Open Access

ARTICLE

Multi-Agent Large Language Model-Based Decision Tree Analysis for Explainable Electric Vehicle Drive Motor Fault Diagnosis

Jaeseung Lee¹, Jehyeok Rew^2,*

1 School of Electrical Engineering, Korea University, Seoul, Republic of Korea
2 Department of Data Science, Duksung Women’s University, Seoul, Republic of Korea

* Corresponding Author: Jehyeok Rew. Email:

Computers, Materials & Continua 2026, 87(3), 100 https://doi.org/10.32604/cmc.2026.077691

Received 15 December 2025; Accepted 12 March 2026; Issue published 09 April 2026

Abstract

The accelerating transition toward electrified mobility has positioned electric vehicles (EVs) as a primary technology in modern transportation systems. In this context, ensuring the reliability of EV drive motors (EVDMs) becomes increasingly critical, given their central role in propulsion performance and operational safety. Accurate and interpretable fault diagnosis of EVDMs is therefore essential for enabling effective maintenance and supporting the broader sustainability and resilience of EVs. This study presents a novel framework that combines decision tree-based fault classification with a multi-agent large language model (LLM) interpretation architecture to deliver transparent and human-readable diagnostic explanations. The proposed framework integrates domain-specific decision rules derived from sensor measurements and utilizes specialized LLM agents to translate tree-based decision logic into coherent narratives. The multi-agent architecture decomposes complex diagnostic reasoning into modular subtasks, allowing for enhanced interpretability and facilitating practical understanding for vehicle engineers. Experimental results on a publicly available EVDM dataset demonstrate that the proposed framework maintains high classification accuracy while significantly improving explanation quality and trustworthiness relative to conventional rule-based and single-agent approaches. By coupling symbolic decision models with LLM-driven reasoning, this work contributes to the advancement of trustworthy artificial intelligence for energy and mobility systems, particularly in predictive maintenance and explainable fault diagnosis. The findings highlight the value of integrating classical machine learning with multi-agent LLMs to support reliable, transparent, and human-centered EV infrastructures.

---

Keywords

---