• Advances in concrete construction
• /
• v.15 no.4
• /
• pp.251-267
• /
• 2023

In this paper, an experimental investigation is carried out to assess the inherent self-compacting properties of geopolymer mortar and its impact on flexural strength of thin-walled ferro-geopolymer box beam. The inherent self-compacting properties of the optimal mix of normal geopolymer mortar was studied and compared with self-compacting cement mortar. To assess the flexural strength of box beams, a total of 3 box beams of size 1500 mm × 200 mm × 150 mm consisting of one ferro-cement box beam having a wall thickness of 40 mm utilizing self-compacting cement mortar and two ferro-geopolymer box beams with geopolymer mortar by varying the wall thickness between 40 mm and 50 mm were moulded. The ferro-cement box beam was cured in water and ferro-geopolymer box beams were cured in heat chamber at 75℃ - 80℃ for 24 hours. After curing, the specimens are subjected to flexural testing by applying load at one-third points. The result shows that the ultimate load carrying capacity of ferro-geopolymer and ferro-cement box beams are almost equal. In addition, the stiffness of the ferro-geoploymer box beam is reduced by 18.50% when compared to ferro-cement box beam. Simultaneously, the ductility index and energy absorption capacity are increased by 88.24% and 30.15%, respectively. It is also observed that the load carrying capacity and stiffness of ferro-geopolymer box beams decreases when the wall thickness is increased. At the same time, the ductility and energy absorption capacity increased by 17.50% and 8.25%, respectively. Moreover, all of the examined beams displayed a shear failure pattern.

• Advances in concrete construction
• /
• v.6 no.4
• /
• 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
• /
• v.34 no.3
• /
• 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.