Battery management systems (BMSs) play a critical role in electric vehicles (EVs), relying heavily on two essential factors: the state of charge (SOC) and state of health (SOH). However, accurately estimating the SOC and SOH in lithium-ion (Li-ion) batteries remains a challenge. To address this, many researchers have turned to machine learning (ML) techniques. This study provides a comprehensive overview of both BMSs and ML, reviewing the latest research on popular ML methods for estimating the SOC and SOH. Additionally, it highlights the challenges involved. Beyond traditional models like equivalent circuit models (ECMs) and electrochemical battery models, this review emphasizes the prevalence of a support vector machine (SVM), fuzzy logic (FL), k-nearest neighbors (KNN) algorithm, genetic algorithm (GA), and transfer learning in SOC and SOH estimation.

Bidirectional converters (BDCs) are important in electric vehicles (EVs). This study investigated different bidirectional power converters and their efficiencies, energy densities, and cost parameters. Control methods such as pulse width modulation (PWM) and hysteresis control are also examined. Comparisons on how well they regulate the output voltage and current in converters are performed. This paper also provides an overview of the types of BDCs used in EVs, including flyback, forward, and push-pull converters. The efficiency, energy density, and cost of each converter are assessed to identify the most appropriate model for EVs. The control methods including the advantages and disadvantages of PWM and hysteresis control and how they influence converter performance are examined. Suggestions for applying bidirectional power converters and control approaches in electric vehicles are also proposed. In summary, the paper consolidates the existing research, findings, and current gaps leading to advancements in the field and provide resources for emerging methodologies and concepts for advanced electric mobility.