Diagnostic and Prognostic Health Management of Electric Vehicle: Bridging the Skills Gap in EV Maintenance with Intuitive 3D Interactive Solutions

Abstract

This paper presents a novel 3D-based interactive diagnosis system for electric vehicles ( EV), aiming bridge the skills gap in their maintenance. Traditional diagnostic tools often rely on extensive documentation and predefined troubleshooting scenarios, which could be inefficient and necessitate expert-level training, these limitations lead to inaccurate diagnostics and increased vehicle downtime. Our proposed system leverages advanced 3D interactive models, supplemented by Artificial Intelligence , to provide intuitive and adaptive maintenance guidance. This approach reduces the dependency on specialist knowledge by simplifying the diagnostic process and providing step-by-step visual assistance for disassembly and reassembly tasks. The system's capacity to learn from historical data and improve over time promises greater accuracy in fault identification and resolution recommendations. We demonstrate the system’s effectiveness through simulated maintenance scenarios, showcasing its capacity to guide even less experienced technicians through complex procedures with increased efficiency and reduced error rates. The system represents a significant step forward in the management of EV health, offering a scalable solution to the automotive industry’s growing demand for accessible and intelligent maintenance tools. Our research suggests that the widespread adoption of such systems could revolutionize EV maintenance, improving service quality and vehicle safety, while transforming the landscape of technician training and expertise.