Predicting Ultra-High-Performance Concrete Compressive Strength Using Tabular Generative Adversarial Networks

Abstract

There have been abundant experimental studies exploring ultra-high-performance concrete (UHPC) in recent years. However, the relationships between the engineering properties of UHPC and its mixture composition are highly nonlinear and difficult to delineate using traditional statistical methods. There is a need for robust and advanced methods that can streamline the diverse pertinent experimental data available to create predictive tools with superior accuracy and provide insight into its nonlinear materials science aspects. Machine learning is a powerful tool that can unravel underlying patterns in complex data. Accordingly, this study endeavors to employ state-of-the-art machine learning techniques to predict the compressive strength of UHPC using a comprehensive experimental database retrieved from the open literature consisting of 810 test observations and 15 input features. A novel approach based on tabular generative adversarial networks was used to generate 6513 plausible synthetic data for training robust machine learning models, including random forest, extra trees, and gradient boosting regression. While the models were trained using the synthetic data, their ability to generalize their predictions was tested on the 810 experimental data thus far unknown and never presented to the models. The results indicate that the developed models achieved outstanding predictive performance. Parametric studies using the models were able to provide insight into the strength development mechanisms of UHPC and the significance of the various influential parameters.

Modeling the Tensile Behavior of Fiber-Reinforced Strain-Hardening Cement-Based Composites: A Review

“…However, it is worth mentioning that there are other ternative methodologies for predicting the mechanical behavior of SHCC, namely, mu The mentioned approaches have the appeal of using the micro-and mesomechanisms observed experimentally. However, it is worth mentioning that there are other alternative methodologies for predicting the mechanical behavior of SHCC, namely, multiphase modeling, in which the fibers are simulated discreetly and immersed in the cementitious matrix (Bitencourt Jr et al, 2019 [20], Qsymah, 2016 [21]; Cunha, Barros and Sena-Cruz, 2011 [22]); inverse analysis, in which the stress-strain relationship of the material is obtained by inverse analysis techniques based on experimental responses (Kang et al, 2010 [80]; Baby et al, 2013 [81], Stephen et al, 2019 [82]); use of different types of machine learning such as artificial neural network (ANN), support vector regression (SVR), classification and regression tree (CART), and gradient boosting tree (GBoost) (Guo et al, 2021 [83]; Abellán-García and Guzmán-Guzmán, 2021 [84], Marani, Jamali, Nehdi, 2020 [85]); and techniques based on the theory of homogenization with the development of multiscale models (Yu et al, 2020 [86]).…”

Model-Based Adaptive Machine Learning Approach in Concrete Mix Design

“…In 2020, Marani A. et al [ 42 ] presented a solution to predict the compressive strength of ultra-high-performance concrete using a machine learning algorithm. They trained their algorithm on a database of 810 samples gathered from open-access sources.…”

The Time-Dependent Effect in Ultra High-Performance Concrete According to the Curing Methods

“…Research has been continuously conducted to predict the strength of UHPC. Marani et al (2020) investigated a novel framework for predicting the compressive strength of UHPC using a tabular generative adversarial net model with 810 experimental data points from the literature [ 1 ]. Zhang et al (2017), Abuodeh et al (2020), and Nguten et al (2022) suggested an artificial neural network (ANN) model to predict the compressive strength of the UHPC [ 2 , 3 , 4 ].…”