Analytics & Visualization

Simplify complexity and make better decisions with our comprehensive environment for data analysis and visualization.

Engineering Data Visualization and AnalyticsUnderstanding the relations between variables is crucial for making the right design decisions, especially with complex problems including a high number of conflicting objectives. 

Our sophisticated data analysis and visualization tools enable you to gain deeper insight into your design alternatives, identify key factors and spot the relations among variables.

 

 

TOOLS for every need
Master the Design Space
Understand patterns and trends by visualizing the results of your optimization process in a smart visual context
Reduce Problem Complexity
Make the optimization process more efficient by identifying significant variables and correlation effects.
Consider Different Scenarios
Explore what-if analysis by assessing the impact of varying input assumptions and scenarios.

Our Engineering Data Intelligence technology includes a complete array of analytics and visualization tools, tailormade for the needs of engineering teams.

Basic post-processing

Design Charts are basic post-processing tools enabling the visualization of the optimization trends, distribution and density of samples in the design space (including Pareto designs) and within variable ranges. These charts also allow to filter out only certain designs, and re-use them for further optimization or local RSM.

 

Basic Post Processing Charts

Analyze the trade-offs among conflicting design attributes

Exploit our set of Multi-Variate Analysis (MVA) tools to visualize patterns and relationships governing the system response given a particular design configuration.

 

  • Self-Organizing Maps (SOM) | The Self-Organizing Map tool effectively highlights local correlation of multiple variables and hidden cluster structures.
  • Principal Component Analysis (PCA) | Principal Component Analysis equips decision makers with a robust guideline for reducing the number of variables of a complex dataset and revealing the simplified structure.
  • Multidimensional Scaling (MDS) | Multidimensional Scaling arranges data in the low-dimensional space in order to reveal hidden similarities and dissimilarities, and identify clusters.
  • Partitive Clustering | Partitive Clustering techniques help analysts spot trends in variable behavior and the effects of combinations of multiple variables.

Identify the most important design variables a priori and make the optimization process more efficient

Sensitivity Analysis charts help designers reduce problem complexity. They provide graphical means for assessing the main interaction effects of input variables on outputs with the aim of excluding those with negligible importance from RSM training and/or optimization.

Assess the distribution of samples

Distribution Analysis charts enable designers to increase the knowledge of the problem, predict the behavior of variables and assess multiobjective robust design optimization.

Evaluate the quality of RSM models when performing virtual optimization cycles

RSM charts enable designers to evaluate the quality of the model generated using  Response Surface Methodologies -  assess the relative and absolute extrapolation errors and other performance indices with respect to the available real designs, and compare them in order to choose the best RSM for virtual optimization..

Rank optimal designs

Multi-criteria Decision Making 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. Read more