Learn more about System Identification Toolbox

Supported Models for Time- and Frequency-Domain Data

On this page…
Supported Models for Time-Domain Data Supported Models for Frequency-Domain Data

Supported Models for Time-Domain Data

Continuous-Time Models

You can directly estimate the following types of continuous-time models:

• Low-order transfer functions. See Identifying Low-Order Transfer Functions (Process Models).

• Input-output polynomial models. See Identifying Input-Output Polynomial Models.

• State-space models. See Identifying State-Space Models.

To get a linear, continuous-time model of arbitrary structure for time-domain data, you can estimate a discrete-time model, and then use d2c to transform it to a continuous-time model.

Discrete-Time Models

You can estimate all linear and nonlinear models supported by the System Identification Toolbox™ product as discrete-time models, except the continuous-time transfer functions (process models). For more information about process models, see Identifying Low-Order Transfer Functions (Process Models).

ODEs (Grey-Box Models)

You can estimate both continuous-time and discrete-time models from time-domain data for linear and nonlinear differential and difference equations. See ODE Parameter Estimation (Grey-Box Modeling).

Nonlinear Models

You can estimate discrete-time Hammerstein-Wiener and nonlinear ARX models from time-domain data. See Nonlinear Black-Box Model Identification.

You can also estimate nonlinear grey-box models from time-domain data. See Estimating Nonlinear Grey-Box Models.

Back to Top

Supported Models for Frequency-Domain Data

There are two types of frequency-domain data:

• Continuous-time data

• Discrete-time data

You specify frequency-domain data as continuous- or discrete-time when you either import data into the System Identification Tool GUI or create a System Identification Toolbox data object. For more information about representing your data as System Identification Toolbox data objects, see Data Import and Processing.

To designate discrete-time data, you set the sampling interval of the data to the experimental data sampling interval. To designate continuous-time data, you must set the sampling interval of the data to zero. Setting the sampling interval to zero corresponds to taking a Fourier transform of continuous-time data.

Continuous-Time Models

You can estimate the following types of continuous-time models directly:

• Low-order transfer functions. See Identifying Low-Order Transfer Functions (Process Models).

• Input-output polynomial models. See Identifying Input-Output Polynomial Models.

• State-space models.

  From continuous-time frequency-domain data, you can estimate continuous-time state-space models. From discrete-time frequency-domain data, you can estimate continuous-time black-box models with canonical parameterization. See Identifying State-Space Models.

To get a linear, continuous-time model of arbitrary structure for frequency-domain data, you can estimate a discrete-time model and use d2c to transform it to a continuous-time model.

Discrete-Time Models

You can estimate only ARX and output-error (OE) polynomial models using frequency-domain data. See Identifying Input-Output Polynomial Models.

Other linear model structures include noise models, which are not supported for frequency-domain data.

ODEs (Grey-Box Models)

For linear grey-box models, you can estimate both continuous-time and discrete-time models from frequency-domain data.

Nonlinear grey-box models are supported only for time-domain data.

See ODE Parameter Estimation (Grey-Box Modeling).

Nonlinear Black-Box Models

Frequency-domain data is not relevant to nonlinear black-box models, which support only time-domain data.

Back to Top

Recommended Model Estimation Sequence

Supported Continuous-Time and Discrete-Time Models

© 1984-2009- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS