User`s guide

Identifying Hammerstein-Wiener Models
Identifying Hammerstein-Wiener Models
In this section...
“Supported Data for Estimating Hammerstein-Wiener Models” on page 4-15
“Definition of the Hammerstein-Wiener Model” on page 4-15
“Nonlinearity Estimators for Hammerstein-Wiener M odels” on page 4-17
“How to Estimate Hammerstein-Wiener Models in the GUI” on page 4-18
“How to Estimate Hammerstein-Wiener Models at the C ommand Line”
on page 4-20
Supported Data for Estimating Hammerstein-Wiener
Models
You can estimate discrete-time Hamm erstei n -Wiener mod els from data w i t h
the f ollow i ng characteristics:
• Time-domain input-output data
Note Hammerstein-Wiener models do not s upport time-series data, which
has no input signal.
• Single-output or multiple-output data
Definition of the H amm erstein-Wiener Model
Hammerstein-Wiener models describe dynamic systems using one or two
static nonlin ear block s in series with a linear block . O nly the linear block
contains dynamic elements.
The linear block is a discrete-time transfer function and the nonlinear
blocks are implemented using nonlinearity estimators, such as
saturation,
wavenet,anddeadzone.
4-15