Haixu Yang, Fengwei Liang, Kerui Li, Jichao Hong, Jinghan Zhang, Xiaohui Chen, State of health estimation and remaining useful life prediction of Li-ion battery oriented to real-world electric vehicles: A comprehensive evaluation methodology, Engineering Applications of Artificial Intelligence, Volume 181, Part 1, 2026, 10.1016/j.engappai.2026.115311.
State of health estimation is essential to ensure the battery’s reliability, safety and economy. It is an integral part of the battery management system. Estimation often faces the problems of a lone indicator and ineffective real-vehicle application. The use of a lone indicator leads to biased and inaccurate state estimation. The complexity of real-world driving scenarios renders the method impractical and inaccurate. Here, we propose a comprehensive evaluation method oriented to real-world electric vehicles. Capacity, ohmic internal resistance, cell voltage inconsistency, and battery pack temperature inconsistency are considered as four indicators of battery degradation. For each indicator, a state of health estimation value can be obtained. A fuzzy matrix is used to fuse the four indicators for a comprehensive evaluation. Also, the fuzzy matrix gives the weights of different health indicators as 0.1988, 0.2463, 0.3183, and 0.2366. The inconsistency of cell voltages carries the highest weighting among these indicators, exerting a more significant influence than the other three. In terms of artificial intelligence, this paper proposes a complete set of data processing, feature computation, and fusion estimation methods for battery health state. In engineering applications, the metrics for health state assessment are greatly enriched and the degree of accuracy is significantly improved. The method breaks through the limitations of the traditional evaluation based on a singular indicator, achieving a multi-dimensional comprehensive and objective evaluation of automotive batteries.