Generalized predictive control based on error correction using the dynamic neural network

Considering the influence of modelling error on the robustness of nonlinear predictive control, the paper proposes a generalized predictive control algorithm based on error correction using the dynamic backpropagation network, the algorithm has dynamic compensation capability so that the dynamic error of the model can be effectively reduced and the modelling accuracy can be raised. The simulation results show the algorithm is effective for nonlinear systems.