基于视觉识别的线控制动压力滑模控制

制动安全是车辆主动安全的关键技术之一。制动决策和执行器控制是影响线控制动系统性能的两个主要因素。路面自适应性和控制器鲁棒性分别对制动决策和执行器控制有着重要影响,制约着线控制动系统的发展。本文中以一种液压调控的线控制动系统为基础,针对路面自适应性和控制器鲁棒性问题,提出一种双层结构的制动系统控制器,上层采用计算机视觉的方法对路面类型进行识别,根据识别结果制定当前路面的最佳滑移率;下层针对制动系统参数不确定性问题,引入滑模控制理论对制动过程中的最佳滑移率进行跟踪控制。通过仿真与实验验证,结果表明,双层结构的制动系统控制器相比传统控制器,路面的自适应性好,制动距离更短,控制器鲁棒性好。

Brake by Wire Pressure Sliding Mode Control Based on Visual Recognition

Brake safety is one of the key technologies for vehicle active safety.Braking decision and actua?tor control are two main factors that affect the performance of the brake by wire system.Road surface adaptability and controller robustness have important influence on braking decision and actuator control respectively,restricting the development of brake by wire system.In this paper,based on a hydraulic brake by wire system,a double-layer structure brake system controller is proposed to solve the problems of road surface adaptability and controller robust?ness.The upper layer uses computer vision to identify the type of road surface,and formulates the optimal slip rate of the current road surface according to the recognition result;the lower layer introduces the sliding mode control theory in track and control of the optimal slip rate during the braking process to solve the problem of brake system parameters uncertainty.Through simulation and experimental verification,the results show that the double-layer structure brake system controller has better road surface adaptability,shorter braking distance and better controller robustness than the traditional controller.