：

中国国家自然科学基金;

关键词：

Prognosis; Monitoring; Hidden semi-Markov model; Adaptive training; Remaining useful lifetime; PREDICTION;

D O I：

10.1016/j.ymssp.2015.03.029

中图分类号：

TH [机械、仪表工业];

学科分类号：

0802 ;

摘要：

Health prognosis for equipment is considered as a key process of the condition-based maintenance strategy. This paper presents an integrated framework for multi-sensor equipment diagnosis and prognosis based on adaptive hidden semi-Markov model (AHSMM). Unlike hidden semi-Markov model (HSMM), the basic algorithms in an AHSMM are first modified in order for decreasing computation and space complexity. Then, the maximum likelihood linear regression transformations method is used to train the output and duration distributions to re-estimate all unknown parameters. The AHSMM is used to identify the hidden degradation state and obtain the transition probabilities among health states and durations. Finally, through the proposed hazard rate equations, one can predict the useful remaining life of equipment with multi-sensor information. Our main results are verified in real world applications: monitoring hydraulic pumps from Caterpillar Inc. The results show that the proposed methods are more effective for multi-sensor monitoring equipment health prognosis. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：217 / 232

页数：16

共 30 条

[1]

Banjevic D., 2006, IMA Journal of Management Mathematics, V17, P115, DOI 10.1093/imaman/dpi029

[2] Combined Probability Approach and Indirect Data-Driven Method for Bearing Degradation Prognostics [J].

Caesarendra, Wahyu ;

Widodo, Achmad ;

Thom, Pham Hong ;

Yang, Bo-Suk ;

Setiawan, Joga Dharma .

IEEE TRANSACTIONS ON RELIABILITY, 2011, 60 (01) :14-20

[3] Machine condition prognosis based on sequential Monte Carlo method [J].

Caesarendra, Wahyu ;

Niu, Gang ;

Yang, Bo-Suk .

EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (03) :2412-2420

[4] Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis [J].

Dong, Ming ;

He, David .

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2007, 178 (03) :858-878

[5] A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology [J].

Dong, Ming ;

He, David .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (05) :2248-2266

[6]

Ferguson J.D., 1980, S APPL HIDDEN MARKOV, P143

[7] A reliability-based framework for fatigue damage prognosis of composite aircraft structures [J].

Gobbato, Maurizio ;

Conte, Joel P. ;

Kosmatka, John B. ;

Farrar, Charles R. .

PROBABILISTIC ENGINEERING MECHANICS, 2012, 29 :176-188

[8]

Hancock KM, 2006, T ASABE, V49, P1203, DOI 10.13031/2013.21720

[9] Predicting remaining life by fusing the physics of failure modeling with diagnostics [J].

Kacprzynski, GJ ;

Sarlashkar, A ;

Roemer, MJ ;

Hess, A ;

Hardman, W .

JOM, 2004, 56 (03) :29-35

[10] Bearing fault prognosis based on health state probability estimation [J].

Kim, Hack-Eun ;

Tan, Andy C. C. ;

Mathew, Joseph ;

Choi, Byeong-Keun .

EXPERT SYSTEMS WITH APPLICATIONS, 2012, 39 (05) :5200-5213

← 1 2 3 →