Akademik Veri Yönetim Sistemi
8th International Conference on Mathematical Advances and Applications (ICOMAA-2025), İstanbul, Türkiye, 7 - 09 Mayıs 2025, cilt.1, sa.1, ss.1-4, (Tam Metin Bildiri)
Accurate estimation of the state of charge (SoC) is critical for optimizing the performance, safety, and lifespan of lithium-ion batteries, which are widely used in electric vehicles (EVs) and portable electronic devices. The development of reliable models for SoC estimation is essential for enhancing the efficiency of battery management systems. In this study, an artificial neural network (ANN)-based model has been developed using SoC data obtained from analytical methods as labels for estimating the SoC in lithium-ion batteries. The model uses voltage (V) and charge (q) data from battery cells as input, and its accuracy is evaluated using performance metrics such as Mean Absolute Error (MAE) and Mean Squared Error (MSE). The results show that the model provides high accuracy in SoC estimation and offers an effective solution to issues such as charge-discharge imbalances. During the training process, continuous improvement in MSE values has been observed due to adaptive learning mechanisms that enhance the model's accuracy. In the future, the integration of heuristic optimization techniques and further development using diverse datasets under different environmental conditions are planned to improve the model's accuracy.