Joint optimization of inspection and maintenance strategy for complex multi-component systems using a quantum-inspired genetic algorithm

Advances in sensor and data technology enable real-time condition monitoring, thus extending the opportunities for condition-based maintenance (CBM) to be applied in practice. In this paper, a joint inspection and maintenance strategy for multi-component systems is proposed. The objective of this strategy is to minimize the long-run expected operational cost by jointly considering the inspection frequency of each health monitor in the system and the threshold for the maintenance initialization. To find the optimal strategy, a dynamic Bayesian network-based maintenance model is developed at first to provide reasoning of the dynamic reliability of degrading components in the multi-component system, in which complex relationship among inspections by different health monitors, different failure modes in the system, and different maintenance actions to system components are considered and quantified. Then, a quantum-inspired genetic algorithm (QGA) is proposed to optimize the strategy. With quantum encoding method, improved rotation gate, and specially designed crossover and mutation operators, the QGA is able to find the optimal strategy for multi-component systems with a general system structure. An example simplified from real practice is presented to demonstrate the effectiveness and advantages of the proposed strategy and the optimization algorithm, with comparison to similar strategies and traditional intelligent optimization algorithms.