Comparative Analysis of Gradient‑Boosting Ensembles for Estimation of Compressive Strength of Quaternary Blend Concrete

Concrete compressive strength is usually determined 28 days after casting via crushing of samples. However, the design strength may not be achieved after this time-consuming and tedious process. While the use of machine learning (ML) and other computational intelligence methods have become increasin...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of concrete structures and materials Ročník 18; číslo 3; s. 523 - 546
Hlavní autori:	Mustapha, Ismail B., Abdulkareem, Muyideen, Jassam, Taha M., AlAteah, Ali H., Al-Sodani, Khaled A. Alawi, Al-Tholaia, Mohammed M. H., Nabus, Hatem, Alih, Sophia C., Abdulkareem, Zainab, Ganiyu, Abideen
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Singapore 한국콘크리트학회 01.12.2024 Springer Nature Singapore Springer Springer Nature B.V SpringerOpen
Predmet:	Blast furnace components Blast furnace slags Building Materials Comparative analysis Compressive strength Concrete Concrete properties Engineering Ensemble machine learning Fly ash Gradient-boosting algorithms Machine learning Mixtures Model testing Quaternary blend concrete Sensitivity analysis Solid Mechanics Statistical analysis Structural Materials Superplasticizers 토목공학 Malaysia Ensemble machine learning Compressive strength Gradient-boosting algorithms Quaternary blend concrete
ISSN:	1976-0485, 2234-1315, 2234-1315
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Concrete compressive strength is usually determined 28 days after casting via crushing of samples. However, the design strength may not be achieved after this time-consuming and tedious process. While the use of machine learning (ML) and other computational intelligence methods have become increasingly common in recent years, findings from pertinent literatures show that the gradient-boosting ensemble models mostly outperform comparative methods while also allowing interpretable model. Contrary to comparison with other model types that has dominated existing studies, this study centres on a comprehensive comparative analysis of the performance of four widely used gradient-boosting ensemble implementations [namely, gradient-boosting regressor, light gradient-boosting model (LightGBM), extreme gradient boosting (XGBoost), and CatBoost] for estimation of the compressive strength of quaternary blend concrete. Given components of cement, Blast Furnace Slag (GGBS), Fly Ash, water, superplasticizer, coarse aggregate, and fine aggregate in addition to the age of each concrete mixture as input features, the performance of each model based on R 2 , RMSE, MAPE and MAE across varying training–test ratios generally show a decreasing trend in model performance as test partition increases. Overall, the test results showed that CatBoost outperformed the other models with R 2 , RMSE, MAE and MAPE values of 0.9838, 2.0709, 1.5966 and 0.0629, respectively, with further statistical analysis showing the significance of these results. Although the age of each concrete mixture was found to be the most important input feature for all four boosting models, sensitivity analysis of each model shows that the compressive strength of the mixtures does increase significantly after 100 days. Finally, a comparison of the performance with results from different ML-based methods in pertinent literature further shows the superiority of CatBoost over reported the methods.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	1976-0485 2234-1315 2234-1315
DOI:	10.1186/s40069-023-00653-w