2026-04-11T01:20:09Zhttps://ebiltegia.mondragon.edu/oai/request

oai:ebiltegia.mondragon.edu:20.500.11984/62382024-04-19T11:07:19Zcom_20.500.11984_473col_20.500.11984_478

Azkue, Markel Miguel, Eduardo Oca, Laura IRAOLA, UNAI 2024-02-02T08:53:17Z 2024-02-02T08:53:17Z 2023 2032-6653 https://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=173318 https://hdl.handle.net/20.500.11984/6238 Creating SoC algorithms for Li-ion batteries based on neural networks requires a large amount of training data, since it is necessary to test the batteries under different conditions so that the algorithm learns the relationship between the different inputs and the output. Obtaining such data through laboratory tests is costly and time consuming; therefore, in this article, a neural network has been trained with data generated synthetically using electrochemical models. These models allow us to obtain relevant data related to different conditions at a minimum cost over a short period of time. By means of the different training rounds carried out using these data, it has been studied how the different hyperparameters affect the behaviour of the algorithm, creating a robust and accurate algorithm. To adapt this approach to new battery references or chemistries, transfer learning techniques can be employed. eng Attribution 4.0 International http://creativecommons.org/licenses/by/4.0/ © 2023 The Authors computer intelligence Li-ion battery estimation algorithm ODS 7 Energía asequible y no contaminante ODS 9 Industria, innovación e infraestructura state of charge synthetic data Creating a Robust SoC Estimation Algorithm Based on LSTM Units and Trained with Synthetic Data http://purl.org/coar/resource_type/c_6501