Experimental Study on Lithium-Ion Batteries Remaining Useful Life Prediction by Developing a Feedforward and a Long-Short-Time-Memory (LSTM) Neural Network for Electric Vehicles Application

This paper proposes a model to predict Lithium-ion battery life for electric cars based on supervised machinelearning linear regression algorithm. The capacity prediction of batteries is voltage-dependent per-cell modeling. When sufficient test data available, learning algorithm will train this give promising result. paper's results are the voltage value measure battery's voltage. Thus, remaining predicted. Expected proven by an experiment table system with NVIDIA Jetson Nano 4GB Developer Kit B01, battery, and sensor. result allows rapid identification manufacturing processes enable users decide replace defective when deterioration in performance lifespan identified.