|
|
|
| R2011b Documentation → Model-Based Calibration Toolbox | |
Learn more about Model-Based Calibration Toolbox |
|
| Contents | Index |
| On this page… |
|---|
You must first have a model for which to design an experiment.
From the Model Browser at startup, click
the
button in the toolbar, or click New in
the Test Plans pane, or choose File > New Test Plan.
Click the new Two-Stage node that appears in the model tree (in the All Models pane), or double-click Two Stage in the Test Plans list at the bottom. The Two-Stage Model diagram appears.
If you already have a project open, you can select any existing model within the test plans in the Model Browser tree. For the purposes of this tutorial, you design experiments for the default Two-Stage global model, which is a quadratic.
There is only one input to the global model by default. To increase the number of input factors:
Double-click the Global Model Inputs block in the diagram. The Input Factors Setup dialog appears.
Increase the number of factors to three by clicking the Number of Factors up/down buttons or entering 3 in the edit box.
Change the symbols of the three input factors to N, L, and A. This matches the global factors modeled in the Quick Start tutorial: speed (n), load (L), and air/fuel ratio (A).
To access the Design Editor, use either of the following methods:
Right-click the global model in the diagram and choose Design Experiment, as shown.
You can also access the Design Editor by selecting the menu item TestPlan > Design Experiment.


The Design Editor window appears.
Click the
button
in the toolbar or select File > New. A new node called Linear
Model Design appears.

The new Linear Model Design node is automatically selected. An empty Design Table appears (see above) because you have not yet chosen a design. For this example you create an optimal design for the default global model, which is a quadratic.
You can change the model for which you are designing an experiment from within the Design Editor window by selecting Edit > Model.
Rename the new node Optimal (you can edit the names by clicking again on a node when it is already selected, or by pressing F2, as when selecting to rename in Windows Explorer).
![]() | What Is Design of Experiment? | Creating Optimal Designs | ![]() |

Includes the most popular MATLAB recorded presentations with Q&A sessions led by MATLAB experts.
| © 1984-2012- The MathWorks, Inc. - Site Help - Patents - Trademarks - Privacy Policy - Preventing Piracy - RSS |