Reinforcement Learning-Based Production Scheduling in an Industry-Based Coating Scenario Using the Digital Model Playground

2026-08-14

AI Summary

This study addresses scheduling challenges in complex manufacturing environments, including sequence-dependent setups, stochastic disturbances, and due date constraints. Leveraging an open-source digital model playground, we developed a discrete-event simulation framework and trained agents using DQN and PPO algorithms to solve practical scheduling problems in industrial coating scenarios. The research validates the feasibility of reinforcement learning in real-world industrial settings, demonstrating that PPO achieves superior robustness and balanced improvements across key performance metrics. By bridging the gap between academic research and industrial application, this work provides both a reusable open-source simulation platform and empirically validated solutions for intelligent manufacturing scheduling.

Abstract

Production scheduling in complex manufacturing environments is challenging when sequence-dependent setup times, stochastic disturbances, and due-date constraints must be addressed simultaneously. While reinforcement learning (RL) methods have shown promising results in research, most studies rely on simplified benchmark processes, limiting their industrial relevance. This paper demonstrates the applicability of RL-based scheduling in an industry-inspired coating process that reflects practical complexities such as sequence-dependent setup times, machine breakdowns, and variable utilization. The open-source Digital Model Playground (DMPG), a discrete event simulation framework, is used to model the scenario and to train RL agents. Two standard algorithms, Deep Q-Networks and Proximal Policy Optimization, are benchmarked against conventional dispatching rules to illustrate feasibility and to provide a transparent testbed for further research. Results indicate that RL-based scheduling achieves balanced improvements across key performance indicators, with PPO delivering the most robust performance. The main contribution of this work is to bridge the gap between academic research and industrial practice by validating RL-based scheduling in a realistic, shareable scenario and by providing a reusable open-source framework for future studies.

Problem

• Production Scheduling
• Reinforcement Learning
• Sequence-dependent Setup Times
• Stochastic Disturbances
• Industrial Application

Innovation

• Reinforcement Learning Scheduling
• Digital Model Playground
• Industry-Based Coating Scenario
• Open-Source Simulation Framework
• Sequence-Dependent Setup Times