Summary of Integrating Llms For Explainable Fault Diagnosis in Complex Systems, by Akshay J. Dave et al.
Integrating LLMs for Explainable Fault Diagnosis in Complex Systems
by Akshay J. Dave, Tat Nghia Nguyen, Richard B. Vilim
First submitted to arxiv on: 8 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG); Systems and Control (eess.SY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes an innovative system that combines physics-based diagnostic tools with Large Language Models (LLMs) to enhance explainability in complex systems, such as nuclear power plants. The integrated system identifies faults while providing clear explanations of their causes and implications. By applying this approach to a molten salt facility, the study demonstrates its ability to connect diagnosed faults to sensor data, answer operator queries, and evaluate historical sensor anomalies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make complex systems like nuclear power plants easier to understand by combining two tools: one that finds problems and another that explains why they happened. The system uses both physics-based ideas and Large Language Models (LLMs) to identify faults and tell operators what caused them. It works well on a real-world example, showing how it can connect problems to sensor data, answer questions, and look at past issues. |
