Machine scheduling optimization via multi-strategy information-aware genetic algorithm in steelmaking continuous casting industrial process

Abstract

Scheduling optimization of the steelmaking continuous casting (SCC) process is vital for enhancing production efficiency and reducing costs in steel enterprises. However, the stringent requirement for uninterrupted casting and the severe imbalance in machine allocation present significant challenges for conventional intelligent optimization algorithms. In particular, these algorithms face the problem of balancing global exploration, local exploitation, and limited population diversity. To this end, this paper proposes a novel multi-strategy information-aware genetic algorithm (MSIAGA) that integrates the requirement for uninterrupted production with the synergy of multiple innovative strategies to achieve optimal equipment scheduling. First, a continuous production-guided chromosome encoding method is developed to ensure that equipment scheduling strictly adheres to uninterrupted casting conditions. Second, a dynamically adaptive mutation strategy is designed to enhance the global exploration and local search capabilities of the model. In addition, a dynamic elite retention strategy is introduced, utilizing retention scores to prioritize elite solutions and enhance population diversity. Finally, extensive experimental results of 21 SCC scheduling cases with different complexity demonstrate that the proposed method outperforms several other representative methods.