User`s guide

Identifying Nonlinear ARX Models
Nonlinearity Estimators for Nonlinear ARX Models
Nonlinear ARX models support the follow in g n on l in earity estimators:
• Sigmoid N etwork
• Tree Partition
• Wavelet Network
• Custom Network
• Linear (indicates absence of nonlinearity estimator)
• Neural Network
Note You must have the Neural Network Toolbox™ product to use
the Neural N etw ork nonlinearity estimator. If your model has only one
regressor, yo u can also use the Saturation, Dead Zone, One -Dimensional
Polynom i al, and Piecewise L inear nonlinearity e stimators, as listed in
“Nonlinearity Estimators for Hammerstein-Wiener Models” on page 4-17.
For a summary of all nonlinearity estimators and links to the corresponding
reference pages, see “Supported Nonlinearity Estimators” on page 4-25.
You can exclude the nonlinearity function from the model structure. In this
case, the model includes all standard and custom regressors and is linear in
the parameters.
In the System Identifi cation Tool GUI. Yo u can omit the nonlinear block
by selecting
None for t he Nonlinearity.
At the command line. You can omit the nonlinear block by setting the
Nonlinearity property value to 'L inea r'. For more information, see the
nlarx and idnlarx reference pages.
For a description of each n onlinearity estim ator, see “Supported Nonlinearity
Estimators” on page 4-25.
4-9