Machine Learning Model for the Prediction of an E-Vehicle's Battery Life Cycle

Abstract

A useful substitute for a traditional car is an electric vehicle. Rechargeable batteries, which are much more efficient than traditional fuels like gasoline and diesel, are used to power the majority of these vehicles. The benefits of batteries can occasionally be outweighed by other reasons. It also takes into account the battery's rapid depreciation. The purpose of this study is to offer a resolution to the aforementioned problem. Three machine learning (ML) models were created and examined for this goal. A dataset with diverse battery-related data has been assembled from the MIT dataset. About 124 Li-ion batteries are included in this collection. Because most of the columns in this dataset are useless, the necessary parameters were extracted from it. Three ML models were also developed. Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting Decision Tree (GBRT) are three separate methods that were used to generate the models. The dataset's acquired features were then used to train the models. The effectiveness of the models was then evaluated to identify the best method that can be applied to the prediction of the battery cycle by looking at the accuracy and loss values of all three algorithms. After accuracy and error analyses, it is concluded that the SVM method is the best. The highest accuracy, 97.3, was generated by the SVM algorithm. It was also more effective because it had the smallest MAE value.