Exploring LLM-based Frameworks for Fault Diagnosis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918149668995072 |
|---|---|
| author | Lee, Xian Yeow Vidyaratne, Lasitha Farahat, Ahmed Gupta, Chetan |
| author_facet | Lee, Xian Yeow Vidyaratne, Lasitha Farahat, Ahmed Gupta, Chetan |
| contents | Large Language Model (LLM)-based systems present new opportunities for autonomous health monitoring in sensor-rich industrial environments. This study explores the potential of LLMs to detect and classify faults directly from sensor data, while producing inherently explainable outputs through natural language reasoning. We systematically evaluate how LLM-system architecture (single-LLM vs. multi-LLM), input representations (raw vs. descriptive statistics), and context window size affect diagnostic performance. Our findings show that LLM systems perform most effectively when provided with summarized statistical inputs, and that systems with multiple LLMs using specialized prompts offer improved sensitivity for fault classification compared to single-LLM systems. While LLMs can produce detailed and human-readable justifications for their decisions, we observe limitations in their ability to adapt over time in continual learning settings, often struggling to calibrate predictions during repeated fault cycles. These insights point to both the promise and the current boundaries of LLM-based systems as transparent, adaptive diagnostic tools in complex environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23113 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring LLM-based Frameworks for Fault Diagnosis Lee, Xian Yeow Vidyaratne, Lasitha Farahat, Ahmed Gupta, Chetan Artificial Intelligence Computers and Society Large Language Model (LLM)-based systems present new opportunities for autonomous health monitoring in sensor-rich industrial environments. This study explores the potential of LLMs to detect and classify faults directly from sensor data, while producing inherently explainable outputs through natural language reasoning. We systematically evaluate how LLM-system architecture (single-LLM vs. multi-LLM), input representations (raw vs. descriptive statistics), and context window size affect diagnostic performance. Our findings show that LLM systems perform most effectively when provided with summarized statistical inputs, and that systems with multiple LLMs using specialized prompts offer improved sensitivity for fault classification compared to single-LLM systems. While LLMs can produce detailed and human-readable justifications for their decisions, we observe limitations in their ability to adapt over time in continual learning settings, often struggling to calibrate predictions during repeated fault cycles. These insights point to both the promise and the current boundaries of LLM-based systems as transparent, adaptive diagnostic tools in complex environments. |
| title | Exploring LLM-based Frameworks for Fault Diagnosis |
| topic | Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2509.23113 |