According to the characteristics that the torque of each wheel of the in-wheel motor driven vehicle is independent and controllable, the stability control of in-wheel motor driven vehicle based on extension pattern recognition method is proposed in this paper. The dynamic model of the vehicle is established by Matlab/Simulink and Carsim. Taking two-degree-of-freedom (2-DOF) vehicle model as reference model, the vehicle yaw rate and the sideslip angle as the control objectives. The differences between the actual values and the reference values of the yaw rate and the actual sideslip angle are used to define the vehicle stability status. The vehicle stability status is divided into four stability control patterns, which are the no control pattern, the yaw rate control pattern, the yaw rate and sideslip angle joint control pattern, and the sideslip angle control pattern, respectively. The extension pattern recognition algorithm is used to determine the vehicle control pattern. The fuzzy controllers of yaw rate and sideslip angle are designed to obtain the additional yaw moment. Besides, the optimal torque distribution method is proposed by taking the lowest total energy loss of four motors as the objective function. The feasibility and effectiveness of the proposed control strategy are verified by Matlab/Simulink and Carsim joint simulation platform and hardware-in-the-loop (HIL) test.

针对轮毂电机驱动车辆各轮扭矩独立可控的特点，提出基于可拓模式识别方法的轮毂电机驱动车辆稳定性控制。利用Matlab/Simulink和Carsim建立了车辆的动力学模型。以二自由度（2-DOF）车辆模型为参考模型，以车辆横摆角速度和侧滑角为控制目标。横摆角速度和实际侧偏角的实际值与参考值之间的差值用于定义车辆的稳定性状态。将车辆稳定性状态分为四种稳定性控制模式，分别为无控制模式、横摆角速度控制模式、横摆角速度与侧滑角联合控制模式、侧滑角控制模式。扩展模式识别算法用于确定车辆控制模式。设计横摆角速度和侧滑角的模糊控制器以获得附加横摆力矩。此外，以四台电机总能量损耗最低为目标函数，提出了最优转矩分配方法。通过Matlab/Simulink和Carsim联合仿真平台和硬件在环(HIL)测试验证了所提控制策略的可行性和有效性。