Frontiers of Structural and Civil Engineering

 Front. Struct. Civ. Eng.    2019, Vol. 13 Issue (1) : 215-239     https://doi.org/10.1007/s11709-018-0489-z
 RESEARCH ARTICLE |
Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine
Ali Reza GHANIZADEH1(), Hakime ABBASLOU1, Amir Tavana AMLASHI1, Pourya ALIDOUST2
1. Department of Civil Engineering, Sirjan University of Technology, Sirjan, Iran
2. Department of Civil Engineering, Iran University of Science & Technology, Tehran, Iran
 Download: PDF(3704 KB)   HTML Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
 Abstract Plastic concrete is an engineering material, which is commonly used for construction of cut-off walls to prevent water seepage under the dam. This paper aims to explore two machine learning algorithms including artificial neural network (ANN) and support vector machine (SVM) to predict the compressive strength of bentonite/sepiolite plastic concretes. For this purpose, two unique sets of 72 data for compressive strength of bentonite and sepiolite plastic concrete samples (totally 144 data) were prepared by conducting an experimental study. The results confirm the ability of ANN and SVM models in prediction processes. Also, Sensitivity analysis of the best obtained model indicated that cement and silty clay have the maximum and minimum influences on the compressive strength, respectively. In addition, investigation of the effect of measurement error of input variables showed that change in the sand content (amount) and curing time will have the maximum and minimum effects on the output mean absolute percent error (MAPE) of model, respectively. Finally, the influence of different variables on the plastic concrete compressive strength values was evaluated by conducting parametric studies. Corresponding Authors: Ali Reza GHANIZADEH Online First Date: 01 June 2018    Issue Date: 04 January 2019
 Cite this article: Ali Reza GHANIZADEH,Hakime ABBASLOU,Amir Tavana AMLASHI, et al. Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine[J]. Front. Struct. Civ. Eng., 2019, 13(1): 215-239. URL: http://journal.hep.com.cn/fsce/EN/10.1007/s11709-018-0489-z http://journal.hep.com.cn/fsce/EN/Y2019/V13/I1/215
 Tab.1  Chemical analysis of cement Type II. Tab.2  Analyzed weight percentage of the chemical compounds of the understudy minerals based on the XRF analysis. Tab.3  Engineering properties of Bentonite and Sepiolite soils. Fig.1  (a) Bentonite, (b) Sepiolite. Fig.2  Details of Bentonite/Sepiolite plastic concrete mixes. Tab.4  Compressive strength test results of bentonite plastic concrete. Tab.5  Compressive strength test results of sepiolite plastic concrete. Fig.3  Summation and transfer function of a typical artificial neuron. Fig.4  A feed-forward back-propagation network architecture with one hidden layer Tab.6  Prepared database of Bentonite plastic concrete. Tab.7  Prepared database of Sepiolite plastic concrete. Tab.8  Statistical parameters of training, testing and validating datasets. Fig.5  Optimal architecture of ANN-B/S Fig.6  ANN-B/S model performance for training (a), testing (b) and validating (c) datasets. Fig.7  Comparison of experimental values with results of ANN-B/S model (training and testing) Fig.8  SVM-B/S model performance for training (a) and testing (b) and validating (c) datasets. Fig.9  Comparison of experimental values with results of SVM-B/S model (training and testing) Tab.9  Statistical parameters of developed models for training, testing and validating datasets. Tab.10  Statistical parameters values of built models in this study compared to empirical equations. Fig.10  Influence of each input parameter on the compressive strength of bentonite (a) and sepiolite (b) plastic concretes. Fig.11  Influence of measurement error of input parameters (change in input) on the output MAPE of bentonite and sepiolite plastic concretes. Fig.12  Variations of compressive strength of bentonite plastic concrete with different sand and gravel amount versus silty clay. Fig.13  Variations of compressive strength sepiolite plastic concrete with different sand and gravel amount versus silty clay. Fig.14  Variations of compressive strength of plastic concrete with different cement amount versus bentonite. Fig.15  Variations of compressive strength of plastic concrete with different cement amount versus sepiolite. Fig.16  Variations of compressive strength of plastic concrete with different cement and bentonite amount versus water. Fig.17  Variations of compressive strength of plastic concrete with different cement and sepiolite amount versus water. Fig.18  Variations of compressive strength of plastic concrete with different cement and bentonite amount versus curing time. Fig.19  Variations of compressive strength of plastic concrete with different cement and sepiolite amount versus curing time.