open menu

Data Visualization

modeFRONTIER’s powerful data visualization features complete the set of Analytics tools helping engineers extract fundamental knowledge about the design from dense datasets.

Information underlying the hundreds of complex numerical data generated from parametric studies or optimization campaign is re-arranged and projected in the sophisticated charts and graphs of the Design Space environment of modeFRONTIER. 


The design space environment is now also available as a standalone application - modeSPACE - that enables efficient license and role management within teams. This module includes the sophisticated set of modeFRONTIER tools for data analysis and investigation of problem characteristics both in the post-processing and in the pre-optimization phase.

The following groups of visualization tools are available:
  • Design Charts: basic post-processing tools enabling the visualization of  optimization trends, distribution and density of samples in the design space, including best designs. 
  • RSM Charts: help designers evaluate the quality of the generated RSM functions when performing virtual optimization cycles. By comparing the results with the available real designs, a choice can be made for best RSM function.
  • Statistical Charts: analytic tools allow the reduction of problem dimensionality by excluding factors of negligible importance. By providing global correlations, as well as primary and interaction effects of both dependent and independent variables  the efficiency of design evaluation is increased.
  • Distribution Analysis Charts: graphical tool for assessing the distribution of samples, increasing the designer’s knowledge of the problem and predicting the behaviour of variables. Distribution Analysis charts provide useful information for multi-objective robust design optimization.
  • MVA charts: SOM Charts, Clustering Charts, PCA Charts, and MDS Charts offer projections of high-dimensional data in lower-dimensional graphs. Multi-Variate Analysis techniques help detect patterns, hidden structures and similarities within a dataset, to achieve a more complete knowledge of variable behaviour and identify effects of multi-variable combinations.  
  • MCDM Charts: provide graphical representation of attributes used for measuring the performance of available alternatives with respect to user preferences. The solutions are then ranked to enhance the users’ understanding of the data under consideration.

Sign in