Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete
The development of nanotechnology has led to the creation of materials with unique properties, and in recent years, numerous attempts have been made to include nanoparticles in concrete in an effort to increase its performance and create concrete with improved qualities. Nanomaterials are typically...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Walter de Gruyter GmbH
2024
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/113396/ http://psasir.upm.edu.my/id/eprint/113396/1/113396.pdf |
| _version_ | 1848866211006251008 |
|---|---|
| author | Alghrairi, Nashat S. Aziz, Farah N. Rashid, Suraya A. Mohamed, Mohd Z. Ibrahim, M. |
| author_facet | Alghrairi, Nashat S. Aziz, Farah N. Rashid, Suraya A. Mohamed, Mohd Z. Ibrahim, M. |
| author_sort | Alghrairi, Nashat S. |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | The development of nanotechnology has led to the creation of materials with unique properties, and in recent years, numerous attempts have been made to include nanoparticles in concrete in an effort to increase its performance and create concrete with improved qualities. Nanomaterials are typically added to lightweight concrete (LWC) with the goal of improving the composite’s mechanical, microstructure, freshness, and durability qualities. Compressive strength is the most crucial mechanical characteristic for all varieties of concrete composites. For this reason, it is essential to create accurate models for estimating the compressive strength (CS) of LWC to save time, energy, and money. In addition, it provides useful information for planning the construction schedule and indicates when the formwork should be removed. To predict the CS of LWC mixtures made with or without nanomaterials, nine different models were proposed in this study: the gradient-boosted trees (GBT), random forest, tree ensemble, XGBoosted (XGB), Keras, simple regression, probabilistic neural networks, multilayer perceptron, and linear relationship model. A total of 2,568 samples were gathered and examined. The most significant factors influencing CS during the modeling process were taken into account as input variables, including the amount of nanomaterials, cement, water-to-binder ratio, density, the content of lightweight aggregates, type of nano, fine and coarse aggregate content, and water. The performance of the suggested models was assessed using a variety of statistical measures, including the coefficient of determination (R2), scatter index, mean absolute error, and root-mean-squared error (RMSE). The findings showed that, in comparison to other models, the GBT model outperformed the others in predicting the compression strength of LWC mixtures enhanced with nanomaterials. The GBT model produced the best results, with the greatest value of R2 (0.9) and the lowest value of RMSE (5.286). Furthermore, the sensitivity analysis showed that the most important factor influencing the prediction of the CS of LWC enhanced with nanoparticles is the water content. |
| first_indexed | 2025-11-15T14:16:59Z |
| format | Article |
| id | upm-113396 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:16:59Z |
| publishDate | 2024 |
| publisher | Walter de Gruyter GmbH |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1133962024-11-22T06:22:32Z http://psasir.upm.edu.my/id/eprint/113396/ Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete Alghrairi, Nashat S. Aziz, Farah N. Rashid, Suraya A. Mohamed, Mohd Z. Ibrahim, M. The development of nanotechnology has led to the creation of materials with unique properties, and in recent years, numerous attempts have been made to include nanoparticles in concrete in an effort to increase its performance and create concrete with improved qualities. Nanomaterials are typically added to lightweight concrete (LWC) with the goal of improving the composite’s mechanical, microstructure, freshness, and durability qualities. Compressive strength is the most crucial mechanical characteristic for all varieties of concrete composites. For this reason, it is essential to create accurate models for estimating the compressive strength (CS) of LWC to save time, energy, and money. In addition, it provides useful information for planning the construction schedule and indicates when the formwork should be removed. To predict the CS of LWC mixtures made with or without nanomaterials, nine different models were proposed in this study: the gradient-boosted trees (GBT), random forest, tree ensemble, XGBoosted (XGB), Keras, simple regression, probabilistic neural networks, multilayer perceptron, and linear relationship model. A total of 2,568 samples were gathered and examined. The most significant factors influencing CS during the modeling process were taken into account as input variables, including the amount of nanomaterials, cement, water-to-binder ratio, density, the content of lightweight aggregates, type of nano, fine and coarse aggregate content, and water. The performance of the suggested models was assessed using a variety of statistical measures, including the coefficient of determination (R2), scatter index, mean absolute error, and root-mean-squared error (RMSE). The findings showed that, in comparison to other models, the GBT model outperformed the others in predicting the compression strength of LWC mixtures enhanced with nanomaterials. The GBT model produced the best results, with the greatest value of R2 (0.9) and the lowest value of RMSE (5.286). Furthermore, the sensitivity analysis showed that the most important factor influencing the prediction of the CS of LWC enhanced with nanoparticles is the water content. Walter de Gruyter GmbH 2024 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/113396/1/113396.pdf Alghrairi, Nashat S. and Aziz, Farah N. and Rashid, Suraya A. and Mohamed, Mohd Z. and Ibrahim, M. (2024) Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete. Open Engineering, 14 (1). art. no. 20220604. pp. 1-27. ISSN 2391-5439; eISSN: 2391-5439 https://www.degruyter.com/document/doi/10.1515/eng-2022-0604/html 10.1515/eng-2022-0604 |
| spellingShingle | Alghrairi, Nashat S. Aziz, Farah N. Rashid, Suraya A. Mohamed, Mohd Z. Ibrahim, M. Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title | Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title_full | Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title_fullStr | Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title_full_unstemmed | Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title_short | Machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| title_sort | machine learning-based compressive strength estimation in nanomaterial-modified lightweight concrete |
| url | http://psasir.upm.edu.my/id/eprint/113396/ http://psasir.upm.edu.my/id/eprint/113396/ http://psasir.upm.edu.my/id/eprint/113396/ http://psasir.upm.edu.my/id/eprint/113396/1/113396.pdf |