For electrified transportation and energy storage systems, battery states are jointly affected by vehicle types, operating conditions, temperature, power demand, user behavior, and aging differences. In real-world operation, the internal health state of batteries is difficult to directly observe, safety risks are often detected only after obvious degradation has occurred, and lifetime prediction can be easily affected by variations across vehicle types, operating conditions, and battery chemistries. Meanwhile, quantitative support is still insufficient for operation and maintenance, warranty assessment, repair, and second-life utilization, leading to inadequate evidence for engineering decision-making. Therefore, it is necessary to develop an intelligent battery health management system for real-world operating scenarios to support safe operation, lifetime management, risk early warning, and asset decision-making.<\/p>\n\n\n\n
1. Real-world operation data modeling:<\/strong> Construct features related to vehicle operation, battery states, environmental conditions, and user behavior.<\/p>\n\n\n\n 2. Battery health state assessment:<\/strong> Enable health assessment across different vehicles, operating conditions, and battery chemistries.<\/p>\n\n\n\n 3. Remaining useful life prediction:<\/strong> Improve the generalization capability of lifetime prediction using large-scale unlabeled real-world operation data.<\/p>\n\n\n\n 4. Safety risk early warning:<\/strong> Combine mechanistic understanding with artificial intelligence algorithms to enable early detection of potential risks.<\/p>\n\n\n\n 5. Hardware deployment and testing:<\/strong> Conduct engineering validation for battery packs, battery management systems, vehicle applications, and energy storage systems.<\/p>\n\n\n\n 1. Generalizable:<\/strong> Adaptable to different vehicle types, operating conditions, and battery chemistries.<\/p>\n\n\n\n 2. Interpretable:<\/strong> Able to identify key factors affecting degradation and safety risks.<\/p>\n\n\n\n 3. Deployable:<\/strong> Support practical hardware deployment and real-world applications.<\/p>\n\n\n\n Jing H, Ou S*<\/strong>, Lv Z, et al. Battery Safety: Mechanisms, Monitoring, and Machine Intelligence[J]. Advanced Energy Materials<\/em><\/strong>, 2026<\/strong>. JCR, Q1<\/strong>, IF 24.4.<\/strong><\/p>\n\n\n\n Jing H, Hu J, Ou S*<\/strong>, Lv Z, et al. Scalable and generalizable deep learning for battery state of health estimation in on-road electric vehicles[J]. Journal of Energy Chemistry, <\/em><\/strong>2025. JCR, Q1, IF 14.9.<\/strong><\/p>\n\n\n\n Lv Z, Ou S<\/strong>*<\/strong>, Jing H, et al. Self-supervised learning for electric vehicle battery remaining useful life prediction using real-world unlabeled data[J]. Energy, <\/em><\/strong>2026. <\/strong>JCR, Q1,<\/strong> IF 9.0<\/strong><\/p>\n\n\n\nOverall Objectives<\/h4>\n\n\n\n
Research Achievements<\/h4>\n\n\n\n