A reinforcement learning/ad-hoc planning and scheduling mechanism for flexible and sustainable manufacturing systems

The process scheduling is still considered a crucial subject for manufacturing industry, due to the ever-changing circumstances dictated by the nowadays product demand and customer trends. These conditions are often associated with increasing costs and energy consumption, considerably affecting the long-term sustainability of manufacturing plants. To mitigate that effect, one should create an effective strategy tailoring integrated operations and processes to the customer demand and trends faced by the nowadays industry. A well-known approach to this matter is the technologies introduced by manufacturing paradigms, e.g., Industry 4.0 and smart manufacturing. As suggested in literature, these technologies are capable of helping decision-makers by continuously gathering significant information about the state of machinery and manufactured goods. This information is thereafter utilized to identify weaknesses and strengths demonstrated within manufacturing plants. To this end, the present paper presents a process optimization framework implemented in a three-stage production line prone to systematic degradation faults. Aiming at strengthening profitability, the framework engages reinforcement learning with ad-hoc manufacturing/maintenance control in decision-making carried out in implemented machines. Simulation experiments showed improved process planning and inventory management enabling cost-effective green and sustainable manufacturing in manufacturing plants.