Preparing Data for Nonlinear Identification

Estimating nonlinear ARX and Hammerstein-Wiener models requires uniformly sampled time-domain data. Your data can have one or more input and output channels.

For time-series data, you can only fit nonlinear ARX models and nonlinear state-space models.

    Tip   Whenever possible, use different data sets for model estimation and validation.

Before estimating models, import your data into the MATLAB® workspace and do one of the following:

  • In the System Identification app. Import data into the app, as described in Represent Data.

  • At the command line. Represent your data as an iddata object, as described in the corresponding reference page.

You can analyze data quality and preprocess data by interpolating missing values, filtering to emphasize a specific frequency range, or resampling using a different sample time (see Ways to Prepare Data for System Identification).

Data detrending can be useful in certain cases, such as before modeling the relationship between the change in input and the change in output about an operating point. However, most applications do not require you to remove offsets and linear trends from the data before nonlinear modeling.

Was this topic helpful?