Sliding Mode Controller for Electronic Throttle Based on RBF Neural Network
In order to solve the model parameter uncertainty and external disturbance of vehicle electronic throttle in complex environment,a sliding mode controller based on RBF neural network was selected according to the nonlin-ear characteristics of electronic throttle.RBF neural network was used to approximate the nonlinear part of the throt-tle,and Lyapunov method was used to design the adaptive law of the system.At the same time,through the design of the expansion state observer,the system can accurately observe the angular velocity change of the valve plate.The simulation results show that the controller can maintain fast response speed and accurate tracking of expected opening for inaccurate throttle model under complex environment.The self-learning ability of neural network improves the ro-bustness of throttle system.
Radial basis function neural networkElectronic throttleSliding mode controlExtended state observer
NETL
NSTL
万方数据
