Neural Network Based on Nonlinear Smith Predictor
TAN Yonghong
Achiel R. Van Cauwenberghe
Abstract：An extension of the Smith predictor principle t o the nonlinear case is proposed. This nonlinear predictor can be constructed using neural networks. This is very useful for the time-delay compensation of nonlinear processes.The neural network based predictor has been applied to the prediction of nonlinear dynamic process. A comparison of the proposed strategy with the iterative and non-iterative d -step-ahead neural predictors for the prediction of the manifold pressure process in an automotive engine is illustrated. The predictiv e result of the corresponding first-principles model-based nonlinear predictor is also illustrated for the comparison.
Keywords：neural networksSmith predictornonlinear systemtime-delay
Publication Date：2000-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 410-414 )