Flexural Strength Prediction of Steel Fiber-Reinforced Concrete Using Artificial Intelligence

Dong Zheng; Rongxing Wu; Muhammad Sufian; Nabil Ben Kahla; Miniar Atig; Ahmed Farouk Deifalla; Oussama Accouche; Marc Azab

doi:10.3390/ma15155194

Flexural Strength Prediction of Steel Fiber-Reinforced Concrete Using Artificial Intelligence

Materials (Basel). 2022 Jul 27;15(15):5194. doi: 10.3390/ma15155194.

Authors

Dong Zheng¹, Rongxing Wu¹, Muhammad Sufian², Nabil Ben Kahla^{3

4}, Miniar Atig^{4

5}, Ahmed Farouk Deifalla⁶, Oussama Accouche⁷, Marc Azab⁷

Affiliations

¹ School of Architectural Engineering, Ningbo Polytechnic, Ningbo 315800, China.
² School of Civil Engineering, Southeast University, Nanjing 210096, China.
³ Department of Civil Engineering, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia.
⁴ Laboratory of Systems and Applied Mechanics, Tunisia Polytechnic School, University of Carthage, La Marsa, Tunis 2078, Tunisia.
⁵ Department of Civil Engineering, The Higher National Engineering School of Tunis, University of Tunis, Tunis, Tunisia.
⁶ Structural Engineering and Construction Management Department, Faculty of Engineering and Technology, Future University in Egypt, Cairo 11835, Egypt.
⁷ College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait.

Abstract

Research has focused on creating new methodologies such as supervised machine learning algorithms that can easily calculate the mechanical properties of fiber-reinforced concrete. This research aims to forecast the flexural strength (FS) of steel fiber-reinforced concrete (SFRC) using computational approaches essential for quick and cost-effective analysis. For this purpose, the SFRC flexural data were collected from literature reviews to create a database. Three ensembled models, i.e., Gradient Boosting (GB), Random Forest (RF), and Extreme Gradient Boosting (XGB) of machine learning techniques, were considered to predict the 28-day flexural strength of steel fiber-reinforced concrete. The efficiency of each method was assessed using the coefficient of determination (R²), statistical evaluation, and k-fold cross-validation. A sensitivity approach was also used to analyze the impact of factors on predicting results. The analysis showed that the GB and RF models performed well, and the XGB approach was in the acceptable range. Gradient Boosting showed the highest precision with an R² of 0.96, compared to Random Forest (RF) and Extreme Gradient Boosting (XGB), which had R² values of 0.94 and 0.86, respectively. Moreover, statistical and k-fold cross-validation studies confirmed that Gradient Boosting was the best performer, followed by Random Forest (RF), based on reduced error levels. The Extreme Gradient Boosting model performance was satisfactory. These ensemble machine learning algorithms can benefit the construction sector by providing fast and better analysis of material properties, especially for fiber-reinforced concrete.

Keywords: concrete; construction materials; flexural strength; mechanical characteristics; steel fiber; steel fiber-reinforced concrete.

Grants and funding

The Authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through the Large Groups Project under grant number RGP. 2/104/43.