Predicting battery capacity with artificial neural networks
| dc.contributor.author | Kılıc, Ismaıl | |
| dc.contributor.author | Aydın, Musa | |
| dc.contributor.author | Sahın, Hasan | |
| dc.date.accessioned | 2026-02-08T15:08:31Z | |
| dc.date.available | 2026-02-08T15:08:31Z | |
| dc.date.issued | 2024 | |
| dc.department | Bursa Teknik Üniversitesi | |
| dc.description.abstract | Li-ion batteries are a commonly used type of battery in various electronic devices and electric vehicles. The capacity of these batteries can decrease over time and affect the lifespan of the device. Therefore, predicting the capacity status of Li-ion batteries is important, there are several ways to estimate the SOC of a battery. When the literature was reviewed and relevant articles were examined, it was observed that artificial neural networks could be an effective tool for predicting the capacity status of Li-ion batteries. In this study, a study was conducted to predict the capacity status of Li-ion batteries using artificial neural networks. For this purpose, data collection, data preprocessing, and the use of artificial neural networks were carried out in stages for the prediction of the capacity status of Li-ion batteries. When the results obtained were examined, it was seen that artificial neural networks were able to correctly predict the capacity status of Li-ion batteries. The comparative analysis among various ANN models, including RNN, LTSM, and GRU highlights the superiority of GRU in performance, with RNN exhibiting comparable performance and LSTM lagging. These predictions can be used to extend the lifespan of Li-ion batteries and optimize the performance of the device. In addition, efforts such as expanding the data set and optimizing the network structure can be made to increase the accuracy of these predictions. This research presents an exemplary study of predicting Li-ion battery capacity using ANNs and has been successfully conducted using NASA datasets. | |
| dc.identifier.doi | 10.51513/jitsa.1380584 | |
| dc.identifier.endpage | 112 | |
| dc.identifier.issn | 2636-820X | |
| dc.identifier.issue | 2 | |
| dc.identifier.startpage | 99 | |
| dc.identifier.trdizinid | 1276009 | |
| dc.identifier.uri | https://doi.org/10.51513/jitsa.1380584 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12885/5062 | |
| dc.identifier.volume | 7 | |
| dc.indekslendigikaynak | TR-Dizin | |
| dc.language.iso | en | |
| dc.relation.ispartof | Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi (Online) | |
| dc.relation.publicationcategory | Makale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.snmz | KA_TR-Dizin_20260207 | |
| dc.subject | LSTM | |
| dc.subject | Artificial Neural Network | |
| dc.subject | SOC | |
| dc.subject | RNN | |
| dc.subject | Li-ion Battery | |
| dc.subject | Battery Capacity Prediction | |
| dc.subject | GRU State of Capacity | |
| dc.title | Predicting battery capacity with artificial neural networks | |
| dc.type | Article |
