Real-time Adaptive Control of Electric Vehicle Drives using Artificial Neural Networks

Abstract

This study examines the use of artificial neural networks (ANNs) in real-time adaptive control for electric vehicle (EV) propulsion systems, with the goal of enhancing performance and efficiency. The neural network-based control system is developed and validated using experimental data that includes vehicle speed, battery temperature, battery voltage, and motor temperature. The neural network demonstrates precise control output predictions by effectively adapting to dynamic changes in input parameters, exhibiting a remarkable level of responsiveness to diverse operating settings. The analysis of the experimental findings reveals a strong correlation between the expected and actual control values, confirming the system's dependability and effectiveness in managing torque and voltage instructions for the electric vehicle (EV). The performance indicators, such as mean squared error (MSE), R-squared, mean absolute error (MAE), and root mean squared error (RMSE), demonstrate a small difference between the anticipated and actual values, indicating that the system has a high level of accuracy and predictive capacity. Furthermore, the system displays remarkable responsiveness to changes in velocity, battery temperature, and voltage, showcasing its capacity to adjust to different driving situations while still staying within acceptable levels of fluctuation. This research highlights the capacity of artificial neural networks (ANNs) to facilitate accurate and flexible control systems for electric vehicles (EVs), representing a substantial advancement in improving the performance, efficiency, and adaptability of electric vehicle propulsion in sustainable transportation systems. The neural network-based control system has been proven to be accurate, responsive, and reliable. This highlights its potential to revolutionize future electric vehicle (EV) technologies and contribute to advancements in real-time adaptive control strategies for environmentally friendly transportation systems.