PROJECT TITLE :

Capacity Fade Estimation in Electric Vehicle Li-Ion Batteries Using Artificial Neural Networks

ABSTRACT:

In this paper, a synthetic neural network (ANN) primarily based approach is proposed to estimate the capacity fade in lithium-ion (Li-ion) batteries for electric vehicles (EVs). Besides its robustness, stability, and high accuracy, the proposed technique can considerably improve the state-of-charge (SOC) estimation accuracy over the lifespan of the battery, which leads to a lot of reliable battery operation and prolonged lifetime. Also, the proposed technique permits correct prediction of the battery remaining service time. 2 identical 3.half dozen-V/16.five-Ah Li-ion battery cells were repeatedly cycled with constant current and dynamic stress take a look at current profiles at area temperature, and their discharge capacities were recorded. The proposed technique shows that very accurate SOC estimation results can be obtained provided enough coaching data are used to train the ANN models. Model derivation and experimental verification are presented during this paper.