An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process

Efficient asset management is of paramount importance, particularly for systems with costly downtime and failure. As in energy and capital-intensive industries, the economic loss of downtime and failure is huge, the need for a low-cost and integrated health monitoring system has increased significantly over the years. Timely detection of faults and failures through an efficient prognostics and health management (PHM) framework can lead to appropriate maintenance actions to be scheduled proactively to avoid catastrophic failures and minimize the overall maintenance cost of the systems. This paper aims at practical challenges of online diagnostics and prognostics of mechanical systems under unobservable degradation. First, the elements of a multistate degradation structure are reviewed and then a model selection framework is introduced. Important dynamic performance measures are introduced, which can be used for online diagnostics and prognostics. The effectiveness of the result of this paper is demonstrated with a case study on the health monitoring of turbofan engines.

[1]  Konstantinos C. Gryllias,et al.  Rolling element bearing fault detection in industrial environments based on a K-means clustering approach , 2011, Expert Syst. Appl..

[2]  Mitsuo Gen,et al.  Soft computing approach for reliability optimization: State-of-the-art survey , 2006, Reliab. Eng. Syst. Saf..

[3]  Alain Biem,et al.  HMM topology optimization for handwriting recognition , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[4]  M. Zuo,et al.  Optimal Reliability Modeling: Principles and Applications , 2002 .

[5]  David He,et al.  A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology , 2007 .

[6]  Jun Yu,et al.  Deviance Information Criterion for Comparing Stochastic Volatility Models , 2002 .

[7]  Jin-Young Ha,et al.  Model Selection Criterion using Confusion Models for HMM Topology Optimization , 2006, 2006 SICE-ICASE International Joint Conference.

[8]  Soumaya Yacout,et al.  Optimal condition based maintenance with imperfect information and the proportional hazards model , 2007 .

[9]  Bo Guo,et al.  A maintenance optimization model for mission-oriented systems based on Wiener degradation , 2013, Reliab. Eng. Syst. Saf..

[10]  Zhaojun Li,et al.  Continuous-state reliability measures based on fuzzy sets , 2012 .

[11]  Ming Liang,et al.  Detection and diagnosis of bearing and cutting tool faults using hidden Markov models , 2011 .

[12]  Kai Yang,et al.  Dynamic reliability analysis of coherent multistate systems , 1995 .

[13]  Xiaomin Zhao,et al.  Application of Fuzzy Preference Based Rough Set Model to Condition Monitoring , 2010, RSCTC.

[14]  Rui Jiang,et al.  Parameter estimation for partially observable systems subject to random failure , 2013 .

[15]  Abhinav Saxena,et al.  Damage propagation modeling for aircraft engine run-to-failure simulation , 2008, 2008 International Conference on Prognostics and Health Management.

[16]  William S. Griffith,et al.  Optimal Reliability Modeling: Principles and Applications , 2004, Technometrics.

[17]  George Morcous,et al.  Identification of environmental categories for Markovian deterioration models of bridge decks , 2003 .

[18]  Nikolaos Limnios,et al.  Modelling and estimating the reliability of stochastic dynamical systems with Markovian switching , 2008, Reliab. Eng. Syst. Saf..

[19]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[20]  Ming Jian Zuo,et al.  A parameter estimation method for a condition-monitored device under multi-state deterioration , 2012, Reliab. Eng. Syst. Saf..

[21]  David W. Coit,et al.  Reliability analysis for dependent failure processes and dependent failure threshold , 2011, 2011 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering.

[22]  E. Ward.  A review and comparison of four commonly used Bayesian and maximum likelihood model selection tools , 2008 .

[23]  Fanrang Kong,et al.  Machine condition monitoring using principal component representations , 2009 .

[24]  Jian Yang,et al.  Feature fusion: parallel strategy vs. serial strategy , 2003, Pattern Recognit..

[25]  Ming J. Zuo,et al.  Modeling multi-state equipment degradation with non-homogeneous continuous-time hidden semi-markov process , 2012 .

[26]  Zhiwen Liu,et al.  A Monotonic Degradation Assessment Index of Rolling Bearings Using Fuzzy Support Vector Data Description and Running Time , 2012, Sensors.

[27]  Ruey Huei Yeh.  State-age-dependent maintenance policies for deteriorating systems with Erlang sojourn time distributions , 1997 .

[28]  John Yuan,et al.  A two-stage preventive maintenance policy for a multi-state deterioration system , 2010, Reliab. Eng. Syst. Saf..

[29]  Robert X. Gao,et al.  PCA-based feature selection scheme for machine defect classification , 2004, IEEE Transactions on Instrumentation and Measurement.

[30]  Jacques Janssen,et al.  Numerical Treatment of Homogeneous and Non-homogeneous Semi-Markov Reliability Models , 2004 .

[31]  Laurent Doyen,et al.  Modeling and Assessment of Aging and Efficiency of Corrective and Planned Preventive Maintenance , 2011, IEEE Transactions on Reliability.

[32]  Loon Ching Tang,et al.  A Distribution-Based Systems Reliability Model Under Extreme Shocks and Natural Degradation , 2011, IEEE Transactions on Reliability.

[33]  Cheng-Der Fuh,et al.  Estimation of Time to Hard Failure Distributions Using a Three-Stage Method , 2010, IEEE Transactions on Reliability.

[34]  Sheng Yue,et al.  A comparison of the power of the t test, Mann-Kendall and bootstrap tests for trend detection / Une comparaison de la puissance des tests t de Student, de Mann-Kendall et du bootstrap pour la détection de tendance , 2004 .

[35]  Daoud Aït-Kadi,et al.  Performance evaluation of multi-state degraded systems with minimal repairs and imperfect preventive maintenance , 2010, Reliab. Eng. Syst. Saf..

[36]  Paolo Magni,et al.  Determining the maximum periodic inspection interval for medium voltage motors using a Markov model , 2008 .

[37]  Daming Lin,et al.  A review on machinery diagnostics and prognostics implementing condition-based maintenance , 2006 .

[38]  F. Wang,et al.  Feature fusion of mechanical faults based on evolutionary computation , 2007 .