Hidden Markov Models for failure diagnostic and prognostic

This paper deals with an estimation of the Remaining Useful Life of bearings based on the utilization of Mixture of Gaussians Hidden Markov Models (MoG-HMMs). The raw signals provided by the sensors are first processed to extract features, which permit to model the physical component and its degradation. The prognostic process is done in two phases: a learning phase and an evaluation phase. During the first phase, the sensors' data are processed in order to extract appropriate and useful features, which are then used as inputs of dedicated learning algorithms in order to estimate the parameters of a MoG-HMM. The obtained model represents the behavior of the component including its degradation. In addition, the model contains the number of health states and the stay durations in each state. Once the learning phase is done, the generated model is exploited during the second phase, where the extracted features are continuously injected to the learned model to assess the current health state of the physical component and to estimate its remaining useful life and the associated confidence. The proposed method is tested on a benchmark data taken from the “NASA prognostic data repository” related to bearings used under several operating conditions. Moreover, the developed method is compared to two methods: the first using traditional HMMs with exponential time durations and the second using regular Hidden Semi Markov Model (HSMM). Finally, simulation results are given and discussed at the end of the paper.

[1]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[2]  Benoît Iung,et al.  Formalisation of a new prognosis model for supporting proactive maintenance implementation on industrial system , 2008, Reliab. Eng. Syst. Saf..

[3]  A. Z. Keller,et al.  Reliability analysis of CNC machine tools , 1982 .

[4]  Javad Poshtan,et al.  Bearing fault detection using wavelet packet transform of induction motor stator current , 2007 .

[5]  Report of Large Motor Reliability Survey of Industrial and Commercial Installations, Part I , 1985, IEEE Transactions on Industry Applications.

[6]  K. Loparo,et al.  Online tracking of bearing wear using wavelet packet decomposition and probabilistic modeling : A method for bearing prognostics , 2007 .

[7]  M. Farid Golnaraghi,et al.  Prognosis of machine health condition using neuro-fuzzy systems , 2004 .

[8]  Frank L. Lewis,et al.  Intelligent Fault Diagnosis and Prognosis for Engineering Systems , 2006 .

[9]  Van Nostrand,et al.  Error Bounds for Convolutional Codes and an Asymptotically Optimum Decoding Algorithm , 1967 .

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

[11]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

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

[13]  Sheldon M. Ross,et al.  Probability Models for Computer Science , 2001 .

[14]  Joseph P. Cusumano,et al.  A Dynamical Systems Approach to Failure Prognosis , 2004 .

[15]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[16]  Venkat Venkatasubramanian,et al.  Prognostic and diagnostic monitoring of complex systems for product lifecycle management: Challenges and opportunities , 2005, Comput. Chem. Eng..

[17]  Krishna R. Pattipati,et al.  Model-Based Prognostic Techniques Applied to a Suspension System , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[18]  Noureddine Zerhouni,et al.  A mixture of Gaussians Hidden Markov Model for failure diagnostic and prognostic , 2010, 2010 IEEE International Conference on Automation Science and Engineering.