Paper Title
DEEP NEURAL NETWORK BASED STATE OF CHARGE ESTIMATION ON BATTERY MODEL DATA AND EXPERIMENTAL DATA

Abstract
Abstract - State of charge (SOC) estimation of a battery is an important task for battery management systems. Accurate SOC estimation is required to ensure the battery’s safe and reliable operation and to prevent overcharging or undercharging, which can lead to performance degradation and even battery failure. This paper proposes a novel method for SOC estimation of lithium-ion batteries using Pybamm and a Deep Neural Network on experimental data and battery model dataset. The experimental data is collected from a commercial EV battery pack, and the battery model data is generated using the Pybamm software package. Pybamm is a Python-based battery modelling framework that can be used to simulate the electrochemical dynamics of lithium-ion batteries. The proposed DNN model is evaluated on both the experimental data and the battery model data, and it is shown to achieve significantly high accuracy. The proposed method is a promising new approach for SOC estimation of lithium-ion batteries. Keywords - Artificial Intelligence, Battery Management System, Deep Neural Networks, PyBaMM, State of Charge.