Optimizing compressive strength of foamed concrete using stepwise regression
Abstract Foamed concrete (FC) is distinguished by its unique properties and complex mixture design, which often necessitates extensive experimental trials to achieve target characteristics such as compressive strength (CS). Despite these challenges, numerical regression techniques have proven effect...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-06-01
|
| Series: | Discover Applied Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s42452-025-06966-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Foamed concrete (FC) is distinguished by its unique properties and complex mixture design, which often necessitates extensive experimental trials to achieve target characteristics such as compressive strength (CS). Despite these challenges, numerical regression techniques have proven effective in predicting concrete properties. This research introduces the stepwise regression (SR) model as a dependable technique for forecasting the CS of FC at 28 days. The data needed for training and testing was sourced from a trustworthy database. During model training, 75% of the experimental data was utilized, with the remainder used for model validation. The model’s robustness was confirmed through sensitivity and stability analyses performed on a simulated dataset. The accuracy of the model’s predictions for the CS of FC was evaluated using metrics such as the coefficient of determination (R2), mean absolute error (MAE), and root mean squared error (RMSE). The model achieved a high coefficient of determination (R2) of 97.59%, a low mean absolute error (MAE) of 1.45, and a low root mean squared error (RMSE) of 1.74. The study findings indicated that the proposed model demonstrated high precision in predicting the CS of FC. The prediction equation derived from the stepwise regression model emphasizes its significance and can be confidently utilized to predict the CS of FC. Graphical abstract |
|---|---|
| ISSN: | 3004-9261 |