Skip to main content
Journal cover image

Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks

Publication ,  Journal Article
Wang, Y; Zhang, M; Lin, A; Iyer, A; Prasad, AS; Li, X; Zhang, Y; Schadler, LS; Chen, W; Brinson, LC
Published in: Molecular Systems Design and Engineering
June 1, 2020

Data-driven methods have attracted increasingly more attention in materials research since the advent of the material genome initiative. The combination of materials science with computer science, statistics, and data-driven methods aims to expediate materials research and applications and can utilize both new and archived research data. In this paper, we present a data driven and deep learning approach that builds a portion of the structure-property relationship for polymer nanocomposites. Analysis of archived experimental data motivates development of a computational model which allows demonstration of the approach and gives flexibility to sufficiently explore a wide range of structures. Taking advantage of microstructure reconstruction methods and finite element simulations, we first explore qualitative relationships between microstructure descriptors and mechanical properties, resulting in new findings regarding the interplay of interphase, volume fraction and dispersion. Then we present a novel deep learning approach that combines convolutional neural networks with multi-task learning for building quantitative correlations between microstructures and property values. The performance of the model is compared with other state-of-the-art strategies including two-point statistics and structure descriptor-based approaches. Lastly, the interpretation of the deep learning model is investigated to show that the model is able to capture physical understandings while learning.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Molecular Systems Design and Engineering

DOI

EISSN

2058-9689

Publication Date

June 1, 2020

Volume

5

Issue

5

Start / End Page

962 / 975

Related Subject Headings

  • 3403 Macromolecular and materials chemistry
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, Y., Zhang, M., Lin, A., Iyer, A., Prasad, A. S., Li, X., … Brinson, L. C. (2020). Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks. Molecular Systems Design and Engineering, 5(5), 962–975. https://doi.org/10.1039/d0me00020e
Wang, Y., M. Zhang, A. Lin, A. Iyer, A. S. Prasad, X. Li, Y. Zhang, L. S. Schadler, W. Chen, and L. C. Brinson. “Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks.” Molecular Systems Design and Engineering 5, no. 5 (June 1, 2020): 962–75. https://doi.org/10.1039/d0me00020e.
Wang Y, Zhang M, Lin A, Iyer A, Prasad AS, Li X, et al. Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks. Molecular Systems Design and Engineering. 2020 Jun 1;5(5):962–75.
Wang, Y., et al. “Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks.” Molecular Systems Design and Engineering, vol. 5, no. 5, June 2020, pp. 962–75. Scopus, doi:10.1039/d0me00020e.
Wang Y, Zhang M, Lin A, Iyer A, Prasad AS, Li X, Zhang Y, Schadler LS, Chen W, Brinson LC. Mining structure-property relationships in polymer nanocomposites using data driven finite element analysis and multi-task convolutional neural networks. Molecular Systems Design and Engineering. 2020 Jun 1;5(5):962–975.
Journal cover image

Published In

Molecular Systems Design and Engineering

DOI

EISSN

2058-9689

Publication Date

June 1, 2020

Volume

5

Issue

5

Start / End Page

962 / 975

Related Subject Headings

  • 3403 Macromolecular and materials chemistry