IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem

IoT-based enterprise information management system for cost control and enterprise job-shop scheduling problem

연구 분야: Safety

학회: Service Oriented Computing and Applications

The Internet of Things (IoT) transforms modern industries, particularly enterprise information management and supply chain optimization. However, integrating IoT technologies into manufacturing systems introduces challenges, especially in inventory cost control and job-shop scheduling (JSP), which involves optimizing production under complex, dynamic constraints. This research proposes a novel approach to solving JSP by leveraging a Heterogeneous Genetic Algorithm (HGA) and a Hybrid Particle Swarm Optimization (HPSO). HGA addresses traditional Genetic Algorithms (GA) limitations by incorporating immune mechanisms, such as memory and mutation strategies, to prevent premature convergence and enhance exploration capabilities. HPSO is specifically designed to improve job sequencing and minimize production time by combining the strengths of PSO with genetic operators. This hybridization enables HPSOs to balance global and local search efficiency, making it more effective than traditional PSOs in handling the complexities of JSP. In addition to improving HPSO's cost optimization and schedule efficiency performance, this research made significant contributions to the field by hybridizing genetic algorithms with HPSO and introducing a double-chain encoding method for machine selection and job sequencing. The proposed approach is validated through empirical studies, demonstrating that HGA and HPSO significantly outperform conventional scheduling techniques.