| 1. |
- Thomas, HS, et al.
(author)
-
- 2019
-
swepub:Mat__t
|
|
| 2. |
|
|
| 3. |
- Alyami, Mana, et al.
(author)
-
Estimating compressive strength of concrete containing rice husk ash using interpretable machine learning-based models
- 2024
-
In: Case Studies in Construction Materials. - : Elsevier. - 2214-5095. ; 20
-
Journal article (peer-reviewed)abstract
- The construction sector is a major contributor to global greenhouse gas emissions. Using recycled and waste materials in concrete is a practical solution to address environmental challenges. Currently, agricultural waste is widely used as a substitute for cement in the production of eco-friendly concrete. However, traditional methods for assessing the strength of such materials are both expensive and time-consuming. Therefore, this study uses machine learning techniques to develop prediction models for the compressive strength (CS) of rice husk ash (RHA) concrete. The ML techniques used in the present study include random forest (RF), light gradient boosting machine (LightGBM), ridge regression, and extreme gradient boosting (XGBoost). A total of 348 values of CS were collected from the experimental studies, and five characteristics of RHA concrete were taken as input variables. For the performance assessment of the models, multiple statistical metrics were used. During the training phase, the correlation coefficients (R) obtained for ridge regression, RF, XGBoost, and LightGBM were 0.943, 0.981, 0.985, and 0.996, respectively. In the testing set, the developed models demonstrated even higher performance, with correlation coefficients of 0.971, 0.993, 0.992, and 0.998 for ridge regression, RF, XGBoost, and LightGBM, respectively. The statistical analysis revealed that the LightGBM model outperformed other models, whereas the ridge regression model exhibited comparatively lower accuracy. SHapley Additive exPlanation (SHAP) method was employed for the interpretability of the developed model. The SHAP analysis revealed that water-to-cement is a controlling parameter in estimating the CS of RHA concrete. In conclusion, this study provides valuable guidance for builders and researchers to estimate the CS of RHA concrete. However, it is suggested that more input variables be incorporated and hybrid models utilized to further enhance the reliability and precision of the models.
|
|
| 4. |
- Alyami, Mana, et al.
(author)
-
Predictive modeling for compressive strength of 3D printed fiber-reinforced concrete using machine learning algorithms
- 2024
-
In: Case Studies in Construction Materials. - : Elsevier. - 2214-5095. ; 20
-
Journal article (peer-reviewed)abstract
- Three-dimensional (3D) printing in the construction industry is growing rapidly due to its inherent advantages, including intricate geometries, reduced waste, accelerated construction, cost-effectiveness, eco-friendliness, and improved safety. However, optimizing the mixture composition for 3D-printed concrete remains a formidable task, encompassing multiple variables and requiring a comprehensive trial-and-error experimentation process. Accordingly, this study used seven machine learning (ML) algorithms, including support vector regression (SVR), decision tree (DT), SVR-Bagging, SVR-Boosting, random forest (RF), gradient boosting (GB), and gene expression programming (GEP) for forecasting the compressive strength (CS) of 3D printed fiber-reinforced concrete (3DP-FRC). For model development, 299 data points were collected from experimental studies and split into two portions: 70% for model training and 30% for model validation. Various statistical metrics were employed to examine the accuracy and generalizability of the established models. The DT, RF, GB, and GEP models demonstrated higher accuracy in the validation set, achieving correlation (R) values of 0.987, 0.986, 0.986, and 0.98, respectively. The DT, RF, GB, and GEP models exhibited mean absolute error (MAE) scores of 4.644, 3.989, 3.90, and 5.691, respectively. Furthermore, the combination of SVR with boosting and bagging techniques slightly improved the accuracy compared to the individual SVR model. Additionally, the SHapley Additive exPlanations (SHAP) approach unveils the proportional significance of parameters in influencing the CS of 3DP-FRC. The SHAP technique revealed that water, silica fume, superplasticizer, sand content, and loading directions are the dominant parameters in estimating the CS of 3DP-FRC. The SHAP local interpretability unveils the intrinsic relationship between diverse input variables and their impacts on the strength of 3DP-FRC. The SHAP interpretability offers significant insights into the optimum mix proportion of 3DP-FRC.
|
|
