Home > Research > Publications & Outputs > Multi-objective optimization of engineered ceme...

Electronic data

Links

Text available via DOI:

View graph of relations

Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network. / Wang, Y.; Sun, J.; Wang, X. et al.
In: Journal of Building Engineering, Vol. 96, 110471, 01.11.2024.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Wang, Y., Sun, J., Wang, X., Li, S., Zhao, H., Huang, B., Cao, Y., & Saafi, M. (2024). Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network. Journal of Building Engineering, 96, Article 110471. https://doi.org/10.1016/j.jobe.2024.110471

Vancouver

Wang Y, Sun J, Wang X, Li S, Zhao H, Huang B et al. Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network. Journal of Building Engineering. 2024 Nov 1;96:110471. Epub 2024 Sept 6. doi: 10.1016/j.jobe.2024.110471

Author

Wang, Y. ; Sun, J. ; Wang, X. et al. / Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network. In: Journal of Building Engineering. 2024 ; Vol. 96.

Bibtex

@article{5ccb4786a6a54ee898f9dca6af8afda2,
title = "Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network",
abstract = "This study aims to establish a novel framework for mixture design optimization of engineered cementitious composite (ECC) by first collecting two original datasets of ECC's tensile stress and strain from the extensive and credible literature. The datasets comprise a wide range of variables including cementitious ingredients, 9 types of fiber and characteristics, admixtures, and experimental conditions. The data augmentation is then performed using a tuned constraints-modified Conditional Tabular Generative Adversarial Network (Tuned-CTGAN) to increase the model accuracy and generalizability. The fitness functions of tensile stress and strain are established based on four machine learning models with the hyperparameters tuned by the Hunger Games search (HGS) algorithm. After the data augmentation, the values of R2 in their test sets are increased from 0.874 to 0.925 and from 0.772 to 0.889, respectively. Subsequently, the third objective function (cost) is computed by polynomials and four classes of constraints (Min-max, volume, ratio, and fiber) are set up to define the variable's search space. A non-dominated sorting genetic algorithm based on reference-point strategy (NSGA-III) is introduced to optimize the mixture proportions of ECC by simultaneously optimizing tensile stress, tensile strain, and cost. This paper combines the results of data augmentation, model prediction, and multi-objective optimization for complex ECC design, which aims to provide a basis for practical application.",
author = "Y. Wang and J. Sun and X. Wang and S. Li and H. Zhao and B. Huang and Y. Cao and M. Saafi",
year = "2024",
month = nov,
day = "1",
doi = "10.1016/j.jobe.2024.110471",
language = "English",
volume = "96",
journal = "Journal of Building Engineering",
issn = "2352-7102",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Multi-objective optimization of engineered cementitious composite based on machine learning and generative adversarial network

AU - Wang, Y.

AU - Sun, J.

AU - Wang, X.

AU - Li, S.

AU - Zhao, H.

AU - Huang, B.

AU - Cao, Y.

AU - Saafi, M.

PY - 2024/11/1

Y1 - 2024/11/1

N2 - This study aims to establish a novel framework for mixture design optimization of engineered cementitious composite (ECC) by first collecting two original datasets of ECC's tensile stress and strain from the extensive and credible literature. The datasets comprise a wide range of variables including cementitious ingredients, 9 types of fiber and characteristics, admixtures, and experimental conditions. The data augmentation is then performed using a tuned constraints-modified Conditional Tabular Generative Adversarial Network (Tuned-CTGAN) to increase the model accuracy and generalizability. The fitness functions of tensile stress and strain are established based on four machine learning models with the hyperparameters tuned by the Hunger Games search (HGS) algorithm. After the data augmentation, the values of R2 in their test sets are increased from 0.874 to 0.925 and from 0.772 to 0.889, respectively. Subsequently, the third objective function (cost) is computed by polynomials and four classes of constraints (Min-max, volume, ratio, and fiber) are set up to define the variable's search space. A non-dominated sorting genetic algorithm based on reference-point strategy (NSGA-III) is introduced to optimize the mixture proportions of ECC by simultaneously optimizing tensile stress, tensile strain, and cost. This paper combines the results of data augmentation, model prediction, and multi-objective optimization for complex ECC design, which aims to provide a basis for practical application.

AB - This study aims to establish a novel framework for mixture design optimization of engineered cementitious composite (ECC) by first collecting two original datasets of ECC's tensile stress and strain from the extensive and credible literature. The datasets comprise a wide range of variables including cementitious ingredients, 9 types of fiber and characteristics, admixtures, and experimental conditions. The data augmentation is then performed using a tuned constraints-modified Conditional Tabular Generative Adversarial Network (Tuned-CTGAN) to increase the model accuracy and generalizability. The fitness functions of tensile stress and strain are established based on four machine learning models with the hyperparameters tuned by the Hunger Games search (HGS) algorithm. After the data augmentation, the values of R2 in their test sets are increased from 0.874 to 0.925 and from 0.772 to 0.889, respectively. Subsequently, the third objective function (cost) is computed by polynomials and four classes of constraints (Min-max, volume, ratio, and fiber) are set up to define the variable's search space. A non-dominated sorting genetic algorithm based on reference-point strategy (NSGA-III) is introduced to optimize the mixture proportions of ECC by simultaneously optimizing tensile stress, tensile strain, and cost. This paper combines the results of data augmentation, model prediction, and multi-objective optimization for complex ECC design, which aims to provide a basis for practical application.

U2 - 10.1016/j.jobe.2024.110471

DO - 10.1016/j.jobe.2024.110471

M3 - Journal article

VL - 96

JO - Journal of Building Engineering

JF - Journal of Building Engineering

SN - 2352-7102

M1 - 110471

ER -