A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Estimating the compressive strength of plastic concrete samples using machine learning algorithms
Determining the mechanical properties of plastic concrete samples through experimental investigation is costly and time-consuming. This research used supervised machine learning (ML) techniques, including Decision Tree (DT), Random Forest (RF), Gradient Boost (GB), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and K-Nearest Neighborhood (KNN) for predicting the compressive strength of the plastic concrete samples considering different values of cement, water, water-to-cement ratio, bentonite, temperature, and sand. The models' performances are compared and evaluated using the correlation of coefficient (R2) score, Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). According to the results, the DT model was more effective in predicting with R2 = 0.87. In addition, a sensitivity analysis was carried out to determine each parameter's contribution level in implementing models using the RF algorithm. Consequently, it was shown that ML techniques are valuable tools for predicting the mechanical properties of plastic concrete in a more time and cost-effective way compared to laboratory tests.
Estimating the compressive strength of plastic concrete samples using machine learning algorithms
Determining the mechanical properties of plastic concrete samples through experimental investigation is costly and time-consuming. This research used supervised machine learning (ML) techniques, including Decision Tree (DT), Random Forest (RF), Gradient Boost (GB), Extreme Gradient Boost (XGBoost), Support Vector Machine (SVM), and K-Nearest Neighborhood (KNN) for predicting the compressive strength of the plastic concrete samples considering different values of cement, water, water-to-cement ratio, bentonite, temperature, and sand. The models' performances are compared and evaluated using the correlation of coefficient (R2) score, Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE). According to the results, the DT model was more effective in predicting with R2 = 0.87. In addition, a sensitivity analysis was carried out to determine each parameter's contribution level in implementing models using the RF algorithm. Consequently, it was shown that ML techniques are valuable tools for predicting the mechanical properties of plastic concrete in a more time and cost-effective way compared to laboratory tests.
Estimating the compressive strength of plastic concrete samples using machine learning algorithms
Asian J Civ Eng
Alishvandi, Ali (author) / Karimi, Javad (author) / Damari, Siavash (author) / Moayedi Far, Arsham (author) / Setodeh Pour, Mohammad (author) / Ahmadi, Morteza (author)
Asian Journal of Civil Engineering ; 25 ; 1503-1516
2024-02-01
14 pages
Article (Journal)
Electronic Resource
English
Estimating the compressive strength of plastic concrete samples using machine learning algorithms
| Springer Verlag | 2024