Please wait a minute...

Frontiers of Structural and Civil Engineering

Front. Struct. Civ. Eng.    2019, Vol. 13 Issue (4) : 926-936
Estimating moment capacity of ferrocement members using self-evolving network
Abdussamad ISMAIL()
Department of Civil Engineering, Bayero University Kano, Kano State, PMB 3011, Nigeria
Download: PDF(1113 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

In this paper, an empirical model based on self-evolving neural network is proposed for predicting the flexural behavior of ferrocement elements. The model is meant to serve as a simple but reliable tool for estimating the moment capacity of ferrocement members. The proposed model is trained and validated using experimental data obtained from the literature. The data consists of information regarding flexural tests on ferrocement specimens which include moment capacity and cross-sectional dimensions of specimens, concrete cube compressive strength, tensile strength and volume fraction of wire mesh. Comparisons of predictions of the proposed models with experimental data indicated that the models are capable of accurately estimating the moment capacity of ferrocement members. The proposed models also make better predictions compared to methods such as the plastic analysis method and the mechanism approach. Further comparisons with other data mining techniques including the back-propagation network, the adaptive spline, and the Kriging regression models indicated that the proposed models are superior in terms prediction accuracy despite being much simpler models. The performance of the proposed models was also found to be comparable to the GEP-based surrogate model.

