Estimation of the RUL of Alkaline Batteries in EV by using Machine Learning Algorithm

Abstract

The attention on battery longevity and performance has increased due to the quick uptake of electric cars (EVs) as a sustainable substitute for conventional internal combustion engine vehicles. The foundation of EV technology, batteries control the vehicle's dependability, efficiency, and range. With their distinct chemical characteristics, alkaline. Batteries are one of the various battery varieties that may be advantageous for specific EV applications. However, a variety of variables, including charge-discharge cycles, temperature fluctuations, and usage patterns, affect their life cycle and efficiency. To maximize performance, lower maintenance costs, and guarantee user safety, it is crucial to precisely calculate these batteries' Remaining Useful Life (RUL). Conventional approaches to RUL prediction frequently depend on statistical methods or empirical models, which might not take into consideration the intricate relationships between the factors influencing battery deterioration. For a potential solution to this issue machine learning (ML) algorithms, which can examine big datasets and reveal hidden patterns. This study intends to provide a reliable framework for forecasting the RUL of alkaline batteries in EVs by utilizing cutting-edge machine learning models. This will ultimately help to enhance battery management systems and encourage the wider use of EV technology.