An Improved Functional-Link Neural Networks for Dynamic System Identification

An improved functional link neural network was proposed for the identification of the dynamic system. In the improved method, the partial derivatives of the network outputs w.r.t its weights were re-deduced, and the more accurate evaluations of the derivatives were obtained. As a result, a novel recursive algorithm was developed to update the weights of the FLNN and a faster learning could be expected. The experiment results show that, a generic FLNN has been developed to identify the same dynamic system for comparison, the improved one have higher convergence rate and more robustness. So it is more suitable for dynamic system identification.