Optimal maintenance planning for repairable multi-component systems subject to dependent competing risks

Abstract

Many complex multi-component systems suffer from dependent competing risks. The reliability modeling and maintenance planning of repairable dependent competing risks systems are challenging tasks because the repair of the failed component can change the lifetime of the other components when multiple components fail dependently. This article first proposes a generally dependent latent age model to capture the dependence of competing risks under general component repairs. Based on the proposed reliability model, both system- and component-level periodic inspection-based maintenance polices are considered for repairable multi-component systems that are subject to dependent competing risks. Under the system-level maintenance policy, the entire system is restored to the as-good-as-new state once a failure is detected. While under the component-level maintenance policy, only the failed component is repaired imperfectly. The optimal solution of the system-level policy is obtained by using renewal theory. The optimal solution of the component-level policy, however, cannot be obtained analytically, due to its complex failure and repair characteristics. A simulation-based optimization approach with stochastic approximation is developed to solve the optimization problem for the component-level policy. The developed methods are illustrated by using a cylinder head assembly cell that consists of multiple stations.

Keywords:

• Generalized dependent latent age model
• copula
• simulation-based optimization
• stochastic approximation

Acknowledgements

The authors thank the Associate Editor and the referees for their valuable comments that helped to improve this article.

Funding

The work is supported by the National Science Foundation under grant CMMI-1404276 to Wayne State Univer-sity.

Additional information

Notes on contributors

Nailong Zhang

Nailong Zhang is a Ph.D. candidate in the Department of Industrial & Systems Engineering at Wayne State University. He received his B.Eng. degree in Mechanical Engineering from Harbin Institute of Technology, Harbin, China, in 2009. His research interests include statistical methods in reliability engineering as well as maintenance planning for complex systems.

Qingyu Yang

Qingyu Yang received B.S. and M.S. degrees in Automatic Control and Intelligent Systems from the University of Science and Technology of China in 2000 and 2003, respectively, an M.S. degree in Statistics, and Ph.D. degree in Industrial Engineering from the University of Iowa in 2007 and 2008, respectively. Currently, he is an Assistant Professor in the Department of Industrial and Systems Engineering at Wayne State University. His research interests include statistical data analysis, reliability and quality, and complex system modeling. He is a member of INFORMS and IIE.