Abstract
ABSTRACT The commercialization of lithium-ion batteries (LIBs) is rapidly increasing due to a variety of inherent and extrinsic parameters. The State of Charge (SOC), which denotes the amount of remaining capacity, is one of the most important performance metrics for these batteries. As a result, achieving a reliable and precise SOC estimation is essential for the greatest durability and security of LIBs. Estimating the SOC is important to improve the performance and robust utilization of LIBs. Here, this paper uses artificial neural network-based machine learning and deep learning approaches to estimate the battery state of charge. The battery voltage, current, and temperatures have been precisely integrated as input for the models. The proposed model’s accuracy, reliability, and robustness are evaluated using available datasets. The mean absolute error was found to be in the range of 0.0030 to 0.0035, and root mean square errors 0.0043 to 0.0047 were obtained at 0 and 10°C operating temperatures. The outcomes demonstrate that the models can successfully estimate the SOC under different temperature conditions.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call