Creating an Automatic Approximation

You can create an automatic approximation if you do not want to learn the details of the approximation techniques. When you create an automatic approximation, Isight uses a preconfigured RBF model with most of the options set to the appropriate values. You only have to configure the input and output parameters and their properties. In addition, Isight can attempt to improve the approximation using sequential sampling. You can create a automatic approximations in the Design Gateway and the Runtime Gateway.

Important: If you are selecting a component that is in a Task Plan, you must select the component using the model explorer.

  1. Do one of the following:

    • From the Design Gateway,

      1. Select the component for which you want to create an approximation:
        • Select a component on the Sim-flow tab or in the model explorer, and click the Approximations button on the component title bar.
        • Right-click the component on the Sim-flow tab or in the model explorer, and select Approximations.

        The Approximations dialog box appears.

      2. On the right side of the dialog box, click New.

        The Approximation Wizard appears.

    • From the Runtime Gateway,

      1. Select a component on the Sim-flow tab or in the model explorer.
      2. Click the Visual Design tab, and click the button on the component title bar.
        Tip: You can also click the Create Approximation button in the middle of the tab to bypass the wizard. Isight creates an approximation using the history data that were gathered during the execution of the model and its components.

        The Approximation Wizard appears.

  2. In the Name of approximation text box, enter a name for the approximation.

  3. Select Automatic, and click Next.

    The Input and Output Parameters screen appears.

    If the approximation is created for an application component, all the parameters of the component are displayed on the page. If the approximation is created for a process component, all the parameters mapped to the subflow are displayed, along with all parameters from the subflow that are still not mapped to the parent. Selecting the latter parameters results in the automatic creation of corresponding parameters in the process component.

    1. Determine which parameters you want to use by selecting the corresponding check boxes in the first column. Alternatively, you can click Check to add all the selected parameters. To clear all the parameters, click Uncheck.

      If your parameters contain arrays, click the check box next to the array root to select all members of the array.

      Note: For any inputs that are not selected, the values for these inputs will have no effect on the outputs evaluated from the approximation. Similarly, if you do not select one of the output parameters, its value will remain constant during execution of the approximation.

    2. Click Next.

      The Sampling Options screen appears.

  4. From the Sampling Options screen, set the following options, as desired:

    • In the sample points text box, specify the number of points for your approximation. This number must be at or above the minimum required number of points specified in the text message above the entry box. If you selected an array, the minimum required number of points reflects your choice.

    • Click As many points as possible in, and enter a time limit for determining the number of points. Isight will keep executing for the specified duration of time.

      Note: If less than the minimum required number of points is executed, Isight will continue executing sampling points until the requirement is met.

    • Click Use a fixed random seed, and specify a seed value to use for the random number generator when determining the set of sample points to be executed. This option allows you to reproduce the approximation with the same set of points later, if desired.

    • Click Execute design points in parallel if you want to execute your initialization points in parallel. You can use this option only if you are using a multiple CPU system or if you are connected to a SIMULIA Execution Engine.

  5. Click Next.

    The Sampling Range screen appears.

  6. From the Sampling Range screen, change the Lower and Upper values for the listed input parameters, as desired. These bounds determine the design space where the random points are generated by Isight.

  7. Click Next.

    The Approximation Improvement Options screen appears.

  8. From the Approximation Improvement Options screen, set the following options as desired. For more information, see Improving Approximations using Sequential Sampling.

    1. Click Skip this step to toggle off approximation improvement. By default, approximation improvement is active for automatic approximations. Isight uses cross-validation to estimate the model error for sequential sampling.
    2. Enter a target for the average prediction error of the approximation. Isight adds sample points sequentially until the average error falls below the value that you enter. Valid values are 0.0–1.0.
    3. Enter the maximum number of additional points that you want to use for improving the approximation.
    4. Enter the maximum number of iterations to improve the approximation. Dividing the maximum number of additional points by the maximum number of iterations results in the number of points that are added during each iteration of sequential sampling. Although it is desirable to add one point during each iteration, choosing fewer iterations reduces the time taken to fit the approximation model.
    5. Click Next.

      The Runtime Options screen appears.

  9. From the Runtime Options screen, set the Store coefficient data in file parameter named option.

    When activated, this option creates a file parameter that stores the approximation’s coefficient data. This option is useful if the approximation is initialized or updated (re-initialized) during execution and the coefficient data are needed for custom postprocessing. It is also useful if you want the coefficient data preserved in your database. For more information on file parameters, see Using File Parameters.

  10. Click Finish.

    A message appears prompting you to initialize the approximation: