Bayesian Optimization‐Active Disturbance Rejection Lateral Stability Control Method for Distributed‐Drive Electric Vehicles

With the development of new energy vehicle technologies, distributed‐drive electric vehicles (DDEVs) have emerged as a pivotal direction for enhancing vehicle maneuverability and energy efficiency thanks to their distinctive feature of independent motor‐driven four wheels. To address strong nonlinear dynamics, sensor measurement error, and difficult parameter tuning, this paper presented a Bayesian optimization‐active disturbance rejection control (BO‐ADRC) method for lateral stability control of DDEVs. Firstly, to address the insufficient accuracy of traditional linear tire models under large lateral forces, an improved nonlinear brush tire model was proposed based on a third‐order Taylor expansion for a 2‐degree‐of‐freedom (2DOF) nonlinear vehicle dynamics model. Secondly, a sampled‐data output‐feedback controller‐based ADRC algorithm was designed to achieve dynamic compensation of complex disturbances through multimodule collaboration, which includes a tracking differentiator (TD), an extended state observer (ESO), and a nonlinear state error feedback law (NLSEF). Thirdly, a BO for NLSEF parameter tuning was proposed to achieve global adaptive tuning for improving the control effectiveness. Fourthly, a minimum driving force‐based yaw moment allocation strategy was introduced, which allocated target yaw moment to all four wheels while minimizing the total energy consumption of the drive system. Simulations were performed to validate the effectiveness of the proposed method under various scenarios. Finally, real vehicle experiments were conducted on a self‐designed vehicle platform, confirming the engineering practicability and effectiveness of the proposed method.