Study of the effect of chloride diffusion coefficient in concrete using neural network models
محورهای موضوعی : Analytical and Numerical Methods in Mechanical DesignAli Delnavaz 1 , ali osat akbari moghaddam 2
1 - Department of civil and surveying engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran
2 - Department of civil engineering, Qazvin branch, Islamic Azad University, Qazvin, Iran
کلید واژه: neural network model, chloride diffusion coefficient ,
چکیده مقاله :
Chloride diffusion is one of the main causes of deterioration of concrete structures. Much research has been done to study the diffusion of chlorides in concrete, experimentally and theoretically. Since chloride diffusion experiments are time consuming, it is desired to develop a model to predict chloride profiles in concrete. This paper investigates the feasibility of using a neural network as an adaptive synthesizer as well as a predictor to meet such a requirement. Neural network models were therefore created to predict the chloride diffusion coefficient. The models were formed from the results of the chloride profile experiments. The input parameters were the water/binder ratios, the amount of silica fume and the environmental conditions of the samples. The output parameter was the chloride diffusion coefficient. Neural network models are multi-layer Perceptron models and differ in the number of layers and hidden neurons. To verify the accuracy of the model, an ANN model was created and the output of the model was compared with the test samples. The result shows that both neural network models have the ability to predict the chloride diffusion coefficient with good accuracy.
Chloride diffusion is one of the main causes of deterioration of concrete structures. Much research has been done to study the diffusion of chlorides in concrete, experimentally and theoretically. Since chloride diffusion experiments are time consuming, it is desired to develop a model to predict chloride profiles in concrete. This paper investigates the feasibility of using a neural network as an adaptive synthesizer as well as a predictor to meet such a requirement. Neural network models were therefore created to predict the chloride diffusion coefficient. The models were formed from the results of the chloride profile experiments. The input parameters were the water/binder ratios, the amount of silica fume and the environmental conditions of the samples. The output parameter was the chloride diffusion coefficient. Neural network models are multi-layer Perceptron models and differ in the number of layers and hidden neurons. To verify the accuracy of the model, an ANN model was created and the output of the model was compared with the test samples. The result shows that both neural network models have the ability to predict the chloride diffusion coefficient with good accuracy.
K. Sakr,” Effect of cement type on the corrosion of reinforcing steel bars exposed to acidic media using electrochemical techniques”, Cem. Concr. Res. 35 (2005) 1820-1826.
2. K.Y. Yeau, E.K. Kim, “An experimental study on corrosion resistance of concrete with ground granulate blast-furnace slag”, Cem. Concr. Res. 35 (2005) 1391-1399.
3. İlker Bekir Topçu, Ahmet Raif Boğa, Fatih Onur Hocaoğlu, “Modeling corrosion currents of reinforced concrete using ANN”, Autom. Const. (2008),
4. A.A. Gürten, K. Kayakırılmaz, M. Erbil, The effect of hiosemicarbazide on corrosion resistance of steel reinforcement in concrete, Const. Buil. Mater. 21 (2007) 669-676.
5. T. Parthiban, R. Ravi, G.T. Parthiban, S. Srinivasan, K.R. Ramakrishnan, M. Raghavan, Neural network analysis for corrosion of steel in concrete, Cor. Sci. 47 (2005) 1625-1642.
6. J. Hou, D.D.L. Chung, Effect of admixtures in concrete on the corrosion resistance of steel reinforced concrete, Cor. Sci. 42 (2000) 1489-1507.
7. K.K. Sideris, A.E. Sava, Durability of mixtures containing calcium nitrite based corrosion inhibitor, Cem. Concr. Compos. 27 (2005) 277-287.
8. C.H. Lim, Y.S. Yoon, J.H. Kim, Genetic algorithm in mix proportioning of high performance concrete, Cem. Concr. Res. 34 (2004) 409-420.
9. E.M.R. Fairbairn, M.M. Silvoso, R.D.T. Filho, J.L.D. Alves, N.F.F. Ebecken, Optimization of mass concrete construction using genetic algorithms, Comp. Struc. 82 (2004) 281-299.
10. G. İnan, A.B. Göktepe, K. Ramyar, A. Sezer, Prediction of sulfate expansion of PC mortar using adaptive neuro-fuzzy methodology, Build. Environ. 42 (2007) 1264-1269.
11. İ.B. Topçu, M. Sarıdemir, Prediction of properties of waste AAC aggregate concrete using artificial neural network, Comput. Mater. Sci. 41 (2007) 117–125.
12. N.Yasuda, T. Tsutsumi T. Kawamura, “Assessment Of Deteriorating Reinforced Concrete Structures Using Artificial Neural Networks”, Ieee Xplore (1993).
13. İ.B. Topçu, M. Sarıdemir, Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic, Comput. Mater. Sci. 41 (2008) 305-311.
14. B.B. Adhikary, H. Mutsuyoshi, Prediction of shear strength of steel fiber RC beams using neural networks, Const. and Buil. Mater. 20 (2006) 801-811.
15. A. Mukherjee, S.N. Biswas, Artificial neural networks in prediction of mechanical behavior of concrete at high temperature, Nucl. Eng. Des. 178 (1997) 1-11.
16. İ.B. Topçu, M. Sarıdemir, Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic, Comput. Mater. Sci. 41 (2008) 305-311.
17. İ.B. Topçu, M. Sarıdemir, