Please wait a minute...

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.

Keywords artificial neural networks      root mean square error      SIFCON      silica fume      metakaolin      steel fiber     
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
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
T. Chandra Sekhara REDDY
Fig.1  Methodology of development of the Artificial Neural Network (ANN)
INPUT OUTPUT
Sl No. % fibre Aspect ratio Mineral admixture %Mineral admixture Compressive strength (MPa) Tensile strength (MPa) Flexural strength (MPa)
1 6 40 1 0 46.44 8 18.6
2 8 40 1 0 48.02 8.6 22.6
3 12 40 1 0 51 9.82 31.82
4 6 50 1 0 48 9.28 21.2
5 8 50 1 0 49.4 9.75 25.37
6 10 50 1 0 50.98 12 30.6
7 12 50 1 0 52.86 12.6 34.58
8 6 60 1 0 51.56 10.8 24.1
9 8 60 1 0 53.03 11.6 29.26
10 10 60 1 0 54.35 12.41 37.28
11 6 40 2 10 51.6 8.91 21.2
12 8 40 2 10 54.2 10.21 25.31
13 12 40 2 10 59.08 12.36 37.18
14 6 50 2 10 54.95 9.85 22.6
15 8 50 2 10 57.8 10.75 27.9
16 12 50 2 10 64.32 13.32 42.56
17 6 60 2 10 62.6 11.2 25.8
18 8 60 2 10 65.3 12.45 33.25
19 12 60 2 10 76.93 14.7 46.55
20 6 40 3 10 51.39 8.98 24.04
21 8 40 3 10 55.98 10.6 28.03
22 10 40 3 10 59.55 11.94 33.35
23 6 50 3 10 55.9 10 25.27
24 8 50 3 10 59.3 10.95 31.82
25 10 50 3 10 62.82 12.45 40
26 12 50 3 10 66.4 13.9 45.2
27 6 60 3 10 63.1 11.2 28.03
28 8 60 3 10 67.66 12.74 37.24
29 10 60 3 10 73.07 13.88 46.6
30 12 60 3 10 78.2 15.2 50.64
31 8 40 1 20 52.88 9.96 24.76
32 10 40 1 20 54.22 11.21 29.33
33 12 40 1 20 56.88 12.46 36.26
34 8 50 1 20 55.55 10.72 27.2
35 10 50 1 20 57.77 11.74 35.06
36 12 50 1 20 61.77 12.99 41.6
37 6 60 1 20 60.44 10.89 24.66
38 8 60 1 20 63.11 12.17 32.53
39 10 60 3 20 69.33 13.27 40.13
40 6 40 3 20 51.11 8.86 23.33
41 10 40 3 20 58.22 11.46 32.4
42 12 40 3 20 61.33 12.56 38.93
43 6 50 3 20 54.22 9.68 24.66
44 8 50 3 20 57.77 10.81 30.93
45 10 50 3 20 61.23 12.2 39.06
46 12 50 3 20 64.88 13.58 44.86
47 6 60 3 20 61.33 11.06 26.93
48 8 60 3 20 65.77 12.45 36.13
49 10 60 3 20 71.11 13.72 44.8
50 10 40 1 30 49.77 9.99 26.4
51 12 40 1 30 52.88 11.21 33.6
52 6 50 1 30 49.77 8.86 20.34
53 8 50 1 30 51.11 9.65 25.2
54 10 50 1 30 53.77 10.78 32.4
55 12 50 1 30 57.77 11.96 38.4
56 6 60 1 30 56 10.04 22.66
57 10 60 1 30 64 12.2 37.2
58 12 60 1 30 68.44 13.23 42
59 6 40 2 30 47.11 8.05 21.6
60 8 40 2 30 50.22 8.61 25.06
61 10 40 2 30 53.33 10.55 30
62 12 40 2 30 56.44 11.54 36
63 6 50 2 30 50.22 8.9 22.66
64 8 50 2 30 52.88 9.93 28.8
65 10 50 2 30 56.44 11.18 35.86
66 6 60 2 30 56.44 10 24.93
67 8 60 2 30 59.55 11.43 33.46
68 10 60 2 30 64.88 12.59 41.87
Tab.1  Part of the training parameters
INPUTS OUTPUTS
Sl No. % fibre Aspect ratio Mineral admixture %Mineral admixture Compressive strength (MPa) Tensile strength (MPa) Flexural strength (MPa)
1 10 40 1 10 56.61 11.46 30.59
2 12 40 2 10 63.11 12.85 39.9
3 6 40 1 20 49.77 8.81 20.85
4 8 60 1 30 57.77 11.18 30
5 12 50 2 30 60 12.45 40.8
6 12 60 1 20 74.22 14.38 45.6
7 12 60 2 20 76 14.83 49.33
8 6 40 1 30 44.88 8.09 19.14
9 8 40 2 20 54.66 9.4 27.06
10 10 50 1 10 60.15 12.01 35.91
11 10 40 3 0 50.2 9.12 26.8
12 12 60 3 0 56 13.87 39.8
13 8 40 1 30 47.11 9.14 22.22
14 12 60 3 30 68.88 13.62 45.6
15 6 50 1 20 53.77 9.62 22.13
16 10 60 1 10 73.02 13.5 41.2
Tab.2  Part of the testing parameters
Node No. Input parameters Min. value Max. value Mean Scaling factor
1 Percentage of Fiber (PF) 6 12 8.8529 15
2 Aspect Ratio (AR) 40 60 50.1471 80
3 Type of Admixture (TA) 1 3 1.9265 10
