SVR Based Modeling Method to Structures Finite Element Uncertainty Propagation Analysis

Yue Zhu; Si Hong Zhu

doi:10.4028/www.scientific.net/AMM.596.22

Paper Titles

Experimental Study on the Transverse Stiffness of WJ-8 Rail Fastening
p.3

Research on Modeling and Characteristics of Two-Stage Pressure Hydro-Pneumatic Spring
p.7

Study on the Mechanism of Detecting Flaws in the Transmission Tower Foundation by the Finite Element Method
p.12

Study on Torsion-Eliminating Performance of Laterally Interconnected Air Suspension
p.17

SVR Based Modeling Method to Structures Finite Element Uncertainty Propagation Analysis
p.22

Hopf Bifurcation Analysis of Digital Hydraulic Cylinder
p.27

Simulation on Kinetic Characteristics of Moving Mooring Marine Current Turbine System
p.32

Situation of Natural Gas Hydrate Research
p.39

Study on the Stainless Steel 1Cr18Ni9Ti Micro-Hole Drilling Experiment
p.43

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 596SVR Based Modeling Method to Structures Finite...

SVR Based Modeling Method to Structures Finite Element Uncertainty Propagation Analysis

Abstract:

Aiming at the uncertainty propagation analysis in modeling of FE model for structure, supported Vector Regression (SVR) method was presented to construct the implicit mapping between structure response and uncertainty parameters. The computational process of forward transfer of uncertainty parameters has been clarified. Three level testing criteria was used to evaluate extensively precision and generalization ability of RSM(Response Surface Modeling) based SVR. The super parameters in RSM were clarified through graded cross-validation. Uncertainty quantization analysis of GARTEUR model prove that the RSM based SVR has higher accuracy. Confidence level 95% finite element model was built because the confidence interval of nature frequency mean-value and variance were computed.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 596)

Pages:

22-26

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.596.22

Citation:

Cite this paper

Online since:

July 2014

Authors:

Yue Zhu*, Si Hong Zhu

Keywords:

GARTEUR Model Confidence Interval, Model Uncertainty Quantization Analysis, Model Validation, SVR

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Trucano T，Oberkampf W，Pilch M. V&V Principles and Challenges. SAND2006-6435C, (2006).

Google Scholar

[2] Oberkampf W L, Trucano T G. Verification and Validation in Computational Fluid Dynamics. SAND2002-0529, (2002).

DOI: 10.2172/793406

Google Scholar

[3] Oberkampf W L, Trucano T G, Hirsch C. Verification, Validation, and Predictive Capability in Computational Engineering and Physics. SAND2003-3769, (2003).

DOI: 10.2172/918370

Google Scholar

[4] Trucano T G, Pilch M, Oberkampf W L. General Concepts for Experimental Validation of ASCI Code Applications. SAND2002-0341, (2002).

DOI: 10.2172/800777

Google Scholar

[5] Guo Qintao．Structural dynamics finite element model validation studies several key problems [D]．Nanjing: nanjing university of aeronautics and astronautics, (2005).

Google Scholar

[6] VAPNIK V N．Statistical learning theory[M]．NewYork：Wiky，1998.

Google Scholar

[7] SUYKENS J A K，VANDEWAL I E J．Least squares support vector machines classifiers[J]. Neural Network Letters, 1999. 19(3): 293-300.

Google Scholar

[8] Balmes E．GARTEUR group on ground vibration testing，Results from the test of a single structure by 12 laboratories in Europe [A]．Proceedings of15th IMAC [C]．USA，1997．I346-1352.

Google Scholar