ESTIMATING THE CONCRETE COMPRESSIVE STRENGTH USING ARTIFICIAL INTELLIGENCE: PROOF OF CONCEPT | ||||
Journal of Advanced Engineering Trends | ||||
Volume 43, Issue 1, January 2024, Page 291-299 PDF (1.01 MB) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/jaet.2022.144122.1201 | ||||
View on SCiNiTO | ||||
Authors | ||||
Ashraf Amin 1; Alaa Abouelezz2 | ||||
1Civil engineering department, faculty of engineering, Minia, Egypt | ||||
2Minia University | ||||
Abstract | ||||
Most structure members used nowadays and in the future contain concrete, so it is crucial to raise the accuracy of forecasting the concrete strength all time to make the best use of it. Concrete is a non-homogeneous material that consists of various materials, each one has its unique physical properties. Based on the contribution percentage for each component of the concrete mixture, we get a different concrete compressive strength for the produced concrete. Experimental mixtures in the lab is a traditional method to design the percentages of each concrete components based on approximate relationships to achieve the required compressive strength of the concrete. This method consumes much time and wasted materials used in the experiments. Using different artificial intelligence techniques to predict the concrete strength is considered fast, inexpensive, and more accurate, so this advanced technique is in continues development which may help us to solve many engineering problems in the future. In this paper, one of the artificial intelligence techniques is applied to predict the concrete behavior under the effect of changing the contribution of the components in the mixture. In addition, some recommendations for the range of inputs make the program optimize the results. New inputs can be taken into consideration like specifying new components' properties and their effect on the resulted strength of the concrete, demonstrating that artificial intelligence can be used to predict the concrete strength. | ||||
Keywords | ||||
Compressive strength; Predictive techniques; Artificial intelligence algorithms; Neural network | ||||
Supplementary Files
|
||||
Statistics Article View: 30 PDF Download: 37 |
||||