5. Normalizing Estimation Data

You can use the LabVIEW System Identification Assistant to normalize signals to set their mean and standard deviation to 0 and 1 respectively. Normalizing signals makes calculations more manageable when estimating models, particularly when a small change in the stimulus can result in a large change in the response.

Complete the following steps to normalize the data you want to use for model estimation.

1. From the LabVIEW SignalExpress menu bar, select Add Step»System Identification»Preprocessing»Normalize Data to add a Normalize Data step to the Project View.
2. On the Input Signals tab in the Configuration View, verify that Estimation Stimulus is selected in the Stimulus signal pull-down menu. This pull-down menu specifies the stimulus signal you want to normalize.
3. Select Estimation Response from the Response signal pull-down menu to specify Estimation Response as the response signal you want to normalize.
4. On the Mean Source Configuration tab, verify that the Auto calculated option is selected in both the Stimulus mean source and Response mean source sections. When you select Auto calculated, the System Identification Assistant automatically calculates the mean of the stimulus or response signal and normalizes the signal using that mean value.
5. Similarly, on the Standard Deviation Source Configuration tab, verify that the Auto calculated option is selected in both the Stimulus standard deviation source and Response standard deviation source sections. When you select Auto calculated, the System Identification Assistant automatically calculates the standard deviation of the stimulus or response signal and normalizes the signal using that standard deviation value.
6. Observe the two graphs in the Configuration View. Stimulus Signals displays the original Estimation Stimulus signal and the same signal after normalization. Response Signals displays the original Estimation Response signal and the same signal after normalization.
   
   You can see from the graphs that the mean of both normalized signals is approximately 0 and their standard deviation is approximately 1.
7. In the Project View, rename the Normalized - Estimation Stimulus output to Normalized Stimulus. You can use Normalized Stimulus as the stimulus signal to estimate the model of the motor.
8. Rename the Normalized - Estimation Response output to Normalized Response. You can use Normalized Response as the response signal to estimate the model of the motor.
9. Select File»Save Project to save the project.