The engine serves as the primary component that generates power and drives vehicle movement. Given its critical role, accurately diagnosing engine faults is essential for ensuring vehicle safety and reliability. Recent advances in machine learning (ML) have enabled the development of artificial intelligence (AI)-based diagnostic models with strong predictive performance. However, the lack of transparency in these models constrains user confidence in their diagnostic outcomes. While explainable AI (XAI) methods such as local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP) have been introduced to improve interpretability, their reliance on visual outputs requires manual interpretation, which can be inefficient and prone to subjectivity. To address this limitation, we propose DRIVE, a novel method for explainable vehicle engine fault diagnosis. In DRIVE, LIME and SHAP are applied to an ML-based diagnostic model, and their visual outputs are translated into textual explanations using the vision-language models (VLMs). These complementary explanations are then synthesized by a large language model (LLM) into a unified diagnostic report, providing a coherent narrative of the model’s reasoning and emphasizing abnormal input features. Experiments conducted on a publicly available vehicle engine fault dataset demonstrate that DRIVE not only produces accurate and transparent diagnostic rationales but also generates structured reports that enhance usability for domain experts. By integrating multiple XAI methods with multimodal LLMs, DRIVE advances the transparency, trustworthiness, and practicality of AI-driven vehicle engine fault diagnosis.

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.