Integrated Prescriptive Maintenance and Production Planning: a Machine Learning Approach for the Development of an Autonomous Decision Support Agent
Mohaiad Elbasheer, Francesco Longo, Giovanni Mirabelli, Antonio Padovano, Vittorio Solina, Simone Talarico
Abstract
Machine Learning (ML) practice represents a vital construct for developing intelligent Cyber-Physical Production Systems (CPPS) capable of making timely optimization for Maintenance and Planning actions. Integrating Adaptive Production Planning and Prescriptive Maintenance (PsM) in future factories provides a novel perspective for flexibility, customization, and resilience of production plans. To this end, we propose a framework for developing an intelligent Decision Support Agent (DSA) for integrated PsM and production planning and control (PPC) based on Reinforcement Learning. The paper highlights the practical implications of developing an autonomous DSA from an ML perspective using a demonstrative use-case of integrated Maintenance and PPC.