Model Analysis > Creo Behavioral Modeling Tools > Design Studies > Statistical Design Study > To Conduct a MODS type of Statistical Design Study
  
To Conduct a MODS type of Statistical Design Study
To conduct a MODS type of Statistical Design Study, you need to select an existing Multi-Objective Design Study (MODS).
1. Click Analysis > Statistical Design Study. The Statistical Design Study dialog box opens. The dialog box consists of the following sections:
Design Study—Displays the Name and Type of the statistical design study to be conducted.
Design Variables—Displays the design variables obtained from an existing MODS along with their minimum and maximum values, the statistical distribution type assigned to the design variables, and the distribution parameters calculated for the design variables. The design variables are listed in separate rows.
Design Goals—Displays the design goals obtained from an existing MODS along with their minimum and maximum values and the statistical distribution type assigned to the design goals. This section also displays the values that you specify for the Lower Limit and Upper Limit for the design goals. By default, the values for these limits are not specified.
2. To create a new study, click File > New and specify a name for the study. To open an existing study, click File > Open and select the name of the study from the Design Study dialog box.
3. Select MODS type of design study from the options available.
4. Click Setup > MODS Response Surface to select an existing MODS. The Design Study dialog box opens listing all the saved multi-objective design studies. Select one of the listed studies. The Design Variables section displays the design variables of the selected MODS, their minimum and maximum values, the statistical distribution assigned to them and their distribution parameters. The Design Goals section displays the design goals of the selected MODS and the distribution type assigned to them.
5. To update the minimum or maximum value for a specific design variable, click the value displayed under Min or Max, respectively, in the Design Variables section and enter the desired value. To update the distribution type for a specific design variable or design goal, select the type from the list under Distribution. The Normal type of distribution is selected by default for all the design variables and design goals.
6. To update the statistical distribution parameters for a particular design variable, double-click any value (except for the value under Distribution, Min or Max) for a particular design variable in the Design Variables section or select any value and click Properties. The Design Variable Statistical Properties dialog box opens. The system generated graph for the distribution type, the minimum and maximum values for the design variable, the selected distribution type, and the distribution parameters applicable to the selected distribution type are displayed.
Enter the desired values for the mean and the distribution parameters. You can also modify the distribution type. The display for the graph is updated as per the new values. Click OK to apply the changes and exit. Or click Cancel to exit.
 
Minimum and maximum values for the design variable are defined by the selected MODS response surface. Thus, you cannot modify these values.
You can enter absolute values or as a percentage of the design variable values for the statistical distribution parameters in case of the MODS type of design study. You must type the % sign in case of percentage values.
7. To specify the number of samples to be computed for each operating point, click Setup > Number of samples. The Samples dialog box opens. Enter the number of samples. You can enter a value between 100 and 250000. The default value is 2000.
8. Enter the values for the Lower Limit and Upper Limit for the design goals that are required for computing the DPMU and n x Sigma values. These values are computed even if you specify only one limit.
9. Click Compute to compute the minimum and maximum values and the statistical distribution parameters for the design goals. Enter the number of experiments you want Creo Parametric to generate to conduct the study. By default, 16 experiments are generated. The completion percentage for the computation is displayed in the message area in the Creo Parametric window.
 
* To abort the computation of the statistical design study, click in the Creo Parametric message area. A Confirmation dialog box appears. Click Yes to abort the computation.
On successful completion, the computed values are displayed under the Table Data section in the Multi-Objective Design Study dialog box. The number of records generated for the statistical distribution parameters is equal to the number of experiments you specify. The generated records are stored as the master table of a multi-objective design study.
10. In the Multi-Objective Design Study dialog box:
You can view the contents of the generated master table. You can derive tables from the master table and view their contents.
For the generated master table or derived table, you can plot graphs that illustrate how the computed distribution parameters for a selected design goal change with respect to the corresponding values of the design variables.
Select any table under the Table Tree section and select any record under the Table Data section. Click Record > Graph or right-click and select Graph from the shortcut menu. The system generated graph for the distribution type and minimum and maximum values are displayed in the Design Goal Statistical Properties dialog box.
The computed values of the distribution parameters, the lower and upper limits that you specify, and the computed values for DPMU and n x Sigma are also displayed. In the system generated graph, vertical red lines indicate the values of the user-defined limits and shaded red areas indicate the regions of defects, that is the number of experiments that fall outside the user-defined limits. Click OK or Cancel to exit.
Click File > Exit to return to the Statistical Design Study dialog box.
11. Click File > Save in the Statistical Design Study dialog box to save the study. If you exit without saving the study, a Confirmation dialog box appears. Click Yes to exit without saving.
12. Click File > Exit or click Close to end the study.