cs.LGNov 10, 2026

Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning

Authors: Wenqi Zhou, Leonardo Baldo, Kai Goebel, Manuel Arias Chao

Organizations: Institute for Data Science, Zurich University of Applied Science, Winterthur, 8401, Switzerland · Fragum Global, Mountain View, CA 94040, USA · Luleå University of Technology, Luleå, 971 87, Sweden · Faculty of Aerospace Engineering, Delft University of Technology, HS 2926 Delft, The Netherlands

Abstract

Fault diagnosis in complex systems requires linking observed changes in physical quantities to the failure mechanisms that produce them. Experienced engineers perform this task by combining sensor information with knowledge of system behavior and fault propagation. Large Language Models (LLMs) can support this process, but their diagnostic reasoning depends on the availability of asset-specific engineering knowledge and on how this knowledge is represented and used during inference. This work introduces Chain of Physics (CoP), an LLM-based fault-diagnosis framework built around a Constrained Knowledge Graph (CKG) generated automatically from asset-specific reference documentation. CoP addresses failure-sensor association from textual engineering knowledge. The CKG stores diagnostic chains connecting failure modes, changes in physical quantities, and monitoring sensors. During inference, semantically similar graph paths are retrieved for each question and used as both information and in-context examples for the reasoning process. Candidate failure modes are extracted from the question and analysed independently through dedicated LLM calls, which generate plausible failure-to-observation chains. A final decision module compares these chains with the available answer choices. CoP is evaluated on the FailureSensorIQ benchmark across four industrial asset classes and three LLMs. Compared with direct prompting and conventional Retrieval-Augmented Generation (RAG), CoP improves diagnostic accuracy across all evaluated models, with gains ranging from 7.8 to 19.6 percentage points and from 11.7 to 18.2 percentage points, respectively. The results show that structured engineering knowledge can improve LLM-based diagnostic reasoning when graph retrieval is combined with in-context examples of fault propagation.

Figures & tables

Explore similar work

CardsList
  1. FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes

    Jun 3, 2025Christodoulos Constantinides, Dhaval Patel, Shuxin Lin +3Question AnsweringLLM Reliability

  2. Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance

    Oct 13, 2026Lucas H. McCabe, Sarah Lukens, H. Howie HuangLLM AgentsFault Diagnosis