An adaptive local range sampling method for reliability-based design optimization using support vector machine and Kriging model

Liu, Xin; Wu, Yongge; Wang, Boxing; Ding, Jun; Jie, Haoxiang

doi:10.1007/s00158-016-1641-9

Cited by 36 publications

(16 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the reliability analysis of high temperature component, the LSF is usually implicit and high nonlinear, especially for complex subjects. The support vector machine, known as a supervised learning technique, is applicable to both classification and regression analysis in the field of machine learning . Least squares support vector machines (LS‐SVM) is one of the developed standard SVM and is cable of approximating the LSF with more excellent accuracy and smaller computational cost .…”

Section: Ls‐svm‐based Response Surface Methods For Fatigue Reliabilitymentioning

confidence: 99%

“…The support vector machine, known as a supervised learning technique, is applicable to both classification and regression analysis in the field of machine learning. 23,24 Least squares support vector machines (LS-SVM) is one of the developed standard SVM and is cable of approximating the LSF with more excellent accuracy and smaller computational cost. 25 Due to that, it has been widely used in engineering reliability analysis.…”

Section: An Adaptive Ls-svm-based Response Surface Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A general framework for fatigue reliability analysis of a high temperature component

Luo

Wang

et al. 2018

Quality & Reliability Eng

View full text Add to dashboard Cite

Fatigue reliability analysis for a high temperature component is a complex task due to the difficulties of doing experiments and uncertainties occurring in practical engineering. Researchers usually focus on the fatigue life scatter of standard specimens since the life data are easily available from fatigue tests. An alternative method is proposed in this paper which can replace the real tests of high temperature components with finite element (FE) simulation. A constitutive model coupled damage rule is utilized in this work to describe the cyclic stress‐strain response. Then, the FE simulations is incorporated into the general framework for reliability assessment. An adaptive least squares support vector machines with Latin hypercube sampling and learning function is employed to construct limit state function. To verify the accuracy and robustness of proposed method, a numerical example is utilized. In the end of this paper, a three‐layer structure extrusion container is applied for whole flowchart of fatigue reliability analysis.

show abstract

Section: Ls‐svm‐based Response Surface Methods For Fatigue Reliabilitymentioning

confidence: 99%

Section: An Adaptive Ls-svm-based Response Surface Methodsmentioning

confidence: 99%

A general framework for fatigue reliability analysis of a high temperature component

Luo

Wang

et al. 2018

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…Simulation can then be made using large samples with low computational effort, since it only requires evaluation of closed form polynomials. Finally, the accuracy of the expansions can be improved by increasing the (24) ∂b…”

Section: Sensitivity Analysismentioning

confidence: 99%

“…Also note that depending on the shape of g and its derivatives, more nodes may be necessary to obtain accurate results for integration of Eqs. (16) and (24).…”

Section: Appendix 1: Basis Functionsmentioning

confidence: 99%

“…For these reasons, computationally efficient methods for RO problems are scarce [15]. Some approaches employed to alleviate the computational burden of RBDO or RO with accurate reliabilty analysis are the use of metamodelling techniques [53] such as artificial neural networks [16], kriging [10], response surfaces [31], support vector machine [24], and polynomial chaos expansions (PCE) [39]. We also highlight the work by Gomes and Beck [15] that developed the design space root finding (DSRF) method for RO.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A gradient-based polynomial chaos approach for risk and reliability-based design optimization

Torii

López

Miguel

2017

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

This paper presents an approach for the solution of risk and reliability-based design optimization problems using gradient-based algorithms together with polynomial chaos expansions (PCE) for probability of failure evaluation and sensitivity analysis. The approach is intended to alleviate the computational burden required by such problems with accurate evaluation of probabilities of failure. Benchmark problems from the literature are solved to assess the effectiveness of the proposed approach and the results show that it is able to obtain accurate solutions with tractable computational effort. The main limitation of the proposed approach, inherited from the PCE, is that the computational effort grows very fast for an increasing number of random variables.

show abstract

Machine learning for combinatorial optimization of brace placement of steel frames

Tamura

Ohsaki

Takagi

2018

Japan Architectural Review

View full text Add to dashboard Cite

A method is presented for optimal placement of braces of plane frames using machine learning. The frame is subjected to static horizontal loads representing seismic loads. We consider the process of seismic retrofit by attaching braces. Therefore, the maximum value of additional stresses in the existing beams and columns and the maximum interstory drift angle are incorporated in the optimization problem. Characteristics of approximate optimal solutions and nonoptimal solutions are extracted using machine learning based on support vector machine and binary decision tree. Convolution and pooling are used for defining the features characterizing the solutions while reducing the number of variables. Optimization is carried out using a heuristic algorithm called simulated annealing based on local search. It is shown in the numerical examples that the computational cost is successfully reduced by avoiding costly structural analysis for a solution judged by machine learning as nonoptimal, and the important features in approximate optimal and nonoptimal solutions are identified.

show abstract

An adaptive local range sampling method for reliability-based design optimization using support vector machine and Kriging model

Cited by 36 publications

References 55 publications

A general framework for fatigue reliability analysis of a high temperature component

A general framework for fatigue reliability analysis of a high temperature component

A gradient-based polynomial chaos approach for risk and reliability-based design optimization

Machine learning for combinatorial optimization of brace placement of steel frames

Contact Info

Product

Resources

About