A Novel Neural Network Adaptive Control For A Uncertain Nonlinear Systems With Prescribed Performance

This paper addresses the problem of adaptive neural networks (NNs) prescribed performance control for a class of unknown nonlinear systems. A neural network is used as feedforward compensator to approximate the unknown function that help us determine the NN approximation domain a priori via the bound of the reference signal. A novel adaptive prescribed performance control (PPC) scheme is proposed. The predetermined approximation domain can be used to choose centers and widths of the radial basis function neural networks. The advantage of the proposed control scheme is that the prescribed performance of the closed-loop systems can be obtained not only on a compact set, but also on the outside of the approximation domain, without violation the predefined bounds. The simulation is performed to demonstrate the effectiveness of the proposed control scheme.