Modeling the compressive strength of eco-friendly self-compacting concrete incorporating ground granulated blast furnace slag using soft computing techniques

• Published in: Environmental science and pollution research international Vol. 29; no. 47; pp. 71338 - 71357
• Main Authors: Faraj, Rabar H., Mohammed, Azad A., Omer, Khalid M.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2022; Springer Nature B.V
• Subjects: Aquatic Pollution; Artificial neural networks; Ashes; Atmospheric Protection/Air Quality Control/Air Pollution; Blast furnace practice; Byproducts; Carbon dioxide; Carbon dioxide emissions; Cement; Climate change; Compressive strength; Concrete; Concrete industry; Earth and Environmental Science; Ecotoxicology; Emissions; Energy conservation; Environment; Environmental Chemistry; Environmental Health; Environmental science; Formwork; GGBS; Global climate; Global warming; Granulation; Mathematical models; Mixtures; Neural networks; Project engineering; Research Article; Root-mean-square errors; Self-compacting concrete; Slag; Soft computing; Statistical analysis; Sustainable production; Waste Water Technology; Water Management; Water Pollution Control; Self-compacting concrete; Curing time; Sensitivity; Compressive strength; Modeling; Ground granulated blast furnace slag
• ISSN: 0944-1344; 1614-7499
• DOI: 10.1007/s11356-022-20889-5

Concern regarding global climate change and its detrimental effects on society demands the building sector, one of the major contributors to global warming. Reducing cement usage is a significant challenge for the concrete industry; achieving this objective can help reduce global carbon dioxide emissions. Replacing the cement in concrete with by-product ashes is a promising approach for reducing the embodied carbon in concrete and improving some of its properties. Among different by-product ashes, ground granulated blast furnace slag (GGBFS) is a viable option to produce sustainable self-compacting concrete (SCC). Compressive strength (CS), on the other hand, is an essential characteristic among other evaluated properties. As a result, establishing trustworthy models to forecast the CS of SCC is critical to saving cost, time, and energy. Furthermore, it provides helpful instruction for planning building projects and determining the best time to remove the formwork. In this study, four alternative models were suggested to predict the CS of SCC mixes produced by GGBFS: the artificial neural network (ANN), nonlinear model (NLR), linear relationship model (LR), and multi-logistic model (MLR). To do so, an extensive set of data consisting of about 200 mixtures were extracted and analyzed to develop the models, and various mixture proportions and curing times were considered input variables. To test the effectiveness of the suggested models, several statistical evaluations including determination coefficient ( R 2 ), mean absolute error (MAE), scatter index (SI), root mean squared error (RMSE), and objective (OBJ) value were utilized. In comparison to other models, the ANN model performed better to forecast the CS of SCC mixes incorporating GGBFS. The RMSE, MAE, OBJ, and R 2 values for this model were 4.73 MPa, 2.3 MPa, 3.4 MPa, and 0.955, respectively.