A Multi-objective Reinforcement Learning Model to Support Decision-Makers in Assessing Key Maintenance Factors for Sustainable Manufacturing

Industry 5.0, the fifth industrial revolution, envisions collaboration between humans and machines, where human intelligence directs decision-making and machines handle empirical processing. This paper presents a decision support framework that combines human-centered design with a multi-objective reinforcement learning model (MORL), specifically multi-criteria decision-making with deep Q-networks (MCDM-DQN). This approach evaluates the importance of maintenance factors in achieving sustainability in manufacturing, emphasizing the perspectives of various stakeholders. By fostering collaboration between stakeholders and the MCDM-DQN, the framework effectively integrates their feedback, improving prioritization according to the operational context of the organization. The experiments confirmed the effectiveness of the method, demonstrating that MCDM-DQN efficiently ranks key factors while adhering to conventional methods and offering advanced features such as real-time feedback. These results assist decision-makers in selecting appropriate sustainable strategies and improve the synergy between advanced automation and human insight within the Industry 5.0 framework, providing valuable guidance to leaders and practitioners.