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

José Carlos Almeida (), Bernardete Ribeiro () and Alberto Cardoso ()
Additional contact information
José Carlos Almeida: University of Coimbra
Bernardete Ribeiro: University of Coimbra
Alberto Cardoso: University of Coimbra

SN Operations Research Forum, 2025, vol. 6, issue 3, 1-34

Abstract: Abstract 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.

Keywords: Deep Q-network; Industry 5.0; Human-centered design; Multi-criteria decision-making; Multi-objective reinforcement learning; Multipolicy approach (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s43069-025-00539-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:snopef:v:6:y:2025:i:3:d:10.1007_s43069-025-00539-5

Ordering information: This journal article can be ordered from
https://www.springer.com/journal/43069

DOI: 10.1007/s43069-025-00539-5

Access Statistics for this article

SN Operations Research Forum is currently edited by Marco Lübbecke

More articles in SN Operations Research Forum from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().