Integrated Approach for Maintenance Planning and Scheduling in a Flow Shop Using Deep Reinforcement Learning

Abstract

Maintenance scheduling is critical for many industries, and Deep Reinforcement Learning (DRL) has shown great potential in optimizing scheduling decisions in complex and dynamic environments. This proposal introduces an integrated simulation tool and DRL algorithm for effective maintenance event scheduling and planning in a Flow Shop production line. This comprehensive solution aims to optimize maintenance plans and maximize productivity by combining simulation capabilities with intelligent decision-making via DRL. The integrated simulation tool replicates the production line Flow Shop in a virtual environment, allowing for precise modeling and simulation of machine operations, job flows, and maintenance events. The tool evaluates different maintenance procedures and their impact on overall performance by capturing the system’s dynamics and complexities. The novelty of the approach lies in the fact that the training phase is performed on a single machine, and the policy developed is tested on a Flow Shop line with machines with the same Weibull parameters (α and β) and with machines with different Weibull parameters. The proposed integrated simulation tool and DRL algorithm provide a powerful solution for the scheduling and planning of maintenance events in a production line Flow Shop. By combining simulation capabilities with intelligent decision-making through DRL, this approach offers a comprehensive solution to optimize maintenance strategies and enhance overall production performance in all experimental settings tested.