A Neural Network Application for a Lithium-ion Battery Pack State-of-Charge Estimator with Enhanced Accuracy

Gabriel C. S. Almeida; A. C. Zambroni de Souza; Paulo F. Ribeiro

Previous Article in event

Optimal Integration of Renewable Sources and Latent Heat Storages for Nearly Zero-Energy Buildings

Previous Article in session

Energy Storage for Peak Shaving in a Microgrid in the Context of Brazilian Time-of-Use Rate

Next Article in event

Conversion of Solid Biomass into Biochar: Act as a Green, Eco-Friendly Energy Source and a Substitute of Fossils Fuel Inputs

Next Article in session

Prediction of Cooling Energy Consumption Using Neural Network on the Example of the Hotel Building

A Neural Network Application for a Lithium-ion Battery Pack State-of-Charge Estimator with Enhanced Accuracy

Gabriel C. S. Almeida

^*,

A. C. Zambroni de Souza

Paulo F. Ribeiro

¹ Institute of Electrical Systems and Energy, Federal University of Itajubá, 37500-903Itajubá, Brazil

Published: 11 September 2020 by MDPI in The First World Energies Forum session Intermediate and Final Energy Use

https://doi.org/10.3390/WEF-06915 (registering DOI)

Abstract:

The State-of-Charge (SOC) real-time estimation plays an essential role in effective energy management. This paper proposes the use of an Artificial Neural Network (ANN) to design a state of charge estimator for a Graphite/LiCoO2 lithium-ion battery pack. The software MATLAB was used to develop and test several network configurations to find the ideal weights to perform the ANN. Results demonstrate that the Mean Squared Error (MSE) achieved rendered the ANN as an effective technique. Thus, it predicted the battery bank’s SOC values with accuracy using only voltage, current, and charge/discharge time as input.