Obálka

Comparison of manifold learning algorithms used in FSI data interpolation of curved surfaces

Uloženo v:
Vydáno v:Multidiscipline Modeling in Materials and Structures vol. 13, no. 2 (2017), p. 217-261
Hlavní autor: Liu, Ming-min
Další autoři: Li, LZ, Zhang, Jun
Vydáno:
Emerald Group Publishing Limited
Témata:
Principal components analysis
Partial differential equations
Fluid-structure interaction
Fault diagnosis
Algorithms
Interpolation
Neural networks
Planes
Information processing
Manifolds (mathematics)
Data transmission
Engineering
Methods
Machine learning
Stress concentration
Mathematical problems
Learning algorithms
Computer simulation
On-line přístup:Citation/Abstract
Full Text
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstrakt:Purpose The purpose of this paper is to discuss a data interpolation method of curved surfaces from the point of dimension reduction and manifold learning. Design/methodology/approach Instead of transmitting data of curved surfaces in 3D space directly, the method transmits data by unfolding 3D curved surfaces into 2D planes by manifold learning algorithms. The similarity between surface unfolding and manifold learning is discussed. Projection ability of several manifold learning algorithms is investigated to unfold curved surface. The algorithms' efficiency and their influences on the accuracy of data transmission are investigated by three examples. Findings It is found that the data interpolations using manifold learning algorithms LLE, HLLE and LTSA are efficient and accurate. Originality/value The method can improve the accuracies of coupling data interpolation and fluid-structure interaction simulation involving curved surfaces.
ISSN:1573-6105
1573-6113
DOI:10.1108/MMMS-07-2016-0032
Zdroj:Materials Science Database