Self-learning brainstorm optimization for synchronization of operations and maintenance toward dual resource-constrained flexible job shops

In semi-automated flexible job shop manufacturing scenarios such as furniture customization and circuit board assembly, machine and worker resources need to be flexibly assigned to the processing of each operation, to improve the efficiency of human-machine collaboration and reduce the makespan. Driven by the practical need, the dual resource-constrained flexible job shop scheduling problem (DRCFJSP) has gradually attracted attention from the academic community. However, preventive maintenance (PM) of machines as a key constraint tends to be overlooked in previous research. In this study, a synchronization optimization of the DRCFJSP and PM scheduling is proposed and a joint decision-making model is established, to strike a balance between flexible job shop operations and maintenance. A self-learning brainstorm optimization algorithm (SLBOA) is developed to solve the model. In the SLBOA, an adaptive K-means algorithm based on the silhouette method is employed for flexible clustering, and four global update strategies are adaptively selected using the Q-learning algorithm to facilitate an effective interaction of individuals between different clusters. Furthermore, two knowledge-based local search methods are used to enhance the exploration of elite solutions within the necessary neighborhood structure. Experimental results show that the SLBOA outperforms four state-of-the-art algorithms in solving the proposed DRCFJSP with PM.