Approximate Nonlinear Output Regulation based on the Universal Approximation Theorem

摘要

The regulator equations arising from the nonlinear output regulation problem are a set of mixed partial and algebraic equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the regulator equations. This paper introduces an approximation method for solving the regulator equations based on a class of feedforward neural network. The method has led to an effective approach to approximately solving the nonlinear output regulation problem. The resulting design method is applied to the well-known inverted pendulum on a cart system. Simulation shows that our approach is much better than the conventional linear controller based on the linearization.