State of Charge Estimation of Batteries Using a Neural Network Based on Impedance Spectroscopy
A comparison of the results of battery state of charge estimation using neural networks with different characteristics applied to the results of battery impedance spectroscopy has been performed. The neural networks differed both in dimensions (number of neurons, number of layers, and number of epochs) and in the training optimization algorithm (Levenberg-Marquardt, Bayesian Regularization, BFGS Quasi-Newton, and Conjugate Gradient).
Authors
- Riccardo Caponetto (ORCID: https://orcid.org/0000-0002-9574-7187)
- Stevan M. Cvetićanin (ORCID: https://orcid.org/0000-0002-5789-3984)
- Francesca Sapuppo (ORCID: https://orcid.org/0000-0001-8772-2759)
Institutions
- University of Messina (IT)
- University of Novi Sad (RS)
Publication Details
- Published
- 2024-11-06
- DOI
- https://doi.org/10.1109/indel62640.2024.10772681
- Primary Topic
- Advanced Battery Technologies Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00