Hammerstein system identification using LS-SVM's

Least Squares - Support Vector Machines can be used for nonlinear static function regression. LS-SVM's have also been used for blackbox modelling of nonlinear dynamic systems of the form y(t) = f(y(t-1,...),u(t-1,.....)) in the same manner of static function regression. As fully nonlinear blackbox models are often overly broad and difficult to tune we propose the use of LS-SVM's for the identification of Hammerstein models, which can be identified as additive nonlinear models with a collinearity constraint. More information can be found in an internal report which was submitted as a conference paper to NOLCOS 2004.

A Hammerstein model





Fitting the static nonlinearity





Fitting the linear model

Co-ordinator(s):  Bart De Moor, Johan Suykens
Researcher(s):  Ivan Goethals, Kristiaan Pelckmans