About the Benchmarks category

UQ with UQLab Benchmarks
1

Library of test functions and data sets to test your uncertainty quantification (UQ) algorithms. You know additional test functions or data sets? Share them by creating a new topic here! Read this post further for an index of the benchmark cases.

Test functions based on the number of dimensions

Test functions based on the field of applications

2

Thank you for your sharing and enthusiasm,benchmarks play an important role in analysis, Are there other standard test functions? Like a cantilever tube, twenty-three truss-type girder. Because this is a non-normal distribution，when using UQLlab, has it been considered that the non-normal distribution has been converted to the standard normal distribution. InputOpts.Marginals(1).Type =‘Gaussian’;
InputOpts.Marginals(1).Parameters = [1,0.05]; For non-standard positive variables, you don’t need to convert them to standard normal distribution again when you define the function?

3

Hi @youxiong,

I’ll be happy to consider implementing and adding those benchmark functions you mentioned if you can point me to the references.

Thanks a lot!

4

Ok. thank you. the cantilever tube ,You can see it in the 5.3 example of the article a novel learning function based on Kriging for reliability analysis. and then, twenty-three truss-type girder , You can see it in the 3.2 of the article an active-learning algorithm that combines sparse polynomial chaos expansions and bootstrap for structural reliability analysis.