4 Percentage of Admixture (PA) 0 30 16.9118 60
Tab.3  Scaling factors for input parameters
Node ?No. Output parameters Min. value (MPa) Max. value (MPa) Mean Scaling factor
1 Compressive Strength (F c) 44.88 78.20 57.8784 100
2 Tensile Strength (F t) 8.00 15.20 11.2197 20
3 Flexural Strength (F f) 18.60 50.64 31.375 80
Tab.4  Scaling factors for output parameters
Network Architecture AF for hidden layer AF for output layer CW R2
Compressive
strength
Tensile
strength
Flexural
strength
Training Testing Training Testing Training Testing
N1 4-5-3 tansig(n) purelin (n) 43 0.9952 0.9948 0.9939 0.9967 0.9910 0.9855
N2 4-6-3 tansig(n) purelin (n) 51 0.9963 0.9953 0.9942 0.9970 0.9916 0.9868
N3 4-7-3 tansig(n) purelin (n) 59 0.9969 0.9957 0.9947 0.9976 0.9920 0.9874
N4 4-8-3 tansig(n) purelin (n) 67 0.9975 0.9960 0.9952 0.9980 0.9927 0.9879
N5 4-9-3 tansig(n) purelin (n) 75 0.9984 0.9963 0.9969 0.9986 0.9934 0.9883
N6 4-10-3 tansig(n) purelin (n) 83 0.9973 0.9961 0.9975 0.9990 0.9939 0.9897
N7 4-11-3 tansig(n) purelin (n) 91 0.9982 0.9964 0.9982 0.9996 0.9942 0.9902
N8 4-12-3 tansig(n) purelin (n) 99 0.9986 0.9967 0.9988 0.9999 0.9946 0.9907
N9 4-13-3 tansig(n) purelin (n) 107 0.9990 0.9970 0.9991 0.99101 0.9950 0.9911
N10 4-14-3 tansig(n) purelin (n) 115 0.9992 0.9974 0.9996 0.99107 0.9958 0.9914
N11 4-15-3 tansig(n) purelin (n) 123 0.9991 0.9981 0.9998 0.99115 0.9961 0.9922
N12 4-5-5-3 tansig(n) purelin (n) 73 0.9987 0.9987 0.9994 0.99121 0.9969 0.9929
N13 4-5-6-3 tansig(n) purelin (n) 82 0.9996 0.9998 0.9997 0.99129 0.9974 0.9935
N14 4-5-7-3 tansig(n) purelin (n) 91 0.9981 0.9999 0.9992 0.99135 0.9980 0.9943
N15 4-5-8-3 tansig(n) purelin (n) 100 0.9979 0.9987 0.9987 0.99142 0.9989 0.9957
N16 4-6-5-3 tansig(n) purelin (n) 83 0.9960 0.9985 0.9984 0.99149 0.9991 0.9962
N17 4-6-6-3 tansig(n) purelin (n) 93 0.9955 0.9983 0.9982 0.99155 0.9994 0.9970
N18 4-6-7-3 tansig(n) purelin (n) 103 0.9954 0.9982 0.9980 0.99158 0.9998 0.9973
N19 4-6-8-3 tansig(n) purelin (n) 113 0.9951 0.9970 0.9978 0.99164 0.9989 0.9977
N20 4-7-5-3 tansig(n) purelin (n) 93 0.9956 0.9975 0.9974 0.99167 0.9984 0.9980
N21 4-7-6-3 tansig(n) purelin (n) 104 0.9980 0.9974 0.9960 0.99170 0.9980 0.9983
N22 4-7-7-3 tansig(n) purelin (n) 115 0.9989 0.9970 0.9962 0.99175 0.9978 0.9985
N23 4-7-8-3 tansig(n) purelin (n) 126 0.9991 0.9967 0.9964 0.99179 0.9975 0.9989
N24 4-8-5-3 tansig(n) purelin (n) 103 0.9993 0.9964 0.9960 0.99185 0.9970 0.9990
N25 4-8-6-3 tansig(n) purelin (n) 115 0.9998 0.9950 0.9958 0.99189 0.9968 0.9992
N26 4-8-7-3 tansig(n) purelin (n) 127 0.9997 0.9958 0.9955 0.99190 0.9965 0.9994
N27 4-8-8-3 tansig(n) purelin (n) 139 0.9992 0.9954 0.9955 0.99191 0.9963 0.9995
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
Algorithm Technique Number of iteration Time (s) Performance
Traincgf Powell conjugate gradient 127 24 0.0595
Trainscg Scaled conjugate gradient 159 45 0.0808
Trainrp Resilient back propagation 153 47 0.1037
Trainlm Levenberg – Marquardt 100 15 0.0023
Tab.6  Comparison of learning algorithms
R2 RMSE MAPE
Strength Properties Training Testing Training Testing Training Testing
Compressive Strength 0.9992 0.9974 0.285 0.703 0.2332 0.5144
Tensile Strength 0.9996 0.99107 0.0464 0.313 0.0348 0.1984
Flexural Strength 0.9958 0.9914 0.224 0.435 0.1798 0.2984
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
Sl. No. No. of epochs Mean square error (MSE)
1 100 0.00000962
2 300 0.00000841
3 500 0.00000784
4 1000 0.00000638
