In a health management system, prognostics, which is an engineering discipline that predicts a system’s future health, is an important aspect yet there is currently limited research in this field. In this paper, a hybrid approach for prognostics is proposed. The approach combines the least squares support vector regression (LSSVR) with the hidden Markov model (HMM). Features extracted from sensor signals are used to train HMMs, which represent different health levels. A LSSVR algorithm is used to predict the feature trends. The LSSVR training and prediction algorithms are modified by adding new data and deleting old data and the probabilities of the predicted features for each HMM are calculated based on forward or backward algorithms. Based on these probabilities, one can determine a system’s future health state and estimate the remaining useful life (RUL). To evaluate the proposed approach, a test was carried out using bearing vibration signals. Simulation results show that the LSSVR/HMM approach can forecast faults long before they occur and can predict the RUL. Therefore, the LSSVR/HMM approach is very promising in the field of prognostics.
References
[1]
Cheng, S.; Azarian, M.; Pecht, M. Sensor system for prognostics and health management. Sensors 2010, 10, 5774–5797.
[2]
Pecht, M. Progn and Health Management of Electron; Wiley-Interscience: New York, NY, USA, 2008.
[3]
Dickson, B.; Cronkhite, J.; Bielefeld, S.; Killian, L.; Hayden, R. Feasibility Study of a Rotorcraft Health and Usage Monitoring System (HUMS): Usage and Structural Life Monitoring Evaluation. NASA Contractor Report 198447; DOT/FAA/AR-95/9, ARL-CR-290; 1996.
[4]
Baroth, E.; Powers, W. T.; Fox, J.; Prosser, B.; Pallix, J.; Schweikard, K.; Zakrajsek, J. IVHM (Integrated Vehicle Health Management) Techniques for Future Space Vehicles. Proceedings of the AIAA 37th Joint Propulsion Conference and Exhibit, Salt Lake City, UT, USA, 8–11 July 2001.
[5]
Ferrell, B.L. Air Vehicle Prognostics and Health Management. Proceedings of the IEEE Conference on Aerospace, Big Sky, MT, USA, 18–25 March 2000; pp. 145–146.
[6]
Hess, A.; Calvello, G.; Dabney, T. PHM a key Enabler for the JSF Autonomic Logistics Support Concept. Proceedings of the IEEE Conference on Aerospace, Big Sky, MT, USA, 6–13 March 2004; pp. 3543–3550.
[7]
Roemer, M.; Dzakowic, J.; Orsagh, R.; Byington, C.; Vachtsevanos, G. An Overview of Selected Prognostic Technologies with Reference to an Integrated PHM Architecture. Proceedings of the First International Forum on Integrated System Health Engineering and Management in Aerospace, Big Sky, UT, USA; 2005; pp. 3941–3947.
[8]
Box, G.E.P.; Jenkins, G.M. Time Series Anal: Forecast and Control, 3rd ed. ed.; Holden-Day: San Francisco, CA, USA, 1994.
[9]
Xue, G.X.; Xiao, L.C.; Bie, M.H.; Lu, S.W. Fault Prediction of Boilers with Fuzzy Mathematics and RBF Neural Network. Proceeding of the International Conference on Communications, Circuits and Systems, Jiangsu, China, 27–30 May 2005; pp. 1012–1016.
[10]
Ferreiro, S.; Arnaiz, A.; Sierra, B.; Irigoien, I. A bayesian network model integrated in a prognostics and health management system for aircraft line maintenance. J. Aerosp. Eng. 2011, 225, 886–901.
[11]
Smola, A.J.; Sch？lkopf, B. A tutorial on support vector regression. Stat. Comput. 2004, 14, 199–222.
[12]
Zhang, J.F.; Hu, S.S. Nonlinear time series fault prediction based on clustering and support vector machines (in Chinese). Control Theory Appl. 2007, 24, 64–68.
[13]
Qu, J.; Zuo, M.J. An LSSVR-based algorithm for online system condition prognostics. Expert Syst. Appl. 2012, 39, 6089–6102.
[14]
Liu, S.; Jia, S.; Li, B.; Li, G.Y. Investigation of Steering Dynamics Ship Model Identification Based on PSO-LSSVR. Proceedings of the 2nd International Symposium on Systems and Control in Aerospace and Astronautics, Shenzhen, China, 10–12 December 2008; pp. 1–6.
[15]
Suykens, J.A.K.; Vandewalle, J. Least squares support vector machine classifiers. Neural Process. Lett. 1999, 9, 293–300.
[16]
Suykens, J.A.K.; Lukas, L.; Vandewalle, J. Spare Least Squares Support Vector Machine Classifiers. Proceeding of the European Symposium on Artificial Neural Networks, Bruges, Belgium, 26–28 April 2000; pp. 37–42.
[17]
Khawaja, T.; Vachtsevanos, G. A Novel Architecture for On-line Failure Pognosis Using Probabilistic Least Squares Support Vector Regression Mmachines. Proceeding of Annual Conference of the Prognostics and Health Management Society, San Diego, CA, USA, 27 September–12 October 009; pp. 1–8.
[18]
Ge, Z.G.; Song, Z.H. Online monitoring of nonlinear multiple mode processes based on adaptive local model approach. Control Eng. Pract. 2008, 16, 1427–1437.
[19]
Baum, L.E.; Petrie, T. Statistical inference for probabilistic functions of finite state markov chain. Ann. Math. Statist. 1966, 37, 1554–1563.
[20]
Atlas, L.; Ostendorf, M.; Bernard, G.D. Hidden Markov Models for Monitoring Machining Tool-Wear. Proceeding of 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP'00, Istanbul, Turkey, 5–9 June 2000; pp. 3887–3890.
[21]
Lee, J.M.; Kim, S.J.; Hwang, Y.; Song, C.S. Diagnosis of mechanical fault signals using continuous hidden markov model. J. Sound Vib. 2004, 27, 1065–1080.
[22]
Ocak, H.; Loparo, K.A. A New Bearing Fault Detection and Diagnosis Scheme Based on Hidden Markov Modeling of Vibration Signals. Proceeding of the International Conference on Acoustics, Speech and Signal Processing, Cleveland, OH, USA, 7–11 May 2001; pp. 3141–3144.
[23]
Ertunc, H.M.; Loparo, K.A. A decision fusion algorithm for tool wear condition monitoring in drilling. Int. J. Machine Tools Manuf. 2001, 41, 1347–1362.
[24]
Wang, L.; Mehrabi, M.G.; Kannatey-Asibu, E. Hidden markov model-based tool wear monitoring in machining. ASME J. Manuf. Sci. Eng. 2002, 124, 651–658.
[25]
Ocak, H.; Loparo, K.A. HMM-based fault detection and diagnosis scheme for rolling element bearings. J. Vib. Acoust. 2005, 127, 299–306.
[26]
Blimes, J.A. A Gentle Tutor. of the EM Algorithm and Its Appl. to Parameter Estim. for Gaussian Mixture and Hidden Markov Models. Report; University of Berkeley: Berkeley, CA, USA, 1998.
[27]
Baruah, P.; Chinnam, R.B. HMMs for diagnostics and prognostics in machining processes. Int. J. Production Res. 2005, 43, 1275–1293.
[28]
Suykens, J.A.K.; Brabanter, J.D.; Lukas, L.; Vandewalle, J. Weighted least squares support vector machines: Robustness and sparse approximation. Neurocomputing 2002, 48, 85–105.
[29]
The Bearing Data Center, the Case Western Reverse University. Available online: http://www.eecs.case.edu/laboratory/bearing/welcom_overview.htm (accessed on 20 March 2012).
