Weighting adaptive control of Wiener model based on multilayer feedforward neural networks

The parameter identification and control method of a typical class of nonlinear systems-Wiener model is studied. A two-step method is proposed to estimate the linear and nonlinear parts. The proposed identification model is made up of a linear autoregressive moving average model in cascade with a multilayer feedforward neural network. The nonlinearity effects can be eliminated by using the classical extended minimum variance self-tuning control strategy of linear systems. The correction of the proposed control algorithm is verified by the simulation results.