Intelligent vehicle stability integrated control based on adaptive algorithm

In addressing the issue of driving stability control for electric vehicles equipped with distributed four-wheel hub motor drives, this study first introduces a method for determining the stability region of vehicles in phase space, utilizing a Radial Basis Function (RBF) neural network algorithm. Building upon this foundation, an adaptive control weight calculation method for the coordination of Active front steering and the Direct Yaw Control system is proposed, grounded in the theory of extension. To tackle the challenges of vehicle stability in complex environments, a three-tier control system is proposed. The upper tier employs Adaptive Gain PID algorithm to design a vehicle speed tracking controller, while Adaptive Non-singular Integral Terminal Sliding Mode theory is utilized to develop a direct yaw moment controller, alongside Adaptive Robust Integral Sliding Mode theory for the active front steering controller. The middle tier incorporates a cost function for tire slip energy loss into an additional yaw moment optimization distribution function, employing a quadratic programing algorithm to derive the optimal tire driving force. Additionally, a PID algorithm is used to design a tire force closed-loop controller, facilitating the transmission of the ideal driving moment and the desired additional steering angle to the execution layer. Finally, the effectiveness of the proposed algorithm is verified by simulation and hardware-in-the-loop test. The simulation and test results based on the proposed algorithm are compared with other algorithms, and the results show that the proposed algorithm has better performance.