An optimal two-stage identification algorithm for Hammerstein-Wiener nonlinear systems
Automatica (Journal of IFAC)
Least Squares Support Vector Machine Classifiers
Neural Processing Letters
A stable one-step-ahead predictive control of non-linear systems
Automatica (Journal of IFAC)
Identification of MIMO Hammerstein models using least squares support vector machines
Automatica (Journal of IFAC)
Pruning error minimization in least squares support vector machines
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
A novel LSSVM-ARX Hammerstein model structure is proposed for a continuous stirred tank reactor (CSTR). LSSVM with a radial basis function (RBF) kernel is used to represent the static nonlinear block in the Hammerstein model. The dynamic linear part of the model is realized by a linear autoregression model with exogenous input (ARX). The linear model parameters and the static nonlinearity can be obtained simultaneously by solving a set of linear equations followed by singular value decomposition. Identification results of CSTR indicate that the proposed Hammerstein model has higher prediction accuracy in comparison with the traditional Hammerstein model, and it can approximate the dynamic behavior of the plant efficiently.