Nonlinear dynamic system identification using pipelined functional link artificial recurrent neural network

摘要: A computationally efficient pipelined functional link artificial recurrent neural network (PFLARNN) is proposed for nonlinear dynamic system identification using a modification real-time learning (RTRL) algorithm in this paper. In contrast to feedforward (such as (FLANN)), the PFLARNN consists of number simple small-scale (FLARNN) modules. Since those modules can be performed simultaneously parallelism fashion, would result significant improvement its total computational efficiency. Moreover, nonlinearity each module introduced by enhancing input pattern with expansion. Therefore, performance filter further improved. Computer simulations demonstrate that proper choice expansion PFLARNN, performs better than FLANN and multilayer perceptron (MLP) identification.