Adaptive high-order Hopfield-based neural network tracking controller for uncertain nonlinear dynamical system

The Hopfield neural network (HNN) has been widely discussed for controlling a nonlinear dynamical system. The weighting factors in HNN will be tuned via the Lyapunov stability criterion to guarantee the convergence performance. The proposed architecture in this paper is high-order Hopfield-based neural network (HOHNN), in which additional inputs from functional link net for each neuron are considered. Compared to HNN, the HOHNN performs faster convergence rate. The simulation results for both HNN and HOHNN show the effectiveness of HOHNN controller for affine nonlinear system. It is obvious from the simulation results that the performance for HOHNN controller is better than HNN controller.