A Layered EV Braking Stability Control Approach Considering the Driver’s Braking Intention and Vehicle Condition

Focusing on the poor applicability of existing brake stability control methods for intelligent electric vehicles and the problem that the actual braking intention of the driver and the actual running condition of the vehicle are less considered, a layered brake stability control method for electric vehicles is proposed which considers the driver’s braking intention and vehicle state. Firstly, a GRU (Gated Recurrent Unit) neural network with SE (Squeeze Excitation) module mechanism is proposed to obtain the driver’s real braking intention, and a vehicle state recognition algorithm is designed to obtain the real-time longitudinal speed of the vehicle under complex working conditions, which form a closed-loop control structure for the braking system. Secondly, the layered control structure is used to distribute braking force, and the upper control strategy of the braking system with multi-attention mechanism is proposed to obtain the braking torque required for stable braking of the vehicle. Then, the lower level control strategy is used to coordinate the electro-hydraulic braking torque, and the dynamic coordination distribution method of motor braking and hydraulic braking is designed. Finally, the effectiveness and real-time performance of the layered braking stability control method considering driver’s braking intention and vehicle state are verified by joint simulation and real vehicle road experiments. The experiment results show that the slip rate of the proposed braking control method is about 1.5%, the SOC value of the battery increases by 0.14%~0.18%, and the stability coefficient is stable in the range of 0.02~0.04. The braking system control method can not only ensure the braking efficiency and stability of the vehicle, but also effectively recover the braking energy, which provides a new solution for the braking stability control of intelligent vehicles.