User`s guide

Identifying Impulse-Response Models
The following tables summarize the commands for computing impulse- and
step-response models. The resulting models are stored as
idarx model objects
and contain imp u lse-response coefficients in the model parameter
B.For
detailed information abou t these comma nds, see the corresponding reference
page.
Commands for Impulse and Step Response
Command
Description
Example
impulse
Estimates a high-order,
noncausal FIR model
using correlation analysis.
To estimate the m odel m and plot the impulse
response, use the following syntax:
m=impulse(data,Time,'pw',N)
where data is a single- or multiple-output
time-d omain
iddata object, and Time is a
scalar value re presenting the time interval
over which the impu lse or step resp onse is
calculated. For a scalar tim e span T,the
resulting response is plo tte d from -T/4 to T.
'pw' and N is an option property-value pair
that specifies the order
N of the prewhitening
filter
'pw'.
step
Estimates a high-order,
noncausal FIR model
correlation analysis.
To estimate the model m and plot the step
response, use the following syntax:
step(data,Time)
where data is a single- or multiple-output
time-d omain
iddata object, and T ime is the
time span.
To validate the model, s ee Chapter 8, “Model A nalysis”. For more information
about continuin g to work with models in the MAT L AB works p ace , see
Chapter 11, “Using System Identifi cation Toolbox Blocks”.
3-17