Data driven simulation based optimization model for job-shop production planning and scheduling: an application in a digital twin shop floor

Effective Production Planning and Scheduling (PPS) is critical in industrial manufacturing for optimizing resources, reducing costs, and meeting deadlines. However, in complex environments like job shops, where the problem is NP-hard (non-deterministic polynomial time-hard) and characterized by unpredictability, traditional PPS models often struggle. These models lack real-time information, leading to infeasible solutions. Furthermore, existing literature does not adequately address the integration of planning and scheduling. This research proposes a Simulation-Based Optimization Model (SBOM) that combines simulation with a Hybrid Particle Swarm Optimization (HPSO) algorithm, enhanced by Digital Twin (DT) technology. The model, using Simio for real-time data integration, aims to optimize schedules, adapt to disruptions, and improve efficiency by providing feasible solutions based on real-time data. It ultimately delivers the best throughput in Industry 4.0-enabled integrated manufacturing environments. The experimental results demonstrate that the model outperforms traditional methods. Tested on the shop floor, the results validate the model’s effectiveness in efficiently managing real-time operations while adeptly handling dynamic changes.