Mohammad Iqbal Khan

In recent years, the field of construction engineering has experienced a significant paradigm shift, embracing the integration of machine learning (ML) methodologies, with a particular emphasis on forecasting the characteristics of steel-fiber-reinforced concrete (SFRC). Despite the theoretical sophistication of existing models, persistent challenges remain—their opacity, lack of transparency, and real-world relevance for practitioners. To address this gap and advance our current understanding, this study employs the extra gradient (XG) boosting algorithm, crafting a comprehensive approach. Grounded in a meticulously curated database drawn from 43 seminal publications, encompassing 420 distinct records, this research focuses predominantly on three primary fiber types: crimped, hooked, and mil-cut. Complemented by hands-on experimentation involving 20 diverse SFRC mixtures, this empirical campaign is further illuminated through the strategic use of partial dependence plots (PDPs), revealing intricate relationships between input parameters and consequent compressive strength. A pivotal revelation of this research lies in the identification of optimal SFRC formulations, offering tangible insights for real-world applications. The developed ML model stands out not only for its sophistication but also its tangible accuracy, evidenced by exemplary performance against independent datasets, boasting a commendable mean target-prediction ratio of 99%. To bridge the theory–practice gap, we introduce a user-friendly digital interface, thoroughly designed to guide professionals in optimizing and accurately predicting the compressive strength of SFRC. This research thus contributes to the construction and civil engineering sectors by enhancing predictive capabilities and refining mix designs, fostering innovation, and addressing the evolving needs of the industry.

A strain-hardening cementitious composite (SHCC) is a modern engineered material offering exceptional ductility and durability. A potential application of SHCCs for crack control and to improve structural members’ load-bearing capabilities is due to its superior properties. In this study, SHCCs were used to enhance the load-carrying capacity and the cracking behavior of precast RC beams. In the bottom tension region of RC beams, the SHCCs of different layer thicknesses (0%, 15%, 30%, and 45% of section height) were cast. Laboratory-scale beams were used in 4-point bending tests. SHCC-layered RC beams showed improved flexural performance compared to control RC beams. Among retrofitted beams, the one with an SHCC layer of 30% of the section height was found to be the most efficient pertaining to strength, ductility, and cracking control. In this study, the flexural response of composite beams was also predicted using an analytical approach. The average difference between predicted and measured moment capacities was less than 10%.

In the literature, there is little information available regarding the behavior of composite beams made up of reinforced concrete (RC) and ultra-ductile fiber-reinforced concrete (UDFRC). In this study, UDFRC was examined for its effectiveness in enhancing the strength of RC beams. With a tensile strength of 4.35 MPa and a strain capacity of 2.5%, PVA-based UDFRC was prepared. The performance of 12 medium-sized reinforced concrete (RC) beams was measured under four-point flexural loading. The beams measured 1800 mm long, 150 mm wide, and 200–260 mm deep. The experimental program on beam specimens was divided into two phases. In the first, four 150 × 200 × 1800 mm RC beams with UDFRC layer thicknesses of 0, 30, 60, and 90 mm were tested. Additionally, four concrete and four concrete–UDFRC beams were investigated, measuring 150 × 230 × 1800 mm and 150 × 260 × 1800 mm, respectively. The study focused on medium-sized, slender RC beams under quasi-static loads and room temperature with additional or substituted UDFRC layers. As a result of replacing concrete with UDFRC, the load-carrying capacity at first crack and steel yield significantly increased between 18.4 and 43.1%, but the ultimate load-carrying capacity increased only in the range of 6.3–10.8%. Furthermore, beams with additional UDFRC layers could carry 30–50% more load than their concrete counterparts. An RC-UDFRC beam had a load-carrying capacity 10–15% greater than that of a comparable RC beam. Generally, there is a lower deflection response in UDFRC–concrete composite RC beams than in control concrete beams. The UDFRC layering can potentially improve the load-carrying capacity of RC beams, at least when ductility provisions are considered.