Cantilever Beam (Sensitivity Analysis)

From COSSAN Wiki
Jump to: navigation, search

This page shows how to perform local and global sensitivity analysis of the Cantilever Beam.

Local Sensitivity

Analysis

In this section we show how the local sensitivity analysis can be performed starting from the physical model.

The analysis wizard starts clicking on the green arrow on the top-right corner of the physical model editor. Then the analysis type Sensitivity Analysis has to be selected as shown in the following figure:


LocalSensitivityWizard.png

Clicking on next the following wizard page appears:


LineSamplingsWizard2.png

In this page we can select the quantity of interest and the output of interest. Finally, the reference point and the method for estimate the local sensitivity analysis are selected in the next page (random variables can be added through the '+' button):


LineSamplingsWizard3.png

Results

The results of the local sensitivity analysis can be visualized in COSSAN-X open the folder Sensitivity Analysis of the current project. Then, the EngineOutputs object contains the results of the performed sensitivity analysis (i.e. the LocalSensitivityMeasures):


ResultsSensitivityLocal.png

Details of the object can be visualized by selection the object of interest. For instance selection the object of type LocalSensitivityMeasures the description show the summary of the object. Different actions can be performed on this object in order to visualized the results in a number of different ways such as: table, bar histogram etc.


ResultsSensitivityLocal2.png

Global Sensitivity

Analysis

Starting an analysis from the physical model, first the type of analysis must be selected:


GlobalSensitivityWizard1.png

The, the global sensitivity measures is selected as quantity of interest:


GlobalSensitivityWizard2.png

The next wizard page allows to select the input variable that has to be considered in the global sensitivity analysis, the number of bootstrap resamples used to estimate the confidence intervals of the estimated quantities, the number of samples used and finally the algorithm used:


GlobalSensitivityWizard3.png

  • The Random Balance Design is a very efficient method but allows to compute only the first order indices.
  • The Upper Bounds of the upper bounds are computed using Markov chain and the gradient of the function along the point of the chains.
  • The Sobol' indices are computed adopting the Saltelli method that allows to estimate the first order indices and the total indices.

Results

The results of the sensitivity analysis can be visualized in COSSAN-X open the folder Sensitivity Analysis of the current project. Then, the EngineOutputs object contains the results of the performed sensitivity analysis


ResultsSensitivity2.png

Details of the object can be visualized by selection the object of interest. For instance selection the object of type SensitivityMeasures the description show the summary of the object. Different actions can be performed on this object in order to visualized the results in a number of different ways such as: table, bar histogram etc.


ResultsSensitivity3.png

See Also