Regenerative Braking Control Method for Electric Unmanned Vehicles Based on Speed Prediction

In order to improve the energy recovery rate of electric unmanned vehicles during operation, ensure the safety and economy of vehicle operation, a speed prediction based regenerative braking control strategy for electric unmanned vehicles is proposed. The road condition recognition algorithm based on offline training neural network model and the vehicle speed prediction method based on improved Markov chain are adopted to make the predicted values more accurate. Using sliding sampling window method for online pattern recognition of vehicle driving status, and converting predicted speed values into power requirements for vehicle operation, then solving the torque applied to vehicle tires through model predictive controller to determine the optimal solution for braking torque control of electric unmanned vehicles. The experimental results show that the average range of the vehicle has increased by 29.11%, and the energy recovery rate has reached 44.11%. Therefore, this study indicates that electric unmanned vehicles using regenerative braking control strategies can effectively control the energy recovery efficiency during the braking process and expand the range.