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. This previous knowledge enables the formulation of task-related objective functions and constraints as well as the selection of suitable optimization algorithms.
Best Practice
- Coverage of the entire design space and minimization of correlation errors among input variables by optimized Latin Hypercube Sampling (LHS)
- Automated identification of the meta-model with the best prognosis quality
- Quantification of the forecast quality of each meta-model for the prognosis of response values by the CoP
- Identification of the most important input variables related to each response value, constraint and objective
- Minimization of solver runs by MOP workflow
Methods
- Definition of optimization variables with upper and lower bounds or discrete values
- Definition and creation of the Design of Experiments (full factorial, central composite, D-optimal, customized DoE); Latin Hypercube Sampling for optimal scanning of multi-dimensional parameter spaces
- Automated generation of the MOP by testing a library of approximation methods
- Quantification of the prognosis quality by the model independent CoP
Postprocessing & Visualization
- Histograms
- Correlation matrix / parallel coordinate plots
- 2/3D Anthill plots and 2/3D surface plots of the MOP
- CoP matrix with all responses
- Residual plots and local error estimates
- Integration of result images of CAE programs
- Customized plots
Practical Application Examples
Distributors
optiSLang is sold worldwide. A list of our distributors can be found here.
Your contact person
back to top