Fault diagnosis is critical for the safe operation of industrial systems. Conventional diagnosis models typically produce abstract outputs such as anomaly scores or fault categories, failing to answer critical operational questions like "Why" or "How to repair". While large language models (LLMs) offer strong generalization and reasoning abilities, their training on discrete textual corpora creates a semantic gap when processing high-dimensional, temporal industrial signals. To address this challenge, we propose a Signals-to-Semantics fault diagnosis (S2S-FDD) framework that bridges high-dimensional sensor signals with natural language semantics through two key innovations: We first design a Signal-to-Semantic operator to convert abstract time-series signals into natural language summaries, capturing trends, periodicity, and deviations. Based on the descriptions, we design a multi-turn tree-structured diagnosis method to perform fault diagnosis by referencing historical maintenance documents and dynamically querying additional signals. The framework further supports human-in-the-loop feedback for continuous refinement. Experiments on the multiphase flow process show the feasibility and effectiveness of the proposed method for explainable zero-shot fault diagnosis.
URA Research Group, Ho Chi Minh City University of Technology (HCMUT), Vietnam · Ho Chi Minh City International University (HCMIU), Vietnam · University of South-Eastern Norway, Norway · Japan Advanced Institute of Science · Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, F-33400 Talence, France · University of Naples Parthenope, Italy · VNU Information Technology Institute, Vietnam National University, Vietnam · Visual Intelligence Lab, School of Computer Science \& Insight Center for Data Analyitcs, University of Galway, Ireland · Sapienza University of Rome, Italy
Bridging LLMs and Symbolic Reasoning in Educational QA Systems: Insights from the XAI Challenge at IJCNN 2025
