Solving a many-objective PFSP with reinforcement cumulative prospect theory in low-volume PCB manufacturing

Permutation flow-shop scheduling problems with many objectives have wide applications in the modern manufacturing domain such as the printed circuit board (PCB) industry. In this paper, an upgraded method called reinforcement cumulative prospect theory is proposed for solving many-objective permutation flow-shop scheduling problems. Reinforcement cumulative prospect theory is determined by two reference points, the improved prospect value function, and the entropy-based decision weight function. A novel many-objective optimization algorithm, namely, an optimal foraging algorithm based on the reinforcement cumulative prospect theory (OFA/RCPT), is presented. The comprehensive prospect value is used as the fitness strategy of the OFA/RCPT algorithm to guide the optimization process. The performance of the proposed algorithm is assessed by a comparison with nine state-of-the-art algorithms. Three classification experiments are carried out on six Walking-Fish-Group test cases, seven permutation flow-shop scheduling benchmark instances, and a practical permutation flow-shop scheduling problem in low-volume PCB manufacturing. For the experiment, four performance metrics are adopted, and the commercial software Quest is used to simulate a PCB production line. The simulation results show that the proposed algorithm has better performance than the other algorithms.