Adaptive Discrete Beluga Algorithm for Solving Flexible Job Shop Scheduling

Aiming at the problem that global exploration and local development cannot be effectively balanced after the improved intelligent optimization algorithm, an adaptive discrete beluga optimization algorithm based on Q learning is proposed with the maximum completion time of the flexible job shop as the optimization goal. First, the genetic algorithm and the beluga optimization algorithm are mixed to propose a discrete beluga algorithm with stronger global exploration capabilities. At the same time, elite individual strategies are introduced into the search strategy to improve local development capabilities. Taking individual beluga whales as Q-learning agents, Q-learning is used to adaptively determine the search strategy according to the situation of each beluga whale, ensuring the diversity of the population and avoiding falling into local optimality. Finally, the Brandimarte benchmark example is used to conduct simulation to verify the effectiveness of the improvement, and is compared with other improved algorithms. Simulation results prove that this algorithm can effectively balance global exploration and local development, thereby improving solution accuracy.