GA-FLOPS: a novel multi-objective genetic algorithm framework for optimizing layouts in print production facility

Facility layout optimization is a critical aspect of manufacturing efficiency, directly impacting production costs, material handling, energy consumption, and operational safety. This study introduces GA-FLOPS (Genetic Algorithm for Facility Layout Optimization with Production and Safety), a novel multi-objective evolutionary framework tailored to address the complex requirements of real-world facility layout problems (FLPs). The proposed method integrates essential metrics, including material movement cost, energy consumption, production volume flow, and safety penalties, into a unified fitness function to holistically optimize layout configurations. Unlike traditional heuristics, GA-FLOPS dynamically adapts to production-specific constraints and incorporates robust genetic evolution mechanisms, such as adaptive mutation and elite-preserving strategies, ensuring both rapid convergence and solution stability. The performance of GA-FLOPS is benchmarked against Simulated Annealing (SA), Particle Swarm Optimization (PSO), and Deep Reinforcement Learning (DRL), using a print production facility as the testbed. Results demonstrate that GA-FLOPS achieves a significant 62.28% reduction in the fitness score over the initial layout, outperforming alternative methods in terms of efficiency, convergence speed, and robustness to layout perturbations. By addressing critical gaps in previous research and introducing a scalable, production-aware optimization approach, this work advances the field of FLP and provides a flexible framework applicable across diverse manufacturing industries.