Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review

Traditional onboard vehicle diagnostics are rapidly evolving concomitant to the rise of electrified powertrains, digital transformation, and intelligent technologies for advanced system management. The big data now available in modern vehicles offers unprecedented opportunities for condition monitoring and prognosis, but also presents challenges in scaling and integrating multimodal sensor data across components with varying timescale dynamics. Machine learning techniques have proven particularly effective in implementing diagnostic functions within electrified vehicle powertrains. This study systematically reviews intelligent, data-driven techniques for health monitoring and prognosis of electrified powertrains. We categorize existing research based on diagnostic functions and machine learning methods, with a focus on approaches that do not require prior knowledge of faulty operational states. Our findings indicate that deep learning methods are state-of-the-art across several diagnostic functions, fault modes, system levels, and multimodal sensor integration.