# Frontiers of Structural and Civil Engineering

 Front. Struct. Civ. Eng.    2018, Vol. 12 Issue (4) : 490-503     https://doi.org/10.1007/s11709-017-0445-3
 RESEARCH ARTICLE |
Predicting the strength properties of slurry infiltrated fibrous concrete using artificial neural network
T. Chandra Sekhara REDDY()
Civil Engineering, G.P.R. Engineering College, Kurnool 518002, Andhra Pradesh, India
 Download: PDF(1852 KB)   HTML Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
 Abstract This paper is aimed at adapting Artificial Neural Networks (ANN) to predict the strength properties of SIFCON containing different minerals admixture. The investigations were done on 84 SIFCON mixes, and specimens were cast and tested after 28 days curing. The obtained experimental data are trained using ANN which consists of 4 input parameters like Percentage of fiber (PF), Aspect Ratio (AR), Type of admixture (TA) and Percentage of admixture (PA). The corresponding output parameters are compressive strength, tensile strength and flexural strength. The predicted values obtained using ANN show a good correlation between the experimental data. The performance of the 4-14-3 architecture was better than other architectures. It is concluded that ANN is a highly powerful tool suitable for assessing the strength characteristics of SIFCON. Corresponding Authors: T. Chandra Sekhara REDDY Online First Date: 26 December 2017    Issue Date: 20 November 2018
 Cite this article: T. Chandra Sekhara REDDY. Predicting the strength properties of slurry infiltrated fibrous concrete using artificial neural network[J]. Front. Struct. Civ. Eng., 2018, 12(4): 490-503. URL: http://journal.hep.com.cn/fsce/EN/10.1007/s11709-017-0445-3 http://journal.hep.com.cn/fsce/EN/Y2018/V12/I4/490
 Fig.1  Methodology of development of the Artificial Neural Network (ANN) Tab.1  Part of the training parameters Tab.2  Part of the testing parameters Tab.3  Scaling factors for input parameters Tab.4  Scaling factors for output parameters Tab.5  Comparison between specifications of different architectures Fig.2  Architecture of neural network model Fig.3  (a) Relationship between actual and predicted for compressive strength; (b) Relationship between actual and predicted for tensile strength; (c) Relationship between actual and predicted for flexural strength Fig.4  (a) Relationship between actual and predicted for compressive strength; (b) Relationship between actual and predicted for tensile strength; (c) Relationship between actual and predicted for flexural strength Tab.6  Comparison of learning algorithms Tab.7  The MAPE and RMSE statistics of comparison Fig.5  (a) Learning progress of the network 4-14-3; (b) Testing progress of the network 4-14-3 Tab.8  Learning progress of the network 4-14-3 Fig.6  Learning for compressive strength Fig.7  Learning for tensile strength Fig.8  Learning for flexural strength Fig.9  Testing for compressive strength Fig.10  Testing for tensile strength Fig.11  Testing for flexural strength