File Exchange

image thumbnail

Global sensitivity and uncertainty analysis (GSUA) of dynamical systems using variance-based methods

version 3.0 (816 KB) by Carlos M. Velez S.
Global sensitivity and uncertainty analysis (GSUA) of dynamical systems using variance-based methods


Updated 13 Oct 2015

View License

Global sensitivity analysis (GSA) of dynamical systems (Simulink models) using variance-based methods (brute-force, Sobol, Jansen, Saltelli) with combinations of parameters generated by Monte Carlo method with these sampling methods: uniform distribution, Latin hypercube. Several figures are generated: (1) Plot with temporal responses (Monte Carlo simulation) to all sets of parameters, highlighting the nominal or experimental response; (2) Scatter plots of parameters and output; (3) plot of fractional sensitivity indices; (4) plot of normalized total sensitivity indices; (5) Pie and bar plot with sensitivity indices for every parameter in some time instants. This is a toolbox in developing (including English translation). Please, send commentaries and suggestions.

Comments and Ratings (6)

hi Matlab ,

I was trying to run the basic code but i am getting error in running it , can you help me in resolving this issue ??

Error using pie (line 84)
Text labels must be a cell array of strings.

Error in sens_plot (line 235)
h1 = pie(S,labels);

Error in sens_main (line 68)
subplot(2,2,4), sens_plot('Pie',Par,SensMethod,SJ)

mail id :

I am student of post graduation and trying to learn MATLAB can anybody please help me to understand how to use this toolbox for checking sensitivity of any function .
mail id -

This toolbox helped me to implement the VBSA equations from literature in Matlab.

i appreciate!

One function file named 'makedist.m' is missing from the zip folder. Can you please provide this file?



(1) A main script is included to better application of toolbox. (2) A user manual is included.

All functions were optimized in three functions. Bar plots were included. All plots were improved. Sensitivity indices are shown for temporal responses and for scalar minimum square error (MSE) function. The estimated processing time is displayed.

The remaining time is displayed.

Other sensitivity methods are included (Sobol, Jansen, Saltelli).
The examples are better organized.

Integration as a toolbox.

New functions and examples are included.

Correction of pendulum example.

Correction of function description.

MATLAB Release Compatibility
Created with R2013a
Compatible with any release
Platform Compatibility
Windows macOS Linux