Fuel-cell vehicles, plug-in hybrid electric vehicles (PHEVs), hybrid electric vehicles (HEVs), are becoming increasingly popular among automotive manufacturers as a direct result of the growing demand for environmentally friendly and fuel-efficient vehicles. Due to their high energy and power capabilities, for electric vehicles (EVs), lithium-ion batteries (LIB) are a crucial component. Numerous approaches of figuring out a battery's state of health, sometimes referred to as its SoH, have been developed since it is necessary to keep track of the real performance of the batteries even while they are being used. In this paper, Feed-forward Neural Networks (FNN) and Convolutional Neural Networks (CNN) models are developed to evaluate SoH and capacity estimation of Lithium ion battery. Comparatively CNN better performed and the highest accuracy of CNN model towards SoH estimation and Capacity estimation is 98.46% and 97.86% respectively. The highest accuracy of FNN model towards SoH evaluation and Capacity estimation is 97.44% and 96.32% respectively.
Evaluation of Lithium Ion Battery State of Health Using Deep Leaning Methods
2024-07-31
4428195 byte
Conference paper
Electronic Resource
English