Novel approaches in prediction of tensile strain capacity of engineered cementitious composites using interpretable approaches

REVIEWS ON ADVANCED MATERIALS SCIENCE, Год журнала: 2025, Номер 64(1)

Опубликована: Янв. 1, 2025

Abstract The performance and durability of conventional concrete (CC) are significantly influenced by its weak tensile strength strain capacity (TSC). Thus, the intrusion fibers in cementitious matrix forms ductile engineered composites (ECCs) that can cater to this area CC. Moreover, ECCs have become a reasonable substitute for brittle plain due their increased flexibility, ductility, greater TSC. prediction ECC is crucial without need laborious experimental procedures. achieve this, machine learning approaches (MLAs), namely light gradient boosting (LGB) approach, extreme (XGB) artificial neural network (ANN), k -nearest neighbor (KNN), were developed. data gathered from literature comprise input parameters which fiber content, length, cement, diameter, water-to-binder ratio, fly ash (FA), age, sand, superplasticizer, TSC as output utilized. assessment models gauged with coefficient determination ( R 2 ), statistical measures, uncertainty analysis. In addition, an analysis feature importance carried out further refinement model. result demonstrates ANN XGB perform well train test sets > 0.96. Statistical measures show all give fewer errors higher , depict robust performance. Validation via K -fold confirms showing correlation determination. reveals FA major contribution ECC. graphical user interface also developed help users/researchers will facilitate them estimate practical applications.

Язык: Английский

---

Predicting the strengths of basalt fiber reinforced concrete mixed with fly ash using AML and Hoffman and Gardener techniques

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 9, 2025

Basalt fiber-reinforced concrete (BFRC) mixed with fly ash, combined advanced machine learning techniques, offers a practical, cost-effective, and less time-consuming alternative to traditional experimental methods. Conventional approaches evaluating mechanical properties, such as compressive splitting tensile strengths, typically require sophisticated equipment, meticulous sample preparation, extended testing periods. These methods demand substantial financial resources, specialized labor, considerable time for data collection analysis. The integration of provides transformative solution by enabling accurate prediction properties minimal data. from literature analysis were used 121 records collected experimentally tested basalt fiber reinforced samples measuring the strengths concrete. Eleven (11) critical factors have been considered constituents studied predict Fc-Compressive strength (MPa) Fsp-Splitting (MPa), which are output parameters. divided into training set (96 = 80%) validation (25 20%) following requirements partitioning sustainable application. Seven (7) selected techniques applied in prediction. Further, performance evaluation indices compare models' abilities lastly, Hoffman Gardener's technique was evaluate sensitivity parameters on strengths. At end exercise, results collated. In predicting (Fc), AdaBoost similarly excels, matching XGBoosting's R2 0.98 same MAE values. This shows effectiveness boosting predictive modeling estimation. For (Fsp), also outperforms most models, achieving an 0.96 phases. Its exceptionally low 0.124 MPa underscores its excellent generalization capabilities. Overall, XGBoosting consistently demonstrate superior both predictions, followed closely KNN. models benefit ensemble that efficiently handle non-linear patterns noise. SVR performs admirably, whereas GEP GMDHNN exhibit weaker capabilities due limitations handling complex dynamics. analysis, method proves instrumental identifying key drivers concrete, guiding informed decision-making material optimization construction practices.

Язык: Английский

---

Study on chloride penetration resistance of hybrid fiber-reinforced concrete in winter construction

Materials and Structures, Год журнала: 2024, Номер 58(1)

Опубликована: Дек. 26, 2024

Язык: Английский

---

Effect of Supplementary Cementitious Materials on the Mechanical and Physical Properties of Lightweight Concrete

E3S Web of Conferences, Год журнала: 2024, Номер 588, С. 03010 - 03010

Опубликована: Янв. 1, 2024

The effect of different amounts supplemental cementitious materials (SCMs) on the physical and mechanical characteristics lightweight concrete is examined in this study. SCMs include Fly Ash, Rice Husk Ash (RHA), Ground Granulated Blast-furnace Slag (GGBS), Silica Fume. Cube crushing strength, flexural density water absorption tests were performed eight mix proportions. current study also established that, when 20% was incorporated as a replacement, compressive strength 30 MPa 4 MPa, highest 32 4.2 however obtained Fume replacement. In present only small increment recorded for mixtures containing GGBS RHA while shown relatively less than control specimen. So, according to results are good additives since material becomes more stronger durable at same time has low density.

Язык: Английский

---