Exploring LLM-based Frameworks for Fault Diagnosis
It addresses fault diagnosis for industrial monitoring, but is incremental in exploring LLM architectures and inputs.
This study explored using Large Language Models (LLMs) for fault diagnosis in industrial settings, finding that multi-LLM systems with summarized statistical inputs improved sensitivity for fault classification compared to single-LLM approaches, though they struggled with adaptation in continual learning scenarios.
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.