Answers are grounded in this paper and cite their sources.
We propose a decentralized fault diagnosis approach for manufacturing systems by integrating integer linear programming (ILP) techniques with labeled Petri nets. The decentralized architecture consists of multiple local diagnosis sites and a central coordinator. Each local site operates in parallel to compute diagnosis results based on local observations and transmits them to the coordinator. The coordinator then derives global diagnosis decisions from the received information. To support this architecture, we design two dedicated diagnosis algorithms: one for the local sites and another for the coordinator. By leveraging ILP techniques, the local diagnosis algorithm avoids exhaustive enumeration of all transition sequences consistent with a given observation. In contrast to the existing ILP‐based studies, we use a more general model, i.e., labeled Petri nets, to tackle the decentralized diagnosis problem. The effectiveness of the proposed approach is demonstrated through a numerical case study of a manufacturing system producing bolts and nuts. The results show that our approach achieves a clear runtime advantage, with runtime growing only moderately with observation length, in contrast to the pronounced increase observed in related approaches.
No takes yet. Share an insight, caveat, or question.
Zhu et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: