Monitoring and condition-based maintenance with abrupt change in a system’s deterioration rate

Abstract

In this paper, the maintenance of a system which undergoes a change in its deterioration rate is considered. The time of change of regime and the parameters after the change are unknown. To deal with unknown change time and unknown parameters, a detection procedure based on a suitable online change detection algorithm is used. The paper proposes a maintenance decision rule versus detection policy in order to minimise the long-run average maintenance cost, and the performances of this policy are studied through numerical implementations.

Keywords:

• monitoring
• condition-based maintenance
• abrupt online change detection
• online change isolation
• cost model
• stochastic processes

Additional information

Notes on contributors

Mitra Fouladirad

Mitra Fouladirad after gaining her Master degree in statistical mathematics from the University of Paris VI joined the University of Troyes Technology (UTT) where she obtained her PhD degree in statistical fault detection in 2005. She has been working as an associated professor at the Statistics, Operations Research and Numerical Simulation Department since 2006. She is a member of Charles Delaunay Institute CNRS FRE 2848 (Systems Modeling and Dependability Group). Her main field of activity is condition-based maintenance of gradually deteriorating systems. She focused on the use of online monitoring, especially the online change detection algorithms in the framework of maintenance of deteriorating systems.

Antoine Grall

Antoine Grall received his Information Processing Engineering degree in 1989, MS degree in systems control in 1989 and PhD degree in 1992 from Compiègne University of Technology, France. He is a professor of reliability and maintenance engineering at the Troyes University of Technology and currently head of the Statistics, Operations Research and Numerical Simulation Department. He is a member of Charles Delaunay Institute (Systems Modeling and Dependability Group), CNRS UMR. His current research interests include stochastic modelling for residual lifetime prognosis, maintenance policies evaluation and optimization, stochastic degradation modelling and modelling for quantitative analysis of systems dependability.