Dynamic Structure Neural Network for Stable Adaptive Control of Nonlinear Systems

摘要

In this paper an adaptive control strategy based on neural network for a class of nonlinear system is analyzed. A simplified algorithm is presented with the technique in generalized predictive control theory and the gradient descent rule to accelerate learning and improve convergence. Taking the neural network as a model of the system, control signals are directly obtained by minimizing the cumulative differences between a setpoint and output of the model. The applicability in nonlinear system is demonstrated by simulation experiments.