Application of Bio-Inspired Particle Swarm Optimization Algorithm for Production Scheduling Optimization

Production scheduling is a fundamental aspect of manufacturing systems that significantly affects operational efficiency, resource allocation, and delivery performance. Traditional scheduling methods often struggle to solve complex, dynamic scheduling problems, resulting in suboptimal job sequencing and increased makespan. This research aims to develop a hybrid optimization algorithm by integrating Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) to address inefficiencies in job shop scheduling. The proposed hybrid PSO-GA method leverages the global exploration ability of PSO and the local refinement strength of GA. The algorithm was tested on several benchmark datasets using performance metrics such as makespan, tardiness, and machine utilization. Experimental results demonstrate that the hybrid approach achieved a 12.7% improvement over standard PSO and a 15.4% improvement over GA in terms of makespan. The convergence curve also showed stable and faster optimization. These findings confirm that the hybrid PSO-GA model provides a more effective and robust solution for complex production scheduling and has strong potential for real-time application in Industry 4.0 environments