Acquiring and Preprocessing Data (System Identification Toolkit)

LabVIEW System Identification Toolkit

Acquiring and Preprocessing Data (System Identification Toolkit)

The first step in identifying an unknown system is acquiring data. You can acquire plant data by using NI DAQ hardware and software or you can use data from a file on disk. You can acquire data in the time domain and/or the frequency domain.

For verification and validation reasons, you must acquire two sets of input-output data samples or split the data into two sets. You use one set of samples to estimate the mathematical model of the system. You use the second set of samples to validate the resulting model. If the resulting model does not meet the predefined specifications, such as the mean square error (MSE), modify the settings and re-verify the resulting model with the data sets.

After acquiring the data, you must preprocess the raw data samples. Preprocessing involves steps such as removing trends, filtering noise, and so on. You can use the Data Preprocessing VIs to analyze the raw data and determine whether that data accurately reflects the response of the system you want to identify. To identify a system model in the frequency domain by using time-domain data, you must preprocess the time-domain data by estimating the frequency response function (FRF). You can use the SI Estimate FRF VI to estimate the FRF from time-domain data.