Large Models for Machine Monitoring and Fault Diagnostics: Opportunities, Challenges and Future Direction
As a critical technology for industrial system reliability and safety, machine monitoring and fault diagnostics has advanced transformatively with Large Language Models (LLMs). This paper reviews LLM based monitoring and diagnostics methodologies, categorizing them into in-context learning, fine tuning, retrieval augmented generation, multimodal learning, and time series approaches, analyzing advances in diagnostics and decision support. It identifies bottlenecks like limited industrial data and edge deployment issues, proposing a three stage roadmap to highlight LLMs’ potential in shaping adaptive, interpretable PHM frameworks.
Authors
- Yaguo Lei (ORCID: https://orcid.org/0000-0002-5167-1459)
- Shilong Ye
- Yan‐Fu Li (ORCID: https://orcid.org/0000-0001-5755-7115)
- Fan Lü (ORCID: https://orcid.org/0000-0002-8496-3941)
- Zisheng Wang (ORCID: https://orcid.org/0000-0003-1722-2454)
- Simon Parkinson (ORCID: https://orcid.org/0000-0002-4753-5198)
- Zhibin Zhao (ORCID: https://orcid.org/0000-0003-4180-7137)
- Jinxin Liu (ORCID: https://orcid.org/0009-0000-4412-1603)
- Xiang Li (ORCID: https://orcid.org/0000-0003-0569-2176)
- Huan Wang (ORCID: https://orcid.org/0000-0003-3219-7226)
- Xuefeng Chen (ORCID: https://orcid.org/0000-0002-0130-3172)
- Bin Yang (ORCID: https://orcid.org/0000-0001-6180-7412)
Institutions
- University of Huddersfield (GB)
- Xi'an Jiaotong University (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Journal of Dynamics Monitoring and Diagnostics
- Published
- 2025-06-21
- DOI
- https://doi.org/10.37965/jdmd.2025.832
- Citations
- 11
- Primary Topic
- Fault Detection and Control Systems
- Type
- article
- Field-Weighted Citation Impact
- 13.36