A Novel Adaptive Neural Network-based Control for SISO Uncertain Nonlinear Systems

A unified neural control strategy is presented for uncertain nonlinear systems in this paper. Diagonal recurrent neural networks (DRNNs) with adjustable parameters are utilized to approach the unknown terms. By integrating the Lyapunov stability analysis with universal approximation performance of neural network, a stable neural control scheme is proposed to ensure that all the states of the control system are uniformly ultimately bounded (UUB). The novel design strategy contains the offline training of DRNNs and online adaptive control is utilized to reduce the computation of network training. Simulations experiments are given to illustrate the effectiveness of our approach.