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
SIFCON
FRC
W/C
ANNs
RMSE
MSE
GP
PF
AR
TA
PA
Slurry Infiltrated Fibrous Concrete
Fiber Reinforced Concrete
Water-Cement
Artificial Neural Networks
Root Mean Square Error
Mean Square Error
Genetic Programming
Percentage of Fiber
Aspect Ratio
Type of Admixture
Percentage of Admixture
  
1 Lankard D R. Properties application slurry infiltrated fiber concrete (SIFCON). Concrete International, 1984, 6: 44–47
2 Tayfur G, Erdem T, Kırca Ö. Strength Prediction of High-Strength Concrete by Fuzzy Logic and Artificial Neural Networks. Journal of Materials in Civil Engineering, 2014, 26(11): 04014079
https://doi.org/10.1061/(ASCE)MT.1943-5533.0000985
3 Topçu I B, Saridemir M. Prediction of rubberized mortar properties using artificial neural network and fuzzy logic. Journal of Materials Processing Technology, 2008, 199(1-3): 108–118
https://doi.org/10.1016/j.jmatprotec.2007.08.042
4 Zhang X, Wang H, Wang D, Li C. Prediction of Concrete Strength based on Self organizing Fuzzy Neural Network. In: Proceeding of the 11th World Congress on Intelligent Control and Automation Shenyang, China, June-July, 2014
5 Abdalla A J, Hawileh R, Al-Tamimi A. Prediction of FRP-concrete ultimate bond strength using Artificial Neural Network. In: International Conference on Modeling, Simulation and Applied Optimization (ICMSAO), Kuala Lumpur, April, 2011
6 Amani J, Moeini R. Prediction of shear strength of reinforced concrete beams using adaptive neuro-fuzzy inference system and artificial neural network. Scientia Iranica, 2012, 19(2): 242–248
https://doi.org/10.1016/j.scient.2012.02.009
7 Ghaboussi J, Garrett J H Jr, Wu X. Knowledge-Based Modeling of Material Behavior with Neural Networks. Journal of Engineering Mechanics, 1991, 117(1): 132–153
https://doi.org/10.1061/(ASCE)0733-9399(1991)117:1(132)
8 Mukherjee A, Schemauder S, Ruhle M. Artificial neural network for the prediction of the mechanical behaviour of metal matrix composite. Acta Metallurgica et Materialia, 1995, 43(11): 4083–4091
https://doi.org/10.1016/0956-7151(95)00076-8
9 Chopra P, Sharma R K, Kumar M. Prediction of Compressive Strength of Concrete Using Artificial Neural Network and Genetic Programming. Advances in Materials Science and Engineering, 2016, (2): 1-10
10 Akkurt S, Tayfur G, Can S. Fuzzy logic model for the prediction of cement compressive strength. Cement and Concrete Research, 2004, 34(8): 1429–1433
https://doi.org/10.1016/j.cemconres.2004.01.020
11 Demir A. Prediction of Hybrid fibre-added concrete strength using artificial neural networks. Computers and Concrete, 2015, 15(4): 503–514
https://doi.org/10.12989/cac.2015.15.4.503
12 Hamdia K M, Lahmer T, Nguyen-Thoi T, Rabczuk T. Predicting the fracture toughness of PNCs: A stochastic approach based on ANN and ANFIS. Computational Materials Science, 2015, 102: 304–313
https://doi.org/10.1016/j.commatsci.2015.02.045
13 Bal L, Buyle-Bodin F. Artificial neural network for predicting drying shrinkage of concrete. Construction & Building Materials, 2013, 38: 248–254
https://doi.org/10.1016/j.conbuildmat.2012.08.043
14 Başyigit C, Akkurt I, Kilincarslan S, Beycioglu A. Prediction of compressive strength of heavyweight concrete by ANN and FL models. Neural Computation, 2010, 19(4): 507–513
https://doi.org/10.1007/s00521-009-0292-9
15 Dias W P S, Pooliyadda S P. Neural networks for predicting properties of concretes with admixtures. Construction & Building Materials, 2001, 15(7): 371–379
