Faiq M. S. Al-Zwainy1*, Shakir A. Salih2, Mohammed R. Aldikheeli3 1 Department of Civil Engineering, Al-Nahrain University, Baghdad, Iraq
2 Department of Civil Engineering, University of Technology, Baghdad, Iraq
3 Department of Civil Engineering, Al-Kufa University, Baghdad, Iraq
Download Citation:
|
Download PDF
Self-consolidating concrete (SCC) is a very significant advance in concrete technology and became widely spread so it may be involuntary or accidently exposed to elevated temperature. Artificial intelligent techniques and especially artificial neural networks (ANNs) had proved its efficiency to solve complex systems such as concrete exposed to elevated temperature that are hard to model using usual modelling techniques such as mathematical modelling. The purpose of this study is to present an ANN model to predict the residual strength of sustainable (SCC) exposed to elevated temperature and to investigate which of the input variable has the most important impact on the model by conducting the sensitivity analysis. The results are indicated that the back propagation network with one hidden layer comprise two hidden nodes can be effectively used to predict the residual strength with R2, MAPE% and AA% found to be 96.73%, 12.82% and 87.18% respectively. By using Garson algorithm method, the results are showed that fly ash content has the highest relative importance index% (R.I.I) and it was 24.6%.ABSTRACT
Keywords:
Sustainable, Self-consolidating concrete (SCC), Artificial intelligent techniques, Artificial neural networks (ANNs), Sensitivity analysis.
Share this article with your colleagues
REFERENCES
ARTICLE INFORMATION
Received:
2018-04-13
Revised:
2020-11-10
Accepted:
2021-02-22
Available Online:
2021-06-01
Al-Zwainy, F.M.S., Salih, S.A., Aldikheeli, M.R. 2021. Prediction of residual strength of sustainable self-consolidating concrete exposed to elevated temperature using artificial intelligent technique, International Journal of Applied Science and Engineering, 18, 2018039. https://doi.org/10.6703/IJASE.202106_18(2).012
Cite this article:
Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.