Equipment health diagnosis and prognosis using hidden semi-Markov models

In this paper, the development of hidden semi-Markov models (HSMMs) for equipment health diagnosis and prognosis is presented. An HSMM is constructed by adding a temporal component into the well-defined hidden Markov model (HMM) structures. The HSMM methodology offers two significant advantages over the HMM methodology in equipment health diagnosis and prognosis: (1) it overcomes the modeling limitation of HMM due to the Markov property and therefore improves the power in diagnosis, and (2) it can be directly used for prognosis. The application of the HSMMs to equipment health diagnosis and prognosis is demonstrated with the fault classification application of UH-60A Blackhawk main transmission planetary carriers and prognosis of a hydraulic pump health monitoring application. The effectiveness of the HSMMs is compared with that of the HMMs. The results of the application testing have shown that the HSMMs are capable of identifying the faults under both test cell and on-aircraft conditions while the performance of the HMMs is not comparable with that of the HSMMs. Furthermore, the HSMM-based methodology can be used to estimate the remaining useful life of equipment.

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

[2]  Mari Ostendorf,et al.  A stochastic segment model for phoneme-based continuous speech recognition , 1989, IEEE Trans. Acoust. Speech Signal Process..

[3]  Stephen E. Levinson,et al.  Development of an acoustic-phonetic hidden Markov model for continuous speech recognition , 1991, IEEE Trans. Signal Process..

[4]  Mari Ostendorf,et al.  A comparison of trajectory and mixture modeling in segment-based word recognition , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Jian Zhou,et al.  Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  S. Srihari,et al.  Variable duration hidden markov model and morphological segmentation for handwritten word recognition , 1995, IEEE Transactions on Image Processing.

[7]  Michael J. Roemer,et al.  Advanced diagnostics and prognostics for gas turbine engine risk assessment , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[8]  Carey Bunks,et al.  CONDITION-BASED MAINTENANCE OF MACHINES USING HIDDEN MARKOV MODELS , 2000 .

[9]  Les E. Atlas,et al.  Hidden Markov models for monitoring machining tool-wear , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[10]  Michael J. Roemer,et al.  Development of diagnostic and prognostic technologies for aerospace health management applications , 2001, 2001 IEEE Aerospace Conference Proceedings (Cat. No.01TH8542).

[11]  Kenneth A. Loparo,et al.  Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs) , 2001 .

[12]  Kenneth A. Loparo,et al.  A decision fusion algorithm for tool wear condition monitoring in drilling , 2001 .

[13]  Elijah Kannatey-Asibu,et al.  Hidden Markov model-based tool wear monitoring in turning , 2002 .

[14]  Paul,et al.  Vibration Monitoring of UH-60A Main Transmission Planetary Carrier Fault , 2003 .

[15]  P. Baruah,et al.  HMMs for diagnostics and prognostics in machining processes , 2005 .