An Improved Seagull Optimization Algorithm for Flexible Job-shop Scheduling Problem

Job-shop scheduling problem is the core link and key technology to realize smart factory and develop smart manufacturing technology. Among them, the flexible job-shop scheduling problem (FJSP) which is more consistent with the actual production and processing mode has been focused. This paper proposes an improved seagull optimization algorithm(ISOA) for solving the FJSP. The ISOA uses chaos initialization and reverse learning to optimize initial population, and introduces Q-learning to change the fitting parameters to balance global search and local search. In addition, we propose a local search model that is adaptive iterative process to enhance the algorithm's optimization search capability. The results of the experiment proved that the algorithm is superior in terms of optimization speed and scheduling results.