Intelligent SOX Estimation for Automotive Battery Management Systems: State-of-the-Art Deep Learning Approaches, Open Issues, and Future Research Opportunities

Real-time battery SOX estimation including the state of charge (SOC), energy (SOE), and health (SOH) is crucial evaluation indicator to assess performance automotive management systems (BMSs). Recently, intelligent models in terms deep learning (DL) have received massive attention electric vehicle (EV) BMS applications due their improved generalization strong computation capability work under different conditions. However, accurate robust SOC, SOH, SOE real-time challenging since they are internal parameters depend on battery’s materials, chemical reactions, aging as well environmental temperature settings. Therefore, goal this review present a comprehensive explanation various DL approaches for estimation, highlighting features, configurations, datasets, chemistries, targets, results, contributions. Various methods critically discussed, outlining advantages, disadvantages, research gaps. In addition, open challenges, issues, concerns investigated identify existing concerns, limitations, challenges. Finally, future suggestions guidelines delivered toward sustainable operation EV operation.