Hyperparameter-Optimized Neural Network for Precise Battery State of Charge Estimation

Accurate estimation of the state of charge (SOC) of battery cells is crucial for the efficient management and longevity of battery systems, particularly in electric vehicles and renewable energy storage. This paper presents an approach utilizing a Feedforward Neural Network (FNN) to estimate the SOC of battery cells. The proposed method leverages hyperparameter optimization to determine the optimal configuration of the neural network, including the number of neurons, the number of hidden layers, the best activation function, and the most effective learning rate. The primary objective of this research is to minimize the estimation error of the SOC to within 2%, thereby enhancing the reliability and performance of battery management systems. The hyperparameter optimization process involves a systematic search and evaluation of various configurations to identify the most effective neural network architecture. This process is critical as it directly impacts the accuracy and efficiency of the SOC estimation. The methodology includes the collection of extensive battery cell data under various operating conditions to train and validate the neural network model. The data encompasses a wide range of SOC levels, temperatures, and load conditions to ensure the robustness of the model. The FNN is trained using this dataset, and the performance is evaluated based on the mean absolute error (MAE) and root mean square error (RMSE) metrics. Initial results demonstrate that the optimized FNN model achieves an estimation error well within the targeted 2% threshold. The findings indicate that the choice of hyperparameters significantly influences the model’s performance, with certain configurations yielding superior accuracy and stability. The paper also discusses the implications of these findings for the design and implementation of advanced battery management systems.