Visualize Scatter Plots

Plot exploration inputs and outputs.

  1. From the Design Explorer ribbon, Evaluate tool group, click the Results Explorer tool.


    Figure 1.
    The Results Explorer browser opens.
  2. In the Results Explorer browser, click the Scatter Plot icon .
  3. Select the desired X-axis value and the desired Y-axis value(s).
  4. Optional: Select constraints to plot as datum lines.
    Note: Checking Show Violated will color plot points red where corresponding runs violate the given constraint.
  5. Optional: Check Optima.
    This will display data points for only optimal runs. This can be useful when there are a large number of runs and also for multi-objective optimization explorations, which may have more than one optimal run.
  6. Analyze the plot.
    Each point in the plot corresponds to an individual run in the DOE. Selecting any plot point will highlight the corresponding run in the summary table.
    Tip: Creating constraints for DOE explorations can be useful, as they can be selected and plotted as datum lines on a scatter plot. This can be a good visualization tool to see which runs in the DOE violate constraints and which are potentially feasible designs.

Visualize Clusters

Using advanced machine learning techniques, simulation results are classified into clusters.

Note:
  • The prediction feature requires the EngDataSciFieldPredict license feature.
  • To view the clusters, you have to have selected Generate Reports - Clustering in the Evaluate dialog when evaluating the exploration. Or, you can click Generate Clusters to generate a new report. Depending on the size of the results and number of runs in the exploration, this may take several minutes.
Restriction: Clustering reports are currently only supported for explorations using OptiStruct and Radioss.
  1. With a scatter plot active, click Show Clusters.
  2. Optional: Select a loadcase or component to change the clustering criteria and the number of clusters.
    Tip: Hovering the mouse over the number of clusters displays the silhouette score plot indicating the optimal number of clusters for the given combination of clustering criteria.
  3. Select a cluster to show its associated runs.

Animate Clusters

Note: Animations are only available for Loadcase = Displacement.
Use the following context menu options to animate clusters.
  • Right-click on a cluster and select Animate Selection. This loads an animation in the active HyperView client, overlaying the final deformed shape of each run in the selected cluster. This can be useful for visualizing the deformed shape of the given cluster as a whole.
  • Right-click on a cluster or in the white space of the Clusters column and select Animate all Clusters. This creates a new page and loads an animation for each cluster in a new HyperView client, overlaying the final deformed shape of each run in each cluster. This can be useful for visualizing the deformed shape of each cluster as a whole and comparing one cluster to another.
  • Select one or more runs in the Runs in Cluster column, right-click, and select Overlay Selection. This loads an animation in the active HyperView client, overlaying the results, including all timesteps, for the selected runs. This can be useful for comparing two runs within a given cluster.