This academic paper discusses a distributed decision-making approach for task assignment and condition-based machine health maintenance in an industrial setting. The authors propose the use of Markov decision processes as the basis for the decision-making agents, allowing for the incorporation of uncertainty in the decision-making process. The paper includes detailed mathematical models and a practical execution strategy, demonstrated through a case study based on milling machine tool degradation data. The proposed approach offers flexibility, allowing for offline computation and analysis of the decision-making policy. The authors suggest future work could involve the use of artificial intelligence to learn the cost parameters associated with their proposed model.
Publication date: 2 Feb 2024
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2402.00042
