Production planning and scheduling have been profoundly changed by the incorporation of Industry 4.0 technology, especially when it comes to the application of Artificial Intelligence (AI) to optimize the Master Production Schedule (MPS). In dynamic industrial settings, traditional MPS techniques frequently have trouble with scalability, realtime flexibility, and managing complicated restrictions. To improve MPS decision-making, this study suggests an AI-driven optimization framework that makes use of machine learning (ML), reinforcement learning (RL), and evolutionary algorithms (EA). An industrial case study in the automobile industry, where AI-based approaches are applied to actual production data, validates the suggested methodology. When compared to conventional heuristic and rule-based methods, experimental results show notable gains in processing efficiency, forecasting accuracy, and adaptive scheduling. The results demonstrate AI’s potential for real-time production planning, which could result in more flexible and economical manufacturing procedures. In order to further improve the capabilities of smart manufacturing, future research directions include enhancing the interpretability of AI models, hybridizing optimization methodologies, and integrating AI with cyberphysical systems (CPS) and the Internet of Things (IoT).
Chentoufi et al. (Mon,) studied this question.