open menu

Design Space Exploration

When defining an engineering problem and choosing the variables, the region of interest called Design Space is framed. DOE techniques allow for the exploration of the design space by considering all variables simultaneously and predicting the system's response over a wide range of values.

The choice of the most suitable DOE depends largely on:

  • the problem at hand
  • the purpose of the exploration (e.g. optimization, RSM training, etc.)
  • the available computational resources.

modeFRONTIER® offers a number of sophisticated and efficient DOE methods, which permit the efficient measurement of the design space dimensionality, and develop scientifically a series of simulation experiments.

Among those methods, Space Filler DOEs serve as the starting point for a subsequent optimization process or a database for response surface training. Statistical DOEs are useful to create samplings for the sensitivity analysis thus allowing in-depth understanding of the problem by identifying the sources of variation. Robustness and reliability DOEs help create a set of stochastic points for robustness evaluation. Optimal Designs DOEs are special purpose techniques used for reducing the dataset in a suitable way.




New Adaptive Space Filler (ASF) Algorithm

When dealing with limited computational resources and small experimental datasets, space filling algorithms are the best suited to increasing design space knowledge. The new Adaptive Space Filler combines state-of-the-art space filling strategies with the predictive ability of response surfaces. The space filler iteratively adds points to the design space and uses them to train and constantly improve the accuracy of an RSM based on one, or more user-defined criteria.

In essence, ASF enhances design space exploration by providing users with a well-distributed DOE dataset for the initialization of an optimization algorithm as well as a reliable RSM for virtual optimization or further design space investigation.


Benefits from modeFRONTIER® DOE techniques:
  • Time and resource savings on experiments
  • Check for robust solutions 
  • Identify variation sources and variable interaction at an early stage of the design process
  • Provide reusable models of the problem
  • Allow better decision making with detailed knowledge of the design space

Sign in