Optimizing production planning and sequencing in hot strip mills: an approach using multi-objective genetic algorithms

Planning and sequencing for hot strip mills in the steel industry is a challenging, complex problem that has fascinated optimization researchers and practitioners alike. This paper applies a combinatory heuristic search and a multi-objective metaheuristic that is a novel approach called HSMO-NSGA-II and employs the HSMO heuristic search method and NSGA-II multi-objective genetic optimization as a metaheuristic algorithm to address complex hot strip mills scheduling tasks. This research aims to enhance the efficiency and effectiveness of production planning and sequencing in hot strip mill, while minimizing operational costs and maximizing rolling utilization. The output consists of slabs categorized into three parts, which converge toward a set of Pareto-optimal solutions while maintaining diversity across the entire solution space. The results demonstrate a significant improvement in comparing the base methods with the HSMO-NSGA-II method, and the proposed method shows better average performance at 23.01%. Notably, the HSMO-NSGA-II method demonstrated a remarkable improvement in performance across the evaluated scenarios, showcasing its potential to enhance productivity and operational efficiency in industrial applications significantly. These findings not only support the viability of using advanced genetic algorithms in complex industrial settings but also open avenues for future research into hybrid optimization techniques.