Reinforcement learning for dynamic condition-based maintenance of a system with individually repairable components
Authors:
- 4 June 2020
- journal article
- research article
- Published by Taylor & Francis in Quality Engineering
- Vol. 32 (3) , 388-408
Abstract
In this article, a reinforcement learning approach is used to develop a new dynamic maintenance policy for multi-component systems with individually repairable components, where each component experiences two competing failure processes of degradation and random shocks. The gamma process is used to model the degradation path of each component in the system. It is assumed that each incoming shock causes damage to the degradation path of all the components. A combination of component degradation is then used to define the system states. The optimal maintenance action for each component at each specific state is found by modeling the problem as Markov decision process and solving it by using a Q-learning algorithm. Using a reinforcement learning approach provides a more time-efficient and cost-effective method compared to the traditional maintenance optimization solutions, and it can also provide a dynamic maintenance policy for each specific degradation state of the system which is more useful and beneficial compared to the fixed or stationary maintenance plan which is often proposed by previous studies. A numerical example shows how the reinforcement learning can be used to find the optimal maintenance action for systems with different system configurations.Keywords
This publication has 33 references indexed in Scilit:
- Reliability modeling for degradation-shock dependence systems with multiple species of shocksReliability Engineering & System Safety, 2019
- Degradation modeling and classification of mixed populations using segmental continuous hidden Markov modelsQuality and Reliability Engineering International, 2018
- A condition-based maintenance policy for multi-component systems with Lévy copulas dependenceReliability Engineering & System Safety, 2016
- Availability and cost-centered preventive maintenance scheduling of continuous operating series systems using multi-objective genetic algorithm: A case studyQuality Engineering, 2015
- Condition-based maintenance using the inverse Gaussian degradation modelEuropean Journal of Operational Research, 2015
- Condition-Based Maintenance via Simulation and a Targeted Bayesian Network MetamodelQuality Engineering, 2013
- A maintenance optimization model for mission-oriented systems based on Wiener degradationReliability Engineering & System Safety, 2013
- Availability Analysis of Repairable Mechanical Systems Using Analytical Semi-Markov ApproachQuality Engineering, 2013
- An overview of time-based and condition-based maintenance in industrial applicationComputers & Industrial Engineering, 2012
- System health monitoring and prognostics — a review of current paradigms and practicesThe International Journal of Advanced Manufacturing Technology, 2006