User`s guide

1 Data Processing

Ways to Process Data for System Identification

The following tasks help to prepare your data for identifying m odels from data:

Import data into the MATLAB workspa ce

Before you can begin identifying models, you must import your data into the

MATLAB

workspace. You can import the data from external data ﬁles, create

data by simulation, or m anually create data arrays at the command line.

For more information about importing data into MATLAB, see “Importing

Data into the M ATLA B Workspace” on page 1-5.

After you import the data, you must represent it for system identiﬁcation.

Represent data for system identification

You can represent data as variables in the MATLAB workspace by doing

one of the following:

• For working in the GUI, import d ata into the System Identiﬁcation Tool

GUI.

See“RepresentingDataintheGUI”onpage1-13.

• For working at the comma n d line, create an

iddata or idfrd object.

For tim e-domain or frequency-domai n data, see “Representing Tim e- and

Frequency-Domain Data Using iddata Objects” on page 1-47.

For frequency-response data, see “Representing Frequency-Re spon se Data

Using idfrd Objects” on page 1-67.

Simulate data

As an alternative to us ing meas ure d data, you can simul ate data with and

without noise.

To learn how to create data sets using simulation, see “G enerating Data

Using Simulation” on page 1-115.

1-2