A Manifold Learning Approach for Integrated Computational Materials Engineering

Abstract : Image-based simulation is becoming an appealing technique to homogenize properties of real microstructures of heterogeneous materials. However fast computation techniques are needed to take decisions in a limited timescale. Techniques based on standard computational homogenization are seriously compromised by the real-time constraint. The combination of model reduction techniques and high performance computing contribute to alleviate such a constraint but the amount of computation remains excessive in many cases. In this paper we consider an alternative route that makes use of techniques traditionally considered for machine learning purposes in order to extract the manifold in which data and fields can be interpolated accurately and in real-time and with minimum amount of online computation. Locallly Linear Embedding-LLE-is considered in this work for the real-time thermal homogenization of heterogeneous microstructures.
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02265692
Contributor : Mathias Legrand <>
Submitted on : Sunday, August 11, 2019 - 6:03:39 PM
Last modification on : Thursday, August 22, 2019 - 3:53:51 PM

File

LLE.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Collections

Citation

E. Lopez, D. Gonzalez, J. Aguado, E. Abisset-Chavanne, E. Cueto, et al.. A Manifold Learning Approach for Integrated Computational Materials Engineering. Archives of Computational Methods in Engineering, Springer Verlag, 2018, 25 (1), pp.59-68. ⟨10.1007/s11831-016-9172-5⟩. ⟨hal-02265692⟩

Share

Metrics

Record views

41

Files downloads

10