About this document

Identification of Wiener-Hammerstein Systems by khaled is a document available to read on EtoBox.

This paper proposes a method to identify Wiener-Hammerstein systems using Least Squares Support Vector Machines (LS-SVMs). The key idea is to jointly model the input linear dynamic block and static nonlinearity, then apply overparametrization to recover the parameters of the output linear block. This avoids inverting any blocks and allows identification without prior knowledge of the system structures. The method is shown to perform well on both simulated data with suboptimal inputs and real benchmark data.

Author

khaled

Language

EN