https://doi.org/10.1016/S0950-0618(01)00006-X
16 Adeli H. Neural networks in civil engineering: 1989-2000. Comput-Aided. Civ. Inf., 2001, 16: 126–142
17 Aiyer B G, Kim D, Karingattikkal N, Samui P, Rao P R.Prediction of Compressive Strength of Self- Compacting Concrete using Least Square Support Vector Machine and Relevance Vector Machine. KSCE Journal of Civil Engineering, 2014, 18(6): 1753–1758
https://doi.org/10.1007/s12205-014-0524-0
18 Boukhatem B, Kenai S, Hamou A T, Ziou D, Ghrici M. Predicting concrete properties using neural networks (NN) with principal component analysis (PCA) technique. Computers and Concrete, 2012, 10(6): 557–573
https://doi.org/10.12989/cac.2012.10.6.557
19 Alexandridis A, Triantis D, Stavrakas I, Stergiopoulos C. A neural network approach for compressive strength prediction in cement-based materials through the study of pressure-stimulated electrical signals. Construction & Building Materials, 2012, 30: 294–300
https://doi.org/10.1016/j.conbuildmat.2011.11.036
20 Muhammad K, Mohammad N, Rehman F. Modeling shotcrete mix design using artificial neural network. Computers and Concrete, 2015, 15(2): 167–181
https://doi.org/10.12989/cac.2015.15.2.167
21 Bilim C, Atis C D, Tanyildizi H, Karahan O. Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network. Advances in Engineering Software, 2009, 40(5): 334–340
https://doi.org/10.1016/j.advengsoft.2008.05.005
22 Erdem H. Prediction of the moment capacity of reinforced concrete slabs in fire using artificial neural networks. Advances in Engineering Software, 2010, 41(2): 270–276
https://doi.org/10.1016/j.advengsoft.2009.07.006
23 Erdal H I, Karakurt O, Namli E. High performance concrete compressive strength forecasting using ensemble models based on discrete wavelet transform. Engineering Applications of Artificial Intelligence, 2013, 26(4): 1246–1254
https://doi.org/10.1016/j.engappai.2012.10.014
24 Cheng M, Firdausi P M, Prayogo D. High-performance concrete compressive strength prediction using Genetic Weighted Pyramid Operation Tree (GWPOT). Engineering Applications of Artificial Intelligence, 2014, 29: 104–113
https://doi.org/10.1016/j.engappai.2013.11.014
25 Ghafari E, Bandarabadi M, Costa H, Júlio E. Prediction of Fresh and Hardened State Properties of UHPC: Comparative Study of Statistical Mixture Design and an Artificial Neural Network Model. Journal of Materials in Civil Engineering, 2015, 27(11): 04015017
https://doi.org/10.1061/(ASCE)MT.1943-5533.0001270
26 Gupta S. Using Artificial Neural Network to Predict the Compressive Strength of Concrete containing Nano-silica. Civil Engineering and Architecture, 2013, 1: 96–102
27 Hush D R, Horne B G. Progress in supervised Neural Network: What is New since Lippman. IEEE Signal Processing Magazine, 1993, 10: 8–39
https://doi.org/10.1109/79.180705
28 Najigivi A, Khaloo A. A. Iraji zad, and S.A. Rashid, An Artificial Neural Networks Model for Predicting Permeability Properties of Nano Silica–Rice Husk Ash Ternary Blended Concrete. IJCSM, 2013, 7: 225–238
29 Pham A, Hoang N, Nguyen Q. Predicting Compressive Strength of High-Performance Concrete Using Metaheuristic-Optimized Least Squares Support Vector Regression. Journal of Computing in Civil Engineering, 2016, 30(3): 06015002
https://doi.org/10.1061/(ASCE)CP.1943-5487.0000506
30 A.Sincero. Predicting Mixing Power Using Artificial Neural Network. In: Proceedings of World Water & Environmental Resources Congress, Philadelphia, Pennsylvania, United States, June, 2003
