An efficient reliability analysis method combining adaptive Kriging and modified importance sampling for small failure probability

Yun, Wanying; Lü, Zhenzhou; Jiang, Xian

doi:10.1007/s00158-018-1975-6

Cited by 76 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kriging models must memorize the entire training dataset, and thus the training process becomes intractable for large training datasets. There are some approaches (such as the adaptive Kriging combined with importance sampling method [33]) to improve efficiency in designing the training dataset, however, for a given training database, the comparison between Model 2 and Model 3 clearly shows how the type of surrogate model affects the prediction performance. The same number of 5,000 training samples are used in Model 2 and Model 3, and Model 3 using MLP lowers ,Test by 32% compared to Model 2 using Kriging.…”

Section: Kriging Vs Neural Networkmentioning

confidence: 99%

Surrogate Modeling of Time-Dependent Metocean Conditions during Hurricanes

Qiao

Myers

2021

Preprint

View full text Add to dashboard Cite

Metocean conditions during hurricanes are defined by multiple parameters (e.g., significant wave height and surge height) that vary in time with significant auto- and cross-correlation. In many cases, the nature of the variation of these characteristics in time is important to design and assess the risk to offshore structures, but a persistent problem is that measurements are sparse and time history simulations using metocean models are computationally onerous. Surrogate modeling is an appealing approach to ease the computational burden of metocean modeling, however, modeling the time-dependency of metocean conditions using surrogate models is challenging because the conditions at one time instant are dependent on not only the conditions at that instant but also on the conditions at previous time instances. In this paper, time-dependent surrogate modeling of significant wave height, peak wave period, peak wave direction, and storm surge is explored using a database of metocean conditions at an offshore site. Three types of surrogate models, including Kriging, Multilayer Perceptron (MLP), and Recurrent Neural Network with Gated Recurrent Unit (RNN-GRU), are evaluated, with two different time-dependent structures considered for the Kriging model and two training set sizes for the MLP model, resulting in a total of five models evaluated in this paper. The performance of the models is compared in terms of accuracy and sensitivity towards hyperparameters, and the MLP and RNN-GRU models are demonstrated to have extraordinary prediction performance in this context.

show abstract

Section: Kriging Vs Neural Networkmentioning

confidence: 99%

Surrogate Modeling of Time-Dependent Metocean Conditions during Hurricanes

Qiao

Myers

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…An application to structural reliability can be found in [3] and one to fracture mechanics in [20]. The limit state function can also be represented using an Artificial Neural Network (ANN) model [21,22], a Kriging model [5,23], a polynomial chaos expansion [24] as well as based on statistical learning theory [25]. These surrogate models are usually black box models that rely on a set of training samples.…”

Section: Introductionmentioning

confidence: 99%

Efficient structural reliability analysis by using a PGD model in an adaptive importance sampling schema

Robens-Radermacher

Unger

2020

Adv. Model. and Simul. in Eng. Sci.

View full text Add to dashboard Cite

One of the most important goals in civil engineering is to guarantee the safety of the construction. Standards prescribe a required failure probability in the order of 10 −4 to 10 −6. Generally, it is not possible to compute the failure probability analytically. Therefore, many approximation methods have been developed to estimate the failure probability. Nevertheless, these methods still require a large number of evaluations of the investigated structure, usually finite element (FE) simulations, making full probabilistic design studies not feasible for relevant applications. The aim of this paper is to increase the efficiency of structural reliability analysis by means of reduced order models. The developed method paves the way for using full probabilistic approaches in industrial applications. In the proposed PGD reliability analysis, the solution of the structural computation is directly obtained from evaluating the PGD solution for a specific parameter set without computing a full FE simulation. Additionally, an adaptive importance sampling scheme is used to minimize the total number of required samples. The accuracy of the failure probability depends on the accuracy of the PGD model (mainly influenced on mesh discretization and mode truncation) as well as the number of samples in the sampling algorithm. Therefore, a general iterative PGD reliability procedure is developed to automatically verify the accuracy of the computed failure probability. It is based on a goal-oriented refinement of the PGD model around the adaptively approximated design point. The methodology is applied and evaluated for 1D and 2D examples. The computational savings compared to the method based on a FE model is shown and the influence of the accuracy of the PGD model on the failure probability is studied.

show abstract

“…However, although both methods can be adopted for systems with implicit performance function, the extremely inaccurate results may be yielded for highly nonlinear performance functions. Therefore, the use of metamodels which can replace the procedure of simulating calculations is an alternative way in reliability analysis, such as the response surface model, 21,22 the artificial neural networks, 23,24 the Kriging model, [25][26][27][28][29] and the support vector machine. [30][31][32] In recent years, the adaptive sequential sampling method using Kriging has been conducted more than other surrogate models.…”

Section: Introductionmentioning

confidence: 99%

Multidisciplinary reliability analysis of turbine blade with shape uncertainty by Kriging model and free-form deformation methods

Yang

2020

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

This work presents an integrated approach for the multidisciplinary reliability analysis of turbine blades with shape uncertainty, including the metamodel, the free-form deformation, and the Monte Carlo simulation. The multidisciplinary analysis of turbine blade includes fluid, structure, and thermal analyses, which is time-consuming during integration with multidisciplinary reliability analysis. The metamodel is constructed by adaptive sampling to reduce computational cost. The shape uncertainty with small size changes in reliability analysis should be considered. The geometry-based multidisciplinary analysis may fail to capture the small size changes during the geometry and mesh regeneration process. The main contribution of this article is to introduce the free-form deformation in multidisciplinary reliability analysis to overcome the aforementioned problems. The mesh-based method supported by free-form deformation is proposed. Failure probability analysis of the multidisciplinary blade system is performed using the Monte Carlo simulation and the surrogate model. Through the numerical simulation, it is found that the failure probability increases as the blade shape uncertainty becomes larger. The methodology in this article provides a valuable and applicative way to calculate the risk of blade in multidisciplinary system.

show abstract

An efficient reliability analysis method combining adaptive Kriging and modified importance sampling for small failure probability

Cited by 76 publications

References 27 publications

Surrogate Modeling of Time-Dependent Metocean Conditions during Hurricanes

Surrogate Modeling of Time-Dependent Metocean Conditions during Hurricanes

Efficient structural reliability analysis by using a PGD model in an adaptive importance sampling schema

Multidisciplinary reliability analysis of turbine blade with shape uncertainty by Kriging model and free-form deformation methods

Contact Info

Product

Resources

About