Estimate Frequency-Response Models in the App
You must have already imported your data into the app and performed any necessary preprocessing operations. For more information, seeData Preparation.
To estimate frequency-response models in the System Identification app:
In the System Identification app, selectEstimate>Spectral modelsto open the Spectral Model dialog box.
In theMethodlist, select the spectral analysis method you want to use. For information about each method, seeSelecting the Method for Computing Spectral Models.
Specify the frequencies at which to compute the spectral model inoneof the following ways:
In theFrequenciesfield, enter either a vector of values, a MATLAB®expression that evaluates to a vector, or a variable name of a vector in the MATLAB workspace. For example,
logspace(-1,2,500)
.Use the combination ofFrequency SpacingandFrequenciesto construct the frequency vector of values:
In theFrequency Spacinglist, select
Linear
orLogarithmic
frequency spacing.Note
For
etfe
, only theLinear
option is available.In theFrequenciesfield, enter the number of frequency points.
对于时域数据,频率范围从0to the Nyquist frequency. For frequency-domain data, the frequency ranges from the smallest to the largest frequency in the data set.
In theFrequency Resolutionfield, enter the frequency resolution, as described inControlling Frequency Resolution of Spectral Models. To use the default value, enter
default
or, equivalently, the empty matrix[]
.In theModel Namefield, enter the name of the correlation analysis model. The model name should be unique in the Model Board.
ClickEstimateto add this model to the Model Board in the System Identification app.
In the Spectral Model dialog box, clickClose.
To view the frequency-response plot, select theFrequency respcheck box in the System Identification app. For more information about working with this plot, seeFrequency Response Plots for Model Validation.
To view the estimated disturbance spectrum, select theNoise spectrumcheck box in the System Identification app. For more information about working with this plot, seeNoise Spectrum Plots.
Validate the model after estimating it. For more information, seeModel Validation.
To export the model to the MATLAB workspace, drag it to theTo Workspacerectangle in the System Identification app. You can retrieve the responses from the resultingidfrd
model object using thebode
ornyquist
command.