UQ software based on
Bayesian statistics

Standalone software tool for uncertainty quantification and damage identification existing structures. BayesianUQ is contains Bayesian parameter updating of Gram-Charlier expansion based on real-life measurments of structures. The software can be virtually divided to three parts: pre-processing, processing and post-processing.

In pre-processing part, users define the first four central statistical moments. This task can be done manually or users can load original measuremets in .csv file. Very last step of pre-processing is settings of numerical algorithms for Bayesian updating and statistical testing using Kolmogorov-Smirnov test.

Processing is fully-automatic and it contains several crucial steps deeply described in the manual of BayesianUQ. The main task of processing is updating of the probabilistic model in form of Gram-Charlier expansion based on measurements and statistical testing for damage identification.

During post-processing user can manually plot result, use the Gram-Charlier expansion for statistical sampling.

The software BayesianUQ was developed with financial support of Technology Agency of the Czech Republic under project No. TM04000012.

Theoretical background

Theoretical methods implemented into BayesianUQ were described in the following scientific journal paper:

NOVÁK, L. On distribution-based global sensitivity analysis by polynomial chaos expansion. COMPUTERS & STRUCTURES, 2022, 267, ISSN: 0045-7949.

Applications of BayesianUQ

The software tool has been developed in collaboration with industrial partners in the framework of TAČR TM04000012. Validation and applications will be completed in 2025.
If you are interested in software BayesianUQ and its possibilities for your applications/research, please contact main developer Lukas Novak:

Lukas Novak
novak.l@fce.vutbr.cz
Institute of structural mechanics
Faculty of civil engineering
Brno University of Technology
Czech republic

Software for Bayesian updating and Statistical Testing

Accuracy of probabilistic analysis and uncertainty quantification is governed by accuracy of assumed probability distributions of quantity of interest. BayesianUQ software creates the most suitable probabilistic model of quanity of interest based on experimental results and measurements.

Uncertainty quantification
of engineering problems

is a scientific field of great importance focused on analysis of uncertainties in mathemtical models. It is important especially in engineering field in order to optimize the design of structures and reflect given safety requirements.