PHM Techniques for Condition-Based Maintenance Based on Hybrid System Model Representation



Published Oct 10, 2010
Claudia Maria García Teresa Escobet Joseba Quevedo


Condition-based maintenance (CBM) is a maintenance strategy that uses diagnosis and prognosis to determine system‟s health. The overall objective of this paper is design a real-time monitoring system for CBM, applied to a conveyor belt system, based on the integration of prognosis and health management technologies (PHM) and hybrid models. This work is focus on the prognosis part of PHM. A forecasting model based in Adaptive- Network-based Fuzzy Inference Systems (ANFIS) combined with a Gray-Scale Health Index (HI) is implemented to evaluate the system degradation. As shown throughout the paper, the hybrid model allows extracting the main features of the system that will be used in the prognostic algorithm. The obtained results show that the ANFIS prediction model linked to the degradation index HI can track the system degradation, thus have the potential for being used as a tool suitable for condition-based maintenance.

How to Cite

Maria García, C. ., Escobet, T. ., & Quevedo, J. . (2010). PHM Techniques for Condition-Based Maintenance Based on Hybrid System Model Representation. Annual Conference of the PHM Society, 2(1).
Abstract 683 | PDF Downloads 116



adaptive neuro-fuzzy inference system (ANFIS), CBM, PHM, Hybrid Systems, behavior automaton

Bayoudh, M., Travé-Massuyès, L., Olive, X. "Hybrid System Diagnosability by Abstracting Faulty Continuous Dynamics." 17th International Principes of Diagnosis Workshop. 2006.
Bemporad, A. "Master course tutorial: Model Predictive Control of Hybrid Systems." Terrassa, Barcelona, 2006.
Bolander, N., Qiu, H., Eklund, N., Hindle, E., Rosenfeld, T. "Physics-based Remaining Useful Life Prediction for Aircraft Engine Bearing Prognosis." Annula Conference of Prognosis and Health Management Society. San Diego, 2009.
Kalgren, P.W., Byington, C.S., P.E., Roemer M.J., Watson, M.J. "Defining PHM, a lexical evolution of maintenance and logistics." IEEE AUTOTESTCON. Anaheim, California, 2006. 353-358.
Luo, J., Pattipati, K.P., Qiao, L., Chigusa, S., “Model- Based Prognostic Techniques Applied to a Suspension System”. IEEE Transactions on systems, man, and cybernetics – Part A: Systems and humans, 38(5) 2008, 1156-1168.
Lygeros, J. "Lecture Notes on Hybrid Systems." 2004, Hybrid system course, Master in automatic control and Robotics 2008-09.
Muller A., Suhner M.C., Iung B. "Formalisation of a new prognosis model for supporting proactive maintenance implementation on industrial system." Reliability Engineering and System Safety, 93 (2), 2008: 234-253.
Sheppard, J.W., Wilmering,T.J, Kaufman, M.A. "IEEE Standards for Prognostics and Health Management." IEEE AUTOTESTCON . Salt Lake City, 2008.
Tran, V.T., Yang, B.S. and Tan, A.C.C. "Multi-step ahead direct prediction for machine condition prognosis using regression trees and neuro-fuzzy systems." Expert Systems with Applications, 36, 2009: 9378–9387.
Velásquez, J.D., Dyner, I., Souza, R.C., “Modelación de Series Temporales Usando ANFIS.” Revista Iberoamericana de Inteligencia Artificial. Vol. 23(17),2004.
Zhang, H., Kang, R., Pecht, M. "A Hibrid Prognostic and Health Management Approach for Condition- Based Maintenance." Industrial Engineering and Engineering Management, 2009. IEEM 2009. IEEE International Conference on. Hong Kong, 2009. 1165-1169.
Poster Presentations