A Driver Advisory System Based on Large Language Model for High-speed Train

TL;DR

This paper presents IDAS-LLM, an intelligent driver advisory system for high-speed trains that leverages domain-specific fine-tuning and retrieval-augmented generation to improve fault handling accuracy and explainability, demonstrating promising practical results.

Contribution

The paper introduces a novel LLM-based driver advisory system with railway domain fine-tuning and RAG architecture, enhancing fault response accuracy and explainability in high-speed train operations.

Findings

Domain fine-tuning improves answer accuracy by 10%.

RAG architecture increases question-answer recall by 4%.

System demonstrates practical fault handling in simulations.

Abstract

With the rapid development of China high-speed railway, drivers face increasingly significant technical challenges during operations, such as fault handling. Currently, drivers depend on the onboard mechanic when facing technical issues, for instance, traction loss or sensor faults. This dependency can hinder effective operation, even lead to accidents, while waiting for faults to be addressed. To enhance the accuracy and explainability of actions during fault handling, an Intelligent Driver Advisory System (IDAS) framework based on a large language model (LLM) named IDAS-LLM, is introduced. Initially, domain-fine-tuning of the LLM is performed using a constructed railway knowledge question-and-answer dataset to improve answer accuracy in railway-related questions. Subsequently, integration of the Retrieval-augmented Generation (RAG) architecture is pursued for system design to enhance the explainability of generated responses. Comparative experiments are conducted using the constructed railway driving knowledge assessment dataset. Results indicate that domain-fine-tuned LLMs show an improvement in answer accuracy by an average of 10%, outperforming some current mainstream LLMs. Additionally, the inclusion of the RAG framework increases the average recall rate of question-and-answer sessions by about 4%. Finally, the fault handling capability of IDAS-LLM is demonstrated through simulations of real operational scenarios, proving that the proposed framework has practical application prospects.