Uncertainty and sensitivity analysis of functional risk curves based on Gaussian processes

Iooss, Bertrand; Gratiet, Loïc Le

doi:10.1016/j.ress.2017.11.022

Cited by 18 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The density perturbation approach proposed in Lemaître et al 33 (and used in Sueur et al 38 and Iooss and Le Gratiet 46 ) consists of replacing the density f i of one input X i by a perturbed one f i δ , where δ ∈R represents a shift of a moment (e.g. the mean or the variance).…”

Section: Principles Of Pli-quantiles Andpli-superquantilesmentioning

confidence: 99%

BEPU robustness analysis via perturbed law-based sensitivity indices

Iooss

Vergès²,

Larget

2021

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

The “best-estimate plus uncertainty” (BEPU) methodology is the term used in the nuclear engineering community when dealing with uncertainty quantification issues in realistic numerical simulation models. One of the most critical hypothesis in these studies is the choice of the probability distributions of uncertain input variables which are propagated through the model. Bringing stringent justifications to the BEPU approach, especially in a safety study, requires quantifying the impact of potential uncertainty on the input variable distribution. To solve this problem, this paper deepens the robustness analysis based on the “Perturbed Law-based sensitivity Indices” (PLI). The PLI quantifies the impact of a perturbation of an input distribution on the quantity of interest (as a quantile of a model output or a safety margin) in the BEPU study. The mathematical formalism of the PLI is applied to two particular quantities of interest: the quantile and the superquantile. For both quantities, the PLI can be easily computed using a unique Monte-Carlo sample containing model inputs and output. Numerical tests are developed in order to define validity criteria of a PLI-based robustness analysis. The practical use of the method is illustrated on thermal-hydraulic computer experiments, simulating a cold leg Intermediate Break Loss Of Coolant Accident (IBLOCA) in a pressurized water nuclear reactor.

show abstract

Section: Principles Of Pli-quantiles Andpli-superquantilesmentioning

confidence: 99%

BEPU robustness analysis via perturbed law-based sensitivity indices

Iooss

Vergès²,

Larget

2021

Proceedings of the Institution of Mechanical Engineers, Part O:

Self Cite

View full text Add to dashboard Cite

show abstract

“…Among all densities which have an equivalent shift in the chosen moment, f iδ is defined as that which minimizes the Kullback-Leibler divergence from f i . This method has been applied to compute a QoI that corresponds to a failure probability (Iooss and Le Gratiet, 2019;Perrin and Defaux, 2019), a quantile (Sueur et al, 2017;Larget, 2019) and a superquantile (Iooss et al, 2020;Larget and Gautier, 2020).…”

Section: Introductionmentioning

confidence: 99%

An Information Geometry Approach to Robustness Analysis for the Uncertainty Quantification of Computer Codes

et al. 2021

Self Cite

View full text Add to dashboard Cite

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

show abstract

“…Because of the disadvantage of over‐reliance on a large number of finite element samples by iterative method, Box et al 3 first proposed the experimental design of the response surface method. Many authors have used the response surface method for finite element model correction and for proposing improved methods 4–10 . The traditional response surface method mainly uses regression analysis to establish the response surface model instead of the complex finite element model; then, it approximates the target value.…”

Section: Introductionmentioning

confidence: 99%

Prediction method of bridge static deformation based on dynamic test

Pan

Hong

et al. 2020

Structural Concrete

View full text Add to dashboard Cite

To solve the high cost of bridge load tests, considerable influence on traffic, and damage to bridge structure in the process of problem detection and maintenance of existing bridges, we use the method of improved Gaussian process response surface to explore the prediction of the rigidity and unit weight of existing bridges to produce high‐precision predictions of the existing bridge static test. The Gaussian process response surface method in Bayesian principle is adopted to optimize and correct the model. Because Gaussian process is a non‐parameter model with high sensitivity, reliable accuracy, and small calculation, it avoids repeatedly using finite element model. This makes the efficiency of finite element correction improve significantly. A continuous beam bridge is adopted as a study case. In sample selection, an improved uniform design method based on weighting is designed to improve the learning efficiency and prediction accuracy of the model while using ANSYS to analyze and predict the typical bridge. The analysis of the date of the bridge dynamic test is used to correct the finite element model, obtain the actual parameters of the bridge structure, and predict the measured data of the bridge static load test based on the modified finite element model.

show abstract

Uncertainty and sensitivity analysis of functional risk curves based on Gaussian processes

Cited by 18 publications

References 33 publications

BEPU robustness analysis via perturbed law-based sensitivity indices

BEPU robustness analysis via perturbed law-based sensitivity indices

An Information Geometry Approach to Robustness Analysis for the Uncertainty Quantification of Computer Codes

Prediction method of bridge static deformation based on dynamic test

Contact Info

Product

Resources

About