Skip to Main Content
An electronic throttle is a dc-motor-driven valve that regulates air inflow into the combustion system of the engine. An effective controller for electronic throttle is not easy to accomplish since the plant is burdened with strong nonlinear effects of stick-slip friction, spring, and gear backlash. In this brief, an adaptive inverse model control system (AIMCS) is designed for the plant, and two radial basis function (RBF) neural networks are utilized in the AIMCS. The plant is identified by a RBF networks identifier, which provides the sensitivity information of the plant to the control input. And another RBF networks is utilized as inverse model controller established by inverse system method. The RBF networks are offline learned firstly and are online trained using back propagation algorithms. To guarantee convergence and for faster learning, adaptive learning rates are developed. Simulation and experiment results show the effectiveness of the AIMCS.