Keywords ferrocement      moment capacity      self-evolving neural network     
Corresponding Authors: Abdussamad ISMAIL   
Just Accepted Date: 24 April 2019   Online First Date: 30 May 2019    Issue Date: 10 July 2019
 Cite this article:   
Abdussamad ISMAIL. Estimating moment capacity of ferrocement members using self-evolving network[J]. Front. Struct. Civ. Eng., 2019, 13(4): 926-936.
E-mail this article
E-mail Alert
Articles by authors
Abdussamad ISMAIL
Fig.1  Section of a ferrocement member
Fig.2  Topology of a Self-evolving Network
Fig.3  SEANN training flow diagram
parameter µ s xmax xmin
Mu 819.79 1054.08 5393 33
b 150.8 91.03 400 76
h 42.92 22.24 100 13
vf 2.43 1.8032 8.25 0.16
fcu 39.95 13.18 62 12.6
fu 543.1 140.26 979 371
Tab.1  Database summary
Fig.4  Comparison of SEANN-I prediction with experimental data (a) SEANN- I predictions versus training data (b) SEANN-I predictions versus testing data
Fig.5  Comparison of SEANN-II prediction with experimental data (a) SEANN-II predictions versus training data (b) SEANN-II predictions versus testing data
Fig.6  Values of β versus testing data (a) SEANN-I predictions (b) SEANN-II predictions
model approximated function No. of parameters
SEANN-I Eq. (5) 9
SEANN-II Eq. (6) 4
Spline-I (linear) Eq. (5) 16
Spline-II (linear) Eq. (6) 7
Spline-I (cubic) Eq. (5) 10
Spline-II (cubic) Eq. (6) 6
Kriging-I Eq. (5) 220
Kriging-II Eq. (6) 112
Tab.2  Brief descriptions of SEANN, spline and Kriging models
Fig.7  N-RMSE values for SEANN, spline and Kriging models
model No. of parameters N–RMSE (testing) R2 (testing)
SEANN-I 9 0.1688 0.9032
SEANN-II 4 0.1485 0.9190
BP-ANN 39 0.3270 0.7880
GEP 3 0.1849 0.8812
plastic analysis - 0.2414 0.8610
mechanism approach - 0.3981 0.8160
parabolic formula - 0.4953 0.8147
Tab.3  Comparison of results
Fig.8  Performance comparison various methods of predicting moment capacity
Fig.9  Variation of normalized moment capacity with (a) α; (b) vf
Fig.10  Variation of normalized moment capacity with α for various vf values (compared with testing data)
Fig.11  Results of sensitivity analysis
1 M A Mashrei, N Abdulrazzaq, T Y Abdalla, M S Rahman. Neural networks model and adaptive neuro-fuzzy inference system for predicting the moment capacity of ferrocement members. Engineering Structures, 2010, 32(6): 1723–1734
2 A H Gandomi, D A Roke, K Sett. Genetic programming for moment capacity modeling of ferrocement members. Engineering Structures, 2013, 57: 169–176
3 M A Mansur, P Paramasivam. Cracking behavior and ultimate strength of ferrocement in flexure. Journal of Ferrocement, 1986, 16(4): 405–415
4 P Paramasivam, R S Ravindrajah. Effect of arrangements of reinforcements on mechanical properties of ferrocement. ACI Structural Journal, 1988, 85(1): 3–11
5 A E Naaman, J R Homeric. Flexural design of ferrocement computerized evaluation and design aids. Journal of Ferrocement, 1986, 16(2): 101–116
6 B Gaspar, A P Teixeira, C G Soares. Assessment of the efficiency of kriging surrogate models for structural reliability analysis. Probabilistic Engineering Mechanics, 2014, 37: 24–34
7 N Vu-Bac, T Lahmer, Y Zhang, X Zhuang, T Rabczuk. Stochastic predictions of interfacial characteristic of polymeric nanocomposites (pncs). Composites. Part B, Engineering, 2014, 59: 80–95
8 N Vu-Bac, M Silani, T Lahmer, X Zhuang, T Rabczuk. A unified framework for stochastic predictions of mechanical properties of polymeric nanocomposites. Computational Materials Science, 2015, 96: 520–535
9 N Vu-Bac, T Lahmer, X Zhuang, T Nguyen-Thoi, T Rabczuk. A software framework for probabilistic sensitivity analysis for computationally expensive models. Advances in Engineering Software, 2016, 100: 19–31
10 F J Matinez-Garcia, J A Moreno-Perez. Jumping Frogs Optimization: A New Swarm Method for Discrete Optimization. Technical Report DEIOC 3/2008, Department of Statistics, O.R. and Computing, University of La Laguna, Tenerife, Spain, 2008
11 R Durbin, R Rumelhart. Product units: A computationally powerful and biologically plausible extension to backpropagation networks. Neural Computation, 1989, 1(1): 133–142
12 P Paramasivam, M S Mansur, K C Ong. Flexural behavior of light weight ferrocement slabs. Journal of Ferrocement, 1985, 15(1): 25–33
13 M A Mansur. Ultimate strength design of ferrocement in flexure. Journal of Ferrocement, 1988, 18(4): 385–395
14 D Logan, S P Shah. Moment capacity and cracking behavior of ferrocement in flexure. ACI J, 1973, 70(12): 799–804
15 P Desayi, V Reddy. Strength of lightweight ferrocement in flexure. J Cement Concr Composites, 1991, 13: 13–20
16 Y Jin, T Okabe, B Sendhoff. Neural network regularization and ensembling using multi-objective evolutionary algorithms. Congress on Evolutionary Computation (CEC04), IEEE, 2004
17 R D Reed, R J Marks. Neural Smithing. The MIT Press, 1999
18 A T C Goh, Y Zhang, R Zhang, W Zhang, Y Xiao. Evaluating stability of underground entry-type excavations using multivariate adaptive regression splines and logistic regression. Tunnelling and Underground Space Technology, 2017, 70: 148–154
19 A Forghani, R C Peralta. Transport modeling and multivariate adaptive regression splines for evaluating performance of asr systems in freshwater aquifers. Journal of Hydrology (Amsterdam), 2017, 553: 540–548
20 A T C Goh. Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 1995, 9(3): 143–151
21 M S Rahman, J Wang, W Deng, J P Carter. A neural network model of the uplift capacity of suction caissons. Computers and Geotechnics, 2001, 28(4): 269–287
22 N Vu-Bac, T Lahmer, H Keitel, J Zhao, X Zhuang, T Rabczuk. Stochastic predictions of bulk properties of amorphous polyethylene based on molecular dynamics simulations. Mechanics of Materials, 2014, 68: 70–84
Related articles from Frontiers Journals
[1] Behnam VAKHSHOURI, Shami NEJADI. Instantaneous deflection of light-weight concrete slabs[J]. Front. Struct. Civ. Eng., 2017, 11(4): 412-423.
[2] Shouping SHANG , Fangyuan ZHOU , Wei LIU , . Calculation of diagonal section and cross-section bending capacity for strengthening RC structure using high-performance ferrocement laminate[J]. Front. Struct. Civ. Eng., 2009, 3(3): 330-338.
[3] WANG Jingfeng, LI Guoqiang. Bending and rotational behaviour of semi-continuous composite beams[J]. Front. Struct. Civ. Eng., 2008, 2(2): 116-122.
Full text