Radial basis function neural network sliding mode control-based direct yaw moment control for electrically driven vehicles

To improve the lateral stability of distributed electric vehicles, a neural network sliding mode direct yaw moment control (DYC) strategy with hierarchical control was proposed to address the nonlinear dynamic characteristics and poor robustness of the vehicle model under extreme conditions. As well as to control the vehicle to track the expected trajectory, a position-orientation optimal acceleration preview driver model was established based on the optimal acceleration theory of the positional orientation preview. Firstly, a new two-degree-of-freedom (2-DOF) nonlinear control equation of state was derived based on the conventional 2-DOF linear control equation of state. Then, a hierarchical controller was designed in this way, and the radial basis function neural network (RBFNN) sliding mode controller (SMC) was used in the upper layer to calculate the total target additional yaw moment of the vehicle. The lower controller is optimised to minimise tyre adhesion utilisation. It is a torque distribution controller for hub motors that utilises quadratic programming. Finally, simulation tests were performed using CarSim and Simulink. As indicated by the simulation findings, the established controller's better robustness and control accuracy over the SMC and PID controllers improves the vehicle's lateral stability and driving safety.