Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

S2S-FDD: Bridging Industrial Time Series and Natural Language for Explainable Zero-shot Fault Diagnosis

Baoxue Li, Chunhui Zhao

TL;DR

A Signals-to-Semantics fault diagnosis (S2S-FDD) framework that bridges high-dimensional sensor signals with natural language semantics through two key innovations that support human-in-the-loop feedback for continuous refinement is proposed.

Abstract

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.

S2S-FDD: Bridging Industrial Time Series and Natural Language for Explainable Zero-shot Fault Diagnosis

TL;DR

A Signals-to-Semantics fault diagnosis (S2S-FDD) framework that bridges high-dimensional sensor signals with natural language semantics through two key innovations that support human-in-the-loop feedback for continuous refinement is proposed.

Abstract

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.
Paper Structure (9 sections, 14 equations, 2 figures, 3 tables, 1 algorithm)

This paper contains 9 sections, 14 equations, 2 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Method
  3. The Signals to Semantics operator
  4. Multi-turn tree-structured diagnosis method
  5. Theoretical Analysis of Fault Detectability
  6. Experiments
  7. Experimental setup
  8. Comparison of diagnosis accuracy
  9. Conclusion

Figures (2)

  • Figure 1: Overview of the proposed S2S framework. It contains two key components, including the S2S operator and multi-turn tree-structured diagnosis method. The former converts raw sensor data into concise and domain-aware natural language summaries. Based on the descriptions, the latter retrieves relevant historical maintenance documents and conducts zero-shot fault diagnosis.
  • Figure 2: Sketch of the multiphase flow process.