Subspace-based Identification Algorithms for Hammerstein and Wiener Models

摘要

The paper by Gomez and Baeyens contributes to the field of identification of nonlinear block oriented models, i.e. models that consist of interconnections of linear dynamic and static nonlinear blocks. This field of nonlinear system identification, which goes back at least to Wiener, has attracted quite a lot of interest in recent years as indicated by the bibliography of the paper under discussion. One reason is that block oriented models can capture important nonlinear effects, at the same time as the linear dynamics make them tractable from an analysis point of view. The application of subspace identification techniques to nonlinear block oriented models, as pioneered by [2] and [3], represents an important step forward due to the fact that MIMO systems can be treated in a systematic way.