Abstract

An on-line training model for self-turning control is constructed based on the feedback error learning model, and its effectiveness is investigated through controlling an inverted pendulum. In order to deal with the local minimum problem in training neural network with back-propagation algorithm and to enhance controlling precision, neural network's weights are adjusted by optimization algorithm. When compared to other nonlinear modeling techniques for control purposes, it has several specific advantages that make it ideally suited to particular applications. Tow numerical examples are used to demonstrate the performance and properties of the proposed scheme. The simulation results show that the proposed controller with improved neural network is flexible and efficient in the control of discrete nonlinear dynamic system and inverted pendulum system.

Paper Details