Experimental Study on Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Three Regression Models for Electric Vehicle Application

This paper presents three regression models that predict the lithium-ion battery life for electric cars based on a supervised machine learning algorithm. The linear regression, bagging regressor, and random forest regressor will be compared capacity prediction of batteries voltage-dependent per-cell modeling. When sufficient test data are available, algorithms train this model to give promising result. effectiveness demonstrated experimentally. experiment table system is built with an NVIDIA Jetson Nano 4 GB Developer Kit B01, battery, Arduino, voltage sensor. has evaluated model’s accuracy average square difference between initial value predicted in set (MSE (mean error)) RMSE (root mean squared error), which smaller than 516.332762; 22.722957). MSE biggest 22060.500669; 148.527777). result allows remain helpful predicting batteries. Moreover, rapid identification manufacturing processes enable users decide replace defective when deterioration performance lifespan identified.