Regenerative Braking Control Strategy Based on Multi-source Information Fusion under Environment Perception

In this paper, regenerative braking control of electric vehicles is investigated based on multi-source information such as image recognition, GPS and vehicle running parameters. Firstly, the fast normalized cross-correlation (FNCC) algorithm is applied to identify the speed limit traffic signs. Then the vehicle speed is intelligently controlled under the fusion of the detected traffic signs and road slope prediction information. Secondly, an adaptive regenerative braking energy recovery strategy based on multi-source information fusion is designed. The adaptive control strategy can automatically adjust under different braking conditions, so the motor can work at the high-efficiency points. The adaptive control strategy provides the possibility to realize the efficient recovery of braking energy. Finally, the effectiveness of the strategy is verified by MATLAB/Simulink and Prescan co-simulation. Specially, a regenerative braking proportional coefficient K under the multi-source information fusion is proposed. The K can optimize the braking torque distribution and improve the motor high-efficiency operating range. Compared with the traditional series control strategy and fuzzy control strategy, the adaptive control strategy improves the energy recovery rate by 11.9% and 5.3% respectively.