31 Słoński M. A comparison of model selection methods for compressive strength prediction of high performance concrete using neural networks. Computers & Structures, 2010, 88(21-22): 1248–1253
https://doi.org/10.1016/j.compstruc.2010.07.003
32 Sarıdemir M. Predicting the compressive strength of mortars containing metakaolin by artificial neural networks and fuzzy logic. Advances in Engineering Software, 2009, 40(9): 920–927
https://doi.org/10.1016/j.advengsoft.2008.12.008
33 Yeh I C. Analysis of Strength of Concrete Using Design of Experiments and Neural Networks. Journal of Materials in Civil Engineering, 2006, 18(4): 597–604
https://doi.org/10.1061/(ASCE)0899-1561(2006)18:4(597)
34 Yeh I C. Design of High-Performance Concrete Mixture Using Neural Networks and Nonlinear Programming. Journal of Computing in Civil Engineering, 1999, 13(1): 36–42
https://doi.org/10.1061/(ASCE)0887-3801(1999)13:1(36)
35 Hou T H, Su C H, Chang H Z. Using neural networks and immune algorithms to find the optimal parameters for an IC wire bonding process. Expert Systems with Applications, 2008, 34(1): 427–436
https://doi.org/10.1016/j.eswa.2006.09.024
36 Kostić S, Vasović D. Prediction model for compressive strength of basic concrete mixture using artificial neural networks. Neural Computing & Applications, 2015, 26(5): 1005–1024
https://doi.org/10.1007/s00521-014-1763-1
37 Lee S C. Prediction of concrete strength using artificial neural networks. Engineering Structures, 2003, 25(7): 849–857
https://doi.org/10.1016/S0141-0296(03)00004-X
38 Öztaş A, Pala M, Özbay E, Kanca E, Çagˇlar N, Bhatti M A. Predicting the compressive strength and slump of high strength concrete using neural network. Construction & Building Materials, 2006, 20(9): 769–775
https://doi.org/10.1016/j.conbuildmat.2005.01.054
39 Parichatprecha R, Nimityongskul P. Analysis of durability of high performance concrete using artificial neural networks. Construction & Building Materials, 2009, 23(2): 910–917
https://doi.org/10.1016/j.conbuildmat.2008.04.015
40 Morova N, Karahancer S, Terzi S, Serin S. Modeling Marshall Stability of Light Asphalt Concretes Fabricated using Expanded Clay Aggregate with Artificial Neural Networks. International Symposium on Innovations in Intelligent Systems and Applications, Turkey, 2012
41 Vu-Bac N, Lahmer T, Zhuang X, Rabczuk T. A software framework for probabilistic sensitivity analysis for computationally expensive models. Advances in Engineering Software, 2016, 100: 19–31
https://doi.org/10.1016/j.advengsoft.2016.06.005
Related articles from Frontiers Journals
[1] Osama Ahmed MOHAMED, Omar Fawwaz NAJM. Compressive strength and stability of sustainable self-consolidating concrete containing fly ash, silica fume, and GGBS[J]. Front. Struct. Civ. Eng., 2017, 11(4): 406-411.
[2] Sadegh REZAEI,Asskar Janalizadeh CHOOBBASTI. Liquefaction assessment using microtremor measurement, conventional method and artificial neural network (Case study: Babol, Iran)[J]. Front. Struct. Civ. Eng., 2014, 8(3): 292-307.
[3] Chujie JIAO, Wei SUN, Shi HUAN, Guoping JIANG. Behavior of steel fiber–reinforced high-strength concrete at medium strain rate[J]. Front Arch Civil Eng Chin, 2009, 3(2): 131-136.
[4] JIANG Jinyang, SUN Wei, ZHANG Yunsheng, CHEN Cuicui, WANG Jing. Cracking resistance performance of super vertical-distance pumped SFRC[J]. Front. Struct. Civ. Eng., 2008, 2(2): 179-183.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed