An Optimization-Based Neural Network for Estimating Regenerative Braking Force in EVs for Maximal Energy Recovery

Electric vehicles (EVs) are a viable answer to energy and environmental challenges, but their limited endurance severely restricts their marketing and deployment. Regenerative braking is an important method for extending the battery durability of EVs by lowering idle charge time. In regenerative braking, the kinetic energy created during braking is converted into electrical energy and returned to the storage device as charging power. This study offers a method for calculating regenerative braking force (RBF) using a special optimized artificial neural network (ANN) model RBF. The vehicle controller is then optimized via the Improved Wild Horse Optimization Algorithm (IWHO), allowing for maximum energy collection in Electric automobiles without requiring any architectural changes. MATLAB is used to validate the suggested method for the predefined driving schedule Urban Dynamometer Driving Schedule (UDDS). The performance of the ANN is evaluated using the error functions mean absolute error (MAE), mean squared error (MSE), and root mean squared error (RMSE). The suggested methodology’s simulation results are compared to the ANN with traditional algorithms such as Grey Wolf Optimization Algorithm (GWO), Seagull Optimization Algorithm (SOA), FireFly Optimization Algorithm (FF), and Wild Horse Optimization Algorithm (WHO).