User`s guide

4 Nonlinear Black-Box Model Identification
Supported Data for Estimating Nonlinear Black-Box
Models
You can estimate discrete-time black-box m odels for data with the following
characteristics:
• Time-domain input-output or time-series data.
Note Time series are supported for nonlinear ARX models only.
• Single-output or multiple-output data.
Before you begin estimating models, import y our data into the MATLAB
software and represent the data in either of the following ways:
• In the System Identification Tool GUI. ImportthedataintotheGUI,
as described in “Representing Data in the G UI” on page 1-13.
• At the command line. Represent your data as an
iddata or idfrd object.
To examine the data features, plot the data on a time plot or an estimated
frequency-response plot. You can preproces s you r data by inte rpo lating
missing values, filtering to emphasize a s pe cific frequency range, or
resampling using a different time interval. For more information about
available date plots and data-preprocessing operations, see Chapter 1, “Data
Processing”.
Caution For nonlinear modeling, do not remove offsets and linear trends
from the measured signals.
4-2