Enhancing Manufacturing Efficiency Through Symmetry-Aware Adaptive Ant Colony Optimization Algorithm for Integrated Process Planning and Scheduling

Integrated process planning and scheduling (IPPS) is an intricate and vital issue in smart manufacturing, requiring the coordinated optimization of both process plans and production schedules under multiple resource and precedence constraints. This paper presents a novel optimization framework, symmetry-aware adaptive Ant Colony Optimization (SA-AACO), designed to resolve key limitations in existing metaheuristic approaches. The proposed method introduces three core innovations: (1) a symmetry-awareness mechanism to eliminate redundant solutions arising from symmetrically equivalent configurations; (2) an adaptive pheromone-updating strategy that dynamically balances exploration and exploitation; and (3) a dynamic idle time penalty system, integrated with time window-based machine selection. Benchmarked across ten IPPS scenarios, SA-AACO achieves a superior makespan in 9/10 cases (e.g., 29.1% improvement over CCGA in Problem 1) and executes 18-part processing within 30 min. While MMCO marginally outperforms SA-AACO in Problem 10 (makespan: 427 vs. 483), SA-AACO’s consistent dominance across diverse scales underscores the feasibility of its application in industry to balance quality and efficiency. By unifying symmetry handling and adaptive learning, this work advances the reconfigurability of IPPS solutions for dynamic industrial environments.