An efficient method combining active learning Kriging and Monte Carlo simulation for profust failure probability

Ling, Chunyan; Lü, Zhenzhou; Sun, Bo; Wang, Minjie

doi:10.1016/j.fss.2019.02.003

Cited by 30 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where σ2 and R (θ.p.r) are selected, respectively, by variance and Gaussian correlation function between the points p and r by parameter θ. [64][65][66][67][68][69] Method setting parameters…”

Section: Kriging Interpolation Methodsmentioning

confidence: 99%

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Jamali

Mousavi

Peyma

et al. 2022

Journal of Reinforced Plastics and Composites

View full text Add to dashboard Cite

Compressive strength is the ability of materials to withstand loads without deformation or cracking. It is one of the most important criteria for evaluating the properties of concrete. The use of Fiber-Reinforced Polymers (FRP) to Strengthen concrete columns and as a supplement to improve some properties of concrete materials has received much attention in recent decades. Therefore, it is important to investigate and determine the compressive strength of confined concrete with FRP sheets. In this study, a comprehensive database containing 1066 specimens of concrete cylinders confined with FRP sheets has been collected. Then, using machine learning methods, the estimation and evaluation of the compressive strength of the mentioned specimens were discussed. The artificial neural network of multilayer perceptron (MLP) and support vector regression (SVR), fuzzy neural inference system (ANFIS), and its combination with particle swarm algorithm (PSO) and kriging interpolation method are the methods used in this study. Subsequently, these methods were compared with the models presented in previous studies. The results of this comparison show that the kriging interpolation method with a correlation coefficient of 0.985 in estimating compressive strength has the lowest error compared to other models.

show abstract

Section: Kriging Interpolation Methodsmentioning

confidence: 99%

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Jamali

Mousavi

Peyma

et al. 2022

Journal of Reinforced Plastics and Composites

View full text Add to dashboard Cite

show abstract

“…The probabilistic method combines MCS with the Kriging to perform efficiently the reliability analysis [27]. More precisely, the proposed method uses the DOE method to obtain the sampling inputs, and the deterministic FE simulation is performed for all the sampling inputs, then Kriging metamodel is constructed based on the sampling inputs and their corresponding outputs.…”

Section: Reliability Analysis Based Metamodelmentioning

confidence: 99%

Advanced Reliability Analysis of Mechatronic Packagings coupling ANSYS^© and R

Hamdani

Radi

Hami

2022

Int. J. Simul. Multidisci. Des. Optim.

View full text Add to dashboard Cite

The complexity challenges of mechatronic systems justify the need of numerical simulation to efficiently assess their reliability. In the case of solder joints in electronic packages, finite element methods (FEM) are commonly used to evaluate their fatigue response under thermal loading. Nevertheless, Experience shows that the prediction quality is always affected by the variability of the design variables. This paper aims to benefit from the statistical power of the R software and the efficiency of the finite element software ANSYS©, to develop a probabilistic approach to predicting the solder joint reliability in Mechatronic Packaging taking into account the uncertainties in material properties. The coupling of the two software proved an effective evaluation of the reliability of the T-CSP using the proposed method.

show abstract

“…The first example is a series system having four branches. [38][39][40] The performance function is expressed as…”

Section: Example1: Four Branches Functionmentioning

confidence: 99%

“…The first example is a series system having four branches 38–40 . The performance function is expressed as

\begin{equation}G({\bf{x}}) = \min \left\{ { \def\eqcellsep{&}\begin{array}{@{}*{1}{c}@{}} {3 + \frac{{{{({x_1} - {x_2})}^2}}}{{10}} - \frac{{({x_1} + {x_2})}}{{\sqrt 2 }}}\\ {3 + \frac{{{{({x_1} - {x_2})}^2}}}{{10}} + \frac{{({x_1} + {x_2})}}{{\sqrt 2 }}}\\ {({x_1} - {x_2}) + \frac{6}{{\sqrt 2 }}}\\ {({x_2} - {x_1}) + \frac{6}{{\sqrt 2 }}} \end{array} } \right\}\end{equation}

…”

Section: Numerical Examplesmentioning

confidence: 99%

The adaptive weight learning function for reliability analysis and its application to multiple active learning methods

Liu

Zhou

et al. 2022

Quality & Reliability Eng

View full text Add to dashboard Cite

In engineering, evaluating the failure probability of structures with complex performance functions is a challenging task. Some active learning methods based on the Kriging model gain considerable attention for structural reliability analysis. The existing learning functions offer new learning criterions to select sample points, but the probability density function (PDF) of sample points is ignored in some learning functions. To decrease selecting sample points in low PDF regions, this study presents a new adaptive weight learning function (WLF). The learning function WLF constituted by the adaptive orient function and the joint PDF can be applicable to multiple learning functions. Depending on the importance degree of candidate sample points, the sample points can be assigned different weight by learning function WLF. When the leaning function WLF is applicated to the existing active learning methods, the sample point with a higher PDF in neighborhood of the limit state function (LSF) can be given a larger weight to preferentially select into design of experiments (DoE). Therefore, the learning function WLF can help the multiple learning functions to select informative sample points with high PDF, which can further improve the efficiency of these learning functions. Four examples are used to illustrate the accuracy and efficiency as well as the suitability of the learning function WLF.

show abstract

An efficient method combining active learning Kriging and Monte Carlo simulation for profust failure probability

Cited by 30 publications

References 44 publications

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Advanced Reliability Analysis of Mechatronic Packagings coupling ANSYS^© and R

The adaptive weight learning function for reliability analysis and its application to multiple active learning methods

Contact Info

Product

Resources

About

An efficient method combining active learning Kriging and Monte Carlo simulation for profust failure probability

Cited by 30 publications

References 44 publications

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Prediction of compressive strength of fiber-reinforced polymers-confined cylindrical concrete using artificial intelligence methods

Advanced Reliability Analysis of Mechatronic Packagings coupling ANSYS© and R

The adaptive weight learning function for reliability analysis and its application to multiple active learning methods

Contact Info

Product

Resources

About

Advanced Reliability Analysis of Mechatronic Packagings coupling ANSYS^© and R