Estimate State-Space Models in System Identification App

 Prerequisites

  1. Select Estimate > State Space Models.

    The State Space Models dialog box opens.

      Tip   For more information on the options in the dialog box, click Help.

  2. Specify a model name by clicking adjacent to Model name. The name of the model must be unique in the Model Board.

  3. Select the Specify value option (if not already selected) and specify the model order in the edit field. Model order refers to the number of states in the state-space model.

  4. Select the Continuous-time or Discrete-time option to specify whether to estimate a continuous- or discrete-time model.

    You cannot estimate a discrete-time model if the working data is continuous-time frequency-domain data.

  5. Expand the Model Structure Selection section to configure the model structure, such as canonical form, whether to estimate the disturbance component (K matrix), and specification of feedthrough and input delays.

    For more information about the type of state-space parameterization, see Supported State-Space Parameterizations.

  6. Expand the Estimation Options section to select the estimation method, and configure the cost function.

    Select one of the following Estimation Method from the drop-down list and configure the options. For more information about these methods, see State-Space Model Estimation Methods.

     Subspace (N4SID)

     Prediction Error Minimization (PEM)

     Regularized Reduction

  7. Click Estimate to estimate the model. A new model gets added to the System Identification app.

 Next Steps

Was this topic helpful?