The study presents a comparative approach between response surface methodology (RSM) and hybridized, genetic algorithm artificial neural network (GA-ANN) in predicting the water absorption, compressive strength, flexural strength split tensile strength and slump for steel fiber reinforced concrete. The effect of process variables such as aspect ratio, water cement ratio and cement content were investigated using the central composite design of response surface methodology. This same experimental design was used in training the hybrid-training approach of artificial neural network. The predicting ability of both methodologies were compared using the root mean sqaured error (RMSE), mean absolute error (MAE), model predictive error (MPE) and absolute average deviation (AAD). The RSM model was found more accurate in prediction compared to hybrid GA-ANN.
Fibre-reinforced ferroconcrete is a new-generation type of concrete that has been found to have adequate performance. Global emissions of CO2 as a result of concrete production have damaged the earth's atmosphere. These emissions, together with construction waste, such as ceramic powder and aluminium waste, are considered one of the most harmful wastes to the environment, eventually leading to pollution. In this study, the fibre-reinforced ferroconcrete (FRFC) contained waste aluminium fibre, cement, ceramic waste powder, corrugated wire mesh, and fine and coarse aggregate. The cement content in the concrete mix was partially replaced with Ceramic Powder (CP) in proportions of 0%, 10%, and 20%, while the Aluminum Fibers (AF) were added in proportions 0, 1, and 2% to the concrete mix. The variation of ceramic powder and aluminium fibres was done using the central composite design of Response Surface Methodology (RSM) to create experimental design points meant to improve the fibre-reinforced ferroconcrete's mechanical performance. The results conclude that the mechanical performance of the FRFC was slightly improved more than conventional concrete, where at 20% replacement of ceramic powder and 1% addition of aluminium fibre to the concrete mix. There was more compressive, flexural, and split tensile strength increase than conventional concrete, with control concrete having strengths of 13.060, 5.720, and 3.110 N/mm2 and ferroconcrete 15.88, 6.68, and 3.83 N/mm2 respectively. This was further confirmed with microstructural images. The RSM model, with parameters such as; contour plots, analysis of variance, and optimisation, was used to effectively predict and optimise the responses of the ferroconcrete based on the independent variables (Aluminum fibre and Ceramic Powder) considered. The results of the predicted data show a straight-line linear progression as the coefficient of determination (R2) tends to 1, indicating that the RSM model is suitable for predicting the response of the variables on the FRFC. Doi: 10.28991/CEJ-2023-09-04-014 Full Text: PDF
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.