A multi-strategy fruit fly optimization algorithm for the distributed permutation flowshop scheduling problem with sequence-dependent setup times

Distributed manufacturing has become one of the mainstream manufacturing modes today and is widely present in industries such as aviation and electronics. However, in actual production processes, unexpected situations such as machine failures and tool changes may occur, which require time. Based on practical needs, this paper studies a distributed permutation flow shop scheduling problem with sequence-dependent setup times (DPFSP/SDST) aimed at minimizing the makespan and proposes a hybrid multi-strategy fruit fly optimization algorithm (HMFOA) to solve it. In HMFOA, three strategies are constructed to initialize the positions of some individual flies in the solution space to improve population diversity. In the smell search phase, four problem-oriented neighborhood perturbation operators are designed, and sinusoidal optimization algorithm is introduced to control the search range, which improves the global search ability of the algorithm. In the visual search phase, a position reconstruction strategy is proposed to divide individual flies into different populations based on their mass. Through the interaction of individuals from different populations, the convergence is accelerated and the algorithm efficiency is improved. In addition, a local search strategy is designed to guide the flies to more promising areas. Based on well-known examples of DPFSP in the literature, a comprehensive test set was generated for DPFSP/SDST, taking into account various combinations of jobs, machines, factories, and SDST, resulting in 270 benchmark instances used to validate the performance of HMFOA, and compared to eight other advanced algorithms. The relative percentage deviation of HMFOA is 1.00%, which is significant improvement.