Library
local_library Home Repository

Microstructure-informed deep convolutional neural network for predicting short-term creep modulus of cement paste

Journal Article (2022)
Author(s)

M. Liang (TU Delft - Materials and Environment)

Yidong Gan (TU Delft - Materials and Environment)

Z. Chang (TU Delft - Materials and Environment)

Z. Wan (TU Delft - Materials and Environment)

H.E.J.G. Schlangen (TU Delft - Materials and Environment)

B Šavija (TU Delft - Materials and Environment)

Research Group
Materials and Environment
Copyright
© 2022 M. Liang, Y. Gan, Z. Chang, Z. Wan, E. Schlangen, B. Šavija
DOI related publication
https://doi.org/10.1016/j.cemconres.2021.106681
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 M. Liang, Y. Gan, Z. Chang, Z. Wan, E. Schlangen, B. Šavija
Research Group
Materials and Environment
Volume number
152
Pages (from-to)
1-17
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This study aims to provide an efficient alternative for predicting creep modulus of cement paste based on Deep Convolutional Neural Network (DCNN). First, a microscale lattice model for short-term creep is adopted to build a database that contains 18,920 samples. Then, 3 DCNNs with different consecutive convolutional layers are built to learn from the database. Finally, the performance of DCNNs is tested on unseen testing samples. The results show that the DCNNs can achieve high accuracy in the testing set, with the R2 all higher than 0.96. The distribution of creep modulus predicted by the DCNNs coincides with that of the original data. Furthermore, through analyzing the feature maps, it is found that the DCNNs can correctly capture the local importance of different microstructural phases. The DCNN allows therefore prediction of the creep modulus based on microstructural input, which saves computational resources of segmentation procedure and multiple incremental FEM calculations.