Review on Intelligent Approaches for Estimation and Monitoring of the BMS

The global energy sector is undergoing transformation to reduce carbon emissions and combat climate change, driven by the rapid advancement of alternative energy sources and the rapid adoption of lithium-ion (Li-ion) batteries. These batteries are essential across multiple industries necessitating advancement in Battery Management Systems (BMS) to ensure their safe and efficient operation. This article provides a detailed review of recent advancements in BMS. The review encompasses various ML algorithms such as feed forward neural networks (FFNN), radial basis function neural networks (RBFNN), extreme learning machines (ELM), support vector machines (SVM), recurrent neural networks (RNN), and Bayesian networks (BN), among others. The discussion covers underlying principles, advantages, and applicability is discussed, along with comparisons of their performance in SOC and SOH estimation. Furthermore, the paper addresses challenges in data acquisition, model training, and algorithm validation, emphasizing the importance of high-quality datasets and computational efficiency. The review concludes by highlighting future research directions to improve the efficiency and applicability of machine learning-based BMS for electrified vehicle applications.