Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis
This study investigates the effects of varying steel fiber compositions on the workability, compressive strength, and tensile strength of steel fiber–reinforced concrete (SFRC). A total of 52 SFRC mixtures were prepared with different water-to-cement (w/c) ratios ranging from 0.30 to 0.60. The fiber...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Journal of Engineering |
| Online Access: | http://dx.doi.org/10.1155/je/5279864 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849254667139153920 |
|---|---|
| author | Teuku Ferdiansyah |
| author_facet | Teuku Ferdiansyah |
| author_sort | Teuku Ferdiansyah |
| collection | DOAJ |
| description | This study investigates the effects of varying steel fiber compositions on the workability, compressive strength, and tensile strength of steel fiber–reinforced concrete (SFRC). A total of 52 SFRC mixtures were prepared with different water-to-cement (w/c) ratios ranging from 0.30 to 0.60. The fiber volume fraction ranged from 0% to 1.5%, and the aspect ratio varied between 30 and 60. The results indicated that although the addition of steel fibers reduced workability and compressive strength, it significantly enhanced tensile strength, especially in mixtures with 1.5% fiber content and low w/c ratios. In terms of aspect ratio, a value of 50 generally resulted in the highest tensile strength across most mixtures. The study also compared the performance of three statistical regression techniques, namely, multiple linear regression, support vector machines, and fine tree regression, for predicting tensile strength. Among these methods, multiple linear regression showed the best performance by achieving a coefficient of determination (R2) of 0.910, a root mean square error (RMSE) of 0.203, a mean squared error (MSE) of 0.041, and a mean absolute error (MAE) of 0.156. These findings highlight the critical role of fiber composition in SFRC mix design and demonstrate the strong predictive capability of linear regression for estimating concrete tensile strength. |
| format | Article |
| id | doaj-art-a5c00a36e2ab4daca294bc9c2257505e |
| institution | Kabale University |
| issn | 2314-4912 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Engineering |
| spelling | doaj-art-a5c00a36e2ab4daca294bc9c2257505e2025-08-20T03:56:04ZengWileyJournal of Engineering2314-49122025-01-01202510.1155/je/5279864Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression AnalysisTeuku Ferdiansyah0Department of Civil EngineeringThis study investigates the effects of varying steel fiber compositions on the workability, compressive strength, and tensile strength of steel fiber–reinforced concrete (SFRC). A total of 52 SFRC mixtures were prepared with different water-to-cement (w/c) ratios ranging from 0.30 to 0.60. The fiber volume fraction ranged from 0% to 1.5%, and the aspect ratio varied between 30 and 60. The results indicated that although the addition of steel fibers reduced workability and compressive strength, it significantly enhanced tensile strength, especially in mixtures with 1.5% fiber content and low w/c ratios. In terms of aspect ratio, a value of 50 generally resulted in the highest tensile strength across most mixtures. The study also compared the performance of three statistical regression techniques, namely, multiple linear regression, support vector machines, and fine tree regression, for predicting tensile strength. Among these methods, multiple linear regression showed the best performance by achieving a coefficient of determination (R2) of 0.910, a root mean square error (RMSE) of 0.203, a mean squared error (MSE) of 0.041, and a mean absolute error (MAE) of 0.156. These findings highlight the critical role of fiber composition in SFRC mix design and demonstrate the strong predictive capability of linear regression for estimating concrete tensile strength.http://dx.doi.org/10.1155/je/5279864 |
| spellingShingle | Teuku Ferdiansyah Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis Journal of Engineering |
| title | Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis |
| title_full | Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis |
| title_fullStr | Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis |
| title_full_unstemmed | Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis |
| title_short | Predicting Tensile Strength in SFRC: Effects of Fiber Composition and Comparative Regression Analysis |
| title_sort | predicting tensile strength in sfrc effects of fiber composition and comparative regression analysis |
| url | http://dx.doi.org/10.1155/je/5279864 |
| work_keys_str_mv | AT teukuferdiansyah predictingtensilestrengthinsfrceffectsoffibercompositionandcomparativeregressionanalysis |