Machine Learning based Remaining Useful Life Prediction of Lithium-ion Batteries in Electric Vehicle Battery Management System

The accurate prediction of the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for the effective management and maintenance of electric vehicle (EV) battery systems. RUL prediction involves estimating the number of cycles or time until a battery's capacity degrades to a specified threshold, considering factors such as temperature, charging/discharging profiles, State-of-Charge(Q1), Voltage (C1, C2), and operational conditions. The RUL prediction of lithiumion batteries in EV battery management systems is a challenging task due to the complex interplay of degradation mechanisms and evolving battery technologies. Data-driven approaches, leveraging machine learning algorithms and advanced data analytics techniques, have emerged as the primary method for RUL prediction. However, challenges remain in ensuring the scalability, reliability, and real -time applicability of prediction models. This paper aims to contribute to the field by developing state-of-the-art RUL prediction models that seamlessly integrate into existing EV battery management systems. This article first summarizes and classifies various methods for predicting the remaining service life of lithium-ion batteries that have been proposed in recent years. On this basis, by selecting specific criteria to evaluate and compare the accuracy of different models, find the most suitable method. Finally, summarize the development of various methods. According to the research in this article, the average accuracy of Random Forest regression and classification models is higher than the accuracy of the other methods, and the prediction cycle is shorter than the average of the other methods.