Electric vehicle battery charging framework using artificial intelligence modeling of a small wind turbine based on experimental characterization

Abstract

The objective of this paper is to develop a generic electric vehicle battery charging framework using wind energy as the direct energy source. A robust model for a small vertical axis wind turbine based on an artificial neural network algorithm is used for predicting its performance over a wide range of operating conditions. The proposed framework can be implemented at any location worldwide where full prediction of the wind signature is perfectly obtained. In this paper, a small vertical axis wind turbine has been experimentally characterized at different operating conditions, where measured data, output power, and torque have been used to build the model. Once the model has been developed, the model is inserted into the MATLAB/Simulink software tool to predict the charging performance of a battery for an electric vehicle. An rpm controller has been used to achieve the maximum generated power from the wind turbine across the day with various wind speeds. Hence, the generated power is fed to the EV battery charger to implement the constant current constant voltage charging protocol. The charging current reached the desired value in a settling time of 4.5 s, whatever the intermittency of the wind energy. The proposed application of wind energy to EV provides sufficient constant power supported by the utility grid. Graphical Abstract: [Figure not available: see fulltext.]