For sustainable development in the construction industry, blast furnace slag has been used as a substitute for cement in concrete. In contrast, steel-making slag, the second largest by-product in the steel industry, is mostly used as a filler material in embankment construction. This is because steel-making slag has relatively low hydraulicity and a problem with volumetric expansion. However, as the quenching process of slag has improved recently and the steel making process is specifically separated, the properties of steel-making slag has also improved. In this context, there is a need to find a method for recycling steel-making slag as a more highly valued material, such as its potential use as an admixture in concrete. Therefore, in order to confirm the possibility of using electric arc furnace (EAF) oxidizing slag as a binder, a comparative assessment of the mechanical properties of concrete containing electric arc furnace oxidizing slag, steel-making slag, and granulated blast furnace (GBF) slag was performed. The initial and final setting, shrinkage, compressive and split-cylinder tensile strength of the slag concretes were measured. It was found that replacing cement with EAF oxidizing slag delayed the hydration reaction at early ages, with no significant problems in setting time, shrinkage or strength development found.

A new hybrid intelligent model was developed for estimating the compressive strength (CS) of ground granulated blast furnace slag (GGBFS) concrete, and the synergistic benefits of the hybrid algorithm as compared with a single algorithm were verified. While using the collected 269 data from previous experimental studies, artificial neural network (ANN) models with three different learning algorithms namely back-propagation (BP), particle swarm optimization (PSO), and new hybrid PSO-BP algorithms, were constructed and the performance of the models was evaluated with regard to the prediction accuracy, efficiency, and stability through a threefold procedure. It was found that the PSO-BP neural network model was superior to the simple ANNs that were trained by a single algorithm and it is suitable for predicting the CS of GGBFS concrete.

Compressive strength is considered as one of the most important parameters in concrete design. Time and cost can be reduced if the compressive strength of concrete is accurately estimated. In this paper, a new prediction model for compressive strength of high-performance concrete (HPC) was developed using a non-tuned machine learning technique, namely, a regularized extreme learning machine (RELM). The RELM prediction model was developed using a comprehensive dataset obtained from previously published studies. The input variables of the model include cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age of specimens. k-fold cross-validation was used to assess the prediction reliability of the developed RELM model. The prediction results of the RELM model were evaluated using various error measures and compared with that of the standard extreme learning machine (ELM) and other methods presented in the literature. The findings of this research indicate that the compressive strength of HPC can be accurately estimated using the proposed RELM model.

Strain sensors can indicate the conditions of concrete structures, but these sensors are only capable of measuring local behaviors of materials. To solve this problem, researchers have introduced conductive materials that can monitor the overall behavior of concrete structures. Steelmaking slag, which contains large amounts of iron oxide (Fe₂O₃), is conductive, and researchers have considered the addition of this material to improve concrete monitoring. In this study, mechanical and electrical properties of concrete containing steelmaking slag as a binder were evaluated. As the incorporation of steelmaking slag increased, the setting times were delayed, but the compressive strengths were similar within the replacement ratio of 15%. It was found that the addition of steelmaking slag with Fe₂O₃, the main ingredient of magnetite (Fe₃O₄), improved the electrical resistivity, piezoresistivity, and sensitivity of the concrete. Drying of the concretes resulted in an increase in electrical resistance and fractional change in resistivity (FCR). Expansion of steelmaking slag, due to contacting of free CaO and moisture under repeated loads, resulted in cracks in the concrete and affected the gauge factor (GF). This study demonstrates the possibility that the addition of steelmaking slag as a binder may provide an economical and environmentally-friendly solution to concrete strain monitoring.

This study investigates the influence of steel slag (SS) and steel fibers on the electrical resistivity and electromagnetic (EM) shielding effectiveness of high-strength concrete (HSC). It was found that the electrical resistivity of mixtures were mainly influenced by free water. Thus, the EM shielding effectiveness was evaluated without the effect of free water. HSC with 20% replacement ratio of SS exhibited slightly improved EM shielding, lower electrical resistivity, and reduced strength (compressive and flexural) compared to HSC without SS. However, HSC with steel fibers exhibited significantly improved EM shielding, lower electrical resistivity, and higher strength and toughness compared to HSC without steel fibers. An increase in the steel fiber content in the HSC significantly decreased the electrical resistivity and increased the shielding effectiveness, strength, and toughness. Regardless of the fiber content in the fiber volume fraction of mixture, the shielding effectiveness is similar for cases with and without SS whose electrical resistivity values differ only slightly. This proves that the EM shielding effectiveness was mainly affected by the electrical resistivity and these properties are significantly correlated when the electrical resistivity values differ noticeably. HSC reinforced with rebar with 50 mm spacing exhibited a 23.5–75.6% increase in the shielding effectiveness in the 600–1,000 MHz frequency region compared to pristine HSC.