In the context of the rapid growth of the electric and hybrid vehicle fleet, ensuring the reliability, safety, and durability of traction lithium-ion battery packs has become a key scientific and engineering challenge. The technical condition of battery packs, characterized by such parameters as state of charge (SOC), state of health (SOH), and remaining useful life (RUL), directly affects vehicle performance and the total cost of ownership of electric vehicles. This review article systematizes and analyzes current approaches to assessing the technical condition of battery packs. Fundamental degradation mechanisms and factors are considered, including operational, thermal, and mechanical effects. A detailed analysis is presented for the three main classes of diagnostic methods: model-based approaches, data-driven approaches (machine learning and deep learning), and hybrid methods combining the advantages of the former two. Particular attention is paid to methods for early fault detection, thermal runaway prediction, and condition assessment based on real-world operational data. The article presents quantitative results demonstrating the accuracy and effectiveness of various algorithms and also discusses key challenges and promising research directions, such as the use of cloud platforms, digital twins, and explainable artificial intelligence methods.
Katsuba et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: