• Advances in concrete construction
• /
• 제6권4호
• /
• pp.323-344
• /
• 2018

The study herein reports the impact of Steel Fiber (SF) and Ground Granulated Blast Furnaces slag (GGBFS) content on the fresh and hardened properties of fly ash (FA) based Self-Compacting Geopolymer Concrete (SCGC). Two series of self-compacting geopolymer concrete (SCGC) were formulated with a constant binder content of $450kg/m^3$ and at an alkaline-to-binder (a/b) ratio of 0.50. Fly ash (FA) was substituted with GGBFS with the replacement levels being 0%, 25%, 50%, 75%, and 100% by weight in each SCGC series. Steel fiber (SF) wasn't employed in the assembly of the initial concrete series whereas, within the second concrete series, an SF combination was achieved by a constant additional level of 1% by volume. Fresh properties of mixtures were through an experiment investigated in terms of slump flow diameter, T50 slump flow time, V-funnel flow time, and L-box height ratio. Moreover, the mechanical performance of the SCGCs was evaluated in terms of compressive strength, splitting tensile strength, and fracture toughness. Furthermore, a statistical analysis was applied in order to judge the importance of the experimental parameters, like GGBFS and SF contents. The experimental results indicated that the incorporation of SF had no vital impact on the fresh characteristics of the SCGC mixtures whereas GGBFS aggravated them. However, the incorporation of GGBFS was considerably improved the mechanical properties of SCGCs. Moreover, the incorporation of SF with the total different quantity of GGBFS replacement has considerably increased the mechanical properties of SCGCs, by close to (65%) for the splitting strength and (200%) for compressive strength.

• Computers and Concrete
• /
• 제34권3호
• /
• pp.279-296
• /
• 2024

In this study, ensemble machine learning (ML) models are employed to estimate the hardened properties of Self-Compacting Geopolymer Concrete (SCGC). The input variables affecting model development include the content of the SCGC such as the binder material, the age of the specimen, and the ratio of alkaline solution. On the other hand, the output parameters examined includes compressive strength, flexural strength, and split tensile strength. The ensemble machine learning models are trained and validated using a database comprising 396 records compiled from 132 unique mix trials performed in the laboratory. Diverse machine learning techniques, notably K-nearest neighbours (KNN), Random Forest, and Extreme Gradient Boosting (XGBoost), have been employed to construct the models coupled with Bayesian optimisation (BO) for the purpose of hyperparameter tuning. Furthermore, the application of nested cross-validation has been employed in order to mitigate the risk of overfitting. The findings of this study reveal that the BO-XGBoost hybrid model confirms better predictive accuracy in comparison to other models. The R² values for compressive strength, flexural strength, and split tensile strength are 0.9974, 0.9978, and 0.9937, respectively. Additionally, the BO-XGBoost hybrid model exhibits the lowest RMSE values of 0.8712, 0.0773, and 0.0799 for compressive strength, flexural strength, and split tensile strength, respectively. Furthermore, a SHAP dependency analysis was conducted to ascertain the significance of each parameter. It is observed from this study that GGBS, Flyash, and the age of specimens exhibit a substantial level of influence when predicting the strengths of geopolymers.