论文部分内容阅读
为了实现不同驾驶循环工况的精确车速跟踪,提出了一种电磁直驱驾驶机器人模糊神经网络车速控制方法.通过电磁直线作动器直接驱动油门机械腿、制动机械腿、离合器机械腿和换挡机械手.给出了电磁直驱驾驶机器人控制系统结构和协调运动控制模型.在此基础上,设计了电磁直驱驾驶机器人模糊神经网络车速控制模型,电磁直驱驾驶机器人油门、制动、离合器机械腿和换挡机械手的位移作为网络模型的输入,试验车辆的车速作为网络模型的输出.输入变量的隶属度函数个数都为3,隶属度函数的类型都采用广义钟形函数,网络训练算法选用反向传播算法和最小二乘法相结合的混合学习算法.本文提出的方法与其他控制方法和人类驾驶员的驾驶性能进行了对比分析,试验验证了提出方法的有效性.
In order to achieve accurate vehicle speed tracking under different driving cycle conditions, a method of vehicle speed control based on fuzzy neural network for electromagnetic direct-drive robots is proposed, which directly drives the throttle mechanical leg, the brake mechanical leg, the clutch mechanical leg and the changer This paper presents the control system structure and coordinated motion control model of the electromagnetic direct-drive robots.On the basis of this, the design of the vehicle speed control model of the electromagnetic direct-drive driving robot fuzzy neural network, the control of the electromagnetic direct-drive robots throttle, the brake, the clutch The displacement of mechanical leg and shift manipulator is taken as the input of network model, and the vehicle speed of test vehicle is taken as the output of network model. The number of membership functions of input variables is 3. The types of membership functions adopt generalized bell-shaped function, The algorithm uses a hybrid learning algorithm that combines a backpropagation algorithm with a least squares method.The proposed method is contrasted with other control methods and the driving performance of human pilots, and the validity of the proposed method is verified by experiments.