Neural network enhanced output regulation in uncertain nonlinear systems

The problem of designing a control law to achieve asymptotic tracking and disturbance rejection in a nonlinear plant where both the reference and disturbance signal are generated by an exosystem is called the nonlinear output regulation problem. It is known that solvability of this problem relies on the existence of a feedforward function defined by a set of mixed nonlinear partial and algebraic equations called regulator equations. Previous approaches to solving the output regulation problem call for the solution of the regulator equations. However, solving the regulator equations is difficult due to the nonlinearity and complexity. The paper proposes an approximation approach to solving the output regulation problem by directly approximating the feedforward function using a class of artificial neural networks. Further, a control configuration is developed that allows the reduction of the tracking error by the online adjustment of the parameters of the neural networks.