Genetic Aggregation is the default algorithm for generating response surfaces. It automates the process of selecting, configuring, and generating the type of response surface best suited to each output parameter in your problem. From the different types of response surface available (Full 2nd order Polynomial, Non-Parametric Regression, Kriging, and Moving Least Squares), Genetic Aggregation automatically builds the response surface type that is the most appropriate approach for each output.
Auto-refinement is available when you select at least one output parameter for refinement in the Tolerances table and specify a tolerance value for it. Once begun, the auto-refinement process handles design point failures and continues until one of the stopping criteria has been met.
Auto-refinement takes into account failed design points by avoiding the areas close to the failed points when generating the next refinement points. The Crowding Distance Separation Percentage property specifies the minimum allowable distance between new refinement points, providing a radius around failed design points that serves as a constraint for refinement points.
Genetic Aggregation takes more time than classical response surfaces such as Full 2nd order Polynomial, Non-Parametric Regression, or Kriging because of multiple solves of response surfaces and the cross-validation process. In general, Genetic Aggregation is more reliable than the classical response surface models.
To select the best response surface, Genetic Aggregation uses a genetic algorithm that generates populations of different response surfaces solved in parallel.
The fitness function of each response surface is used to determine which one yields the best approach. It takes into account both the accuracy of the response surface on the design points and the stability of the response surface (cross-validation).
The Genetic Aggregation response surface can be a single response surface or a combination of several different response surfaces (obtained by a crossover operation during the genetic algorithm).
For more information, see Genetic Aggregation in the DesignXplorer theory section.
Before generating your response surface, you can set the advanced properties described in Genetic Aggregation Properties.
Because a Genetic Aggregation response surface can take longer to generate than other response surfaces, you can monitor the generation process via the progress bar and messages. You also have the ability to stop the update. If you stop the update, however, any data generated up to this point is discarded.
Once the response surface has been generated, a link to the log file is available in the Properties view. The log file contains information that can help you to assess the quality of your response surface.