Kopfgrafik_OSL_eng_01

optiSLang Sensitivity Analysis

By means of a global sensitivity analysis and the automatic generation of the Metamodel of Optimal Prognosis (MOP), optimization potential and the corresponding important variables are identified With this previous knowledge, task-related objective functions and constraints can be defined as well as suitable algorithms can be selected.

Best Practice

best practice3D plot of single response with respect to the most important variables

  • Coverage of the entire design space by optimized Latin Hypercube Sampling and minimization of correlation errors among input variables
  • Identification of optimization potential and conflicting objectives
  • Identification of the meta-model with the best prognosis quality of the result value variation in the most fitting sub space of important variables by MOP workflow
  • Quantification of the forecast quality of a meta-model (regression model) for the prognosis of result value variation by the Coefficient of Prognosis (CoP)
  • Identification of the most important input variables related to each result value, constraint and objective
  • Minimization of the amount of solver runs by MOP/CoP workflow

Methods

methods Extended linear correlation matrix

  • Definition of optimization variables with upper and lower bounds
  • Definition of the Design of Experiments (full factorial, central composite, D-optimal)
  • Latin Hypercube Sampling for optimal scanning of multi-dimensional parameter spaces
  • Automated generation of the MOP
  • Quantification of the prognosis quality by the CoP

Postprocessing & Visualization

post processing

CoP Matrix

  • Histograms
  • Correlation matrix
  • 2D and 3D anthill plots
  • Principal Component Analysis
  • 2D and 3D plots of the MOP
  • Parallel Coordinate Plots

Practical Application Examples

practical application examples

more >>