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

TL;DR

This paper introduces S2S-FDD, a novel framework that converts industrial sensor signals into natural language summaries and uses large language models for explainable, zero-shot fault diagnosis with human-in-the-loop capabilities.

Contribution

The paper proposes a new Signal-to-Semantic operator and a multi-turn tree-structured diagnosis method that bridge high-dimensional signals with natural language for industrial fault diagnosis.

Findings

Effective conversion of signals into natural language summaries.

Successful zero-shot fault diagnosis on multiphase flow data.

Framework supports human-in-the-loop for continuous improvement.

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.