2026-09-15T04:53:24Zhttps://gredos.usal.es/oai/request

oai:gredos.usal.es:10366/1351462025-05-29T07:28:12Zcom_10366_122575com_10366_4512com_10366_3823col_10366_134811

Fernández Serantes, Luis A. Estrada Vázquez, Raúl Casteleiro Roca, José L. Calvo Rolle, José L. Corchado Rodríguez, Emilio Santiago 2017-09-06T09:17:00Z 2017-09-06T09:17:00Z 2014-06 Hybrid Artificial Intelligence Systems Lecture Notes in Computer Science. pp. 561-572. 978-3-319-07616-4 (Print) / 978-3-319-07617-1 (Online) 0302-9743 (Print) / 1611-3349 (Online) http://hdl.handle.net/10366/135146 Nowadays, batteries have two main purposes: to enable mobility and to buffer intermitent power generation facilities. Due to their electromechaminal nature, several tests are made to check battery performance, and it is very helpful to know a priori how it works in each case. Batteries, in general terms, have a complex behavior. This study describes a hybrid intelligent model aimed to predict the State Of Charge of a LFP (Lithium Iron Phosphate - LiFePO4) power cell type, deploying the results of a Capacity Confirmation Test of a battery. A large set of operating points is obtained from a real system to create the dataset for the operation range of the power cell. Clusters of the different behavior zones have been obtained to achieve the final solution. Several simple regression methods have been carried out for each cluster. Polynomial Regression, Artificial Neural Networks and Ensemble Regression were the combined techniques to develop the hybrid intelligent model proposed. The novel model allows achieving good results in all the operating range. en https://creativecommons.org/licenses/by-nc-nd/3.0/ info:eu-repo/semantics/openAccess Attribution-NonCommercial-NoDerivs 3.0 Unported Computer Science Hybrid Intelligent Model to Predict the SOC of a LFP Power Cell Type info:eu-repo/semantics/conferenceObject