A robust neural adaptive control scheme

A direct nonlinear adaptive controller, to solve the regulation problem for unknown dynamical systems that are modeled by recurrent neural networks is discussed. The behaviour of the closed loop system is analyzed for the case in which the true system differs from the recurrent neural network due to the presence of a modeling error term. Convergence of the state to zero plus boundedness of all signals in the closed loop is guaranteed provided that a complete matching at zero property is satisfied. However, if the above assumption is no longer valid, the authors´ adaptive regulator can still guarantee uniform boundedness with the addition of appropriately modified update laws. Furthermore, the magnitude of the growth of the modeling error is considered unknown