2026-07-25T00:33:48Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:22123 2024-11-26T15:16:37Z ddc:004 open_access

Using Multi-Modal LLMs to Create Models for Fault Diagnosis (Short Paper) Merkelbach, Silke Diedrich, Alexander Sztyber-Betley, Anna Travé-Massuyès, Louise Chanthery, Elodie Niggemann, Oliver Dumitrescu, Roman Fault Diagnosis Large Language Models LLMs Physical Modelling Process Industry P&IDs Creating models that are usable for fault diagnosis is hard. This is especially true for cyber-physical systems that are subject to architectural changes and may need to be adapted to different product variants intermittently. We therefore can no longer rely on expert-defined and static models for many systems. Instead, models need to be created more cheaply and need to adapt to different circumstances. In this article we present a novel approach to create physical models for process industry systems using multi-modal large language models (i.e ChatGPT). We present a five-step prompting approach that uses a piping and instrumentation diagram (P&ID) and natural language prompts as its input. We show that we are able to generate physical models of three systems of a well-known benchmark. We further show that we are able to diagnose faults for all of these systems by using the Fault Diagnosis Toolbox. We found that while multi-modal large language models (MLLMs) are a promising method for automated model creation, they have significant drawbacks. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Silke Merkelbach and Alexander Diedrich and Anna Sztyber-Betley and Louise Travé-Massuyès and Elodie Chanthery and Oliver Niggemann and Roman Dumitrescu 2024 Is Part Of OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/OASIcs.DX.2024.31 urn:nbn:de:0030-drops-221236 https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.31 eng https://creativecommons.org/licenses/by/4.0/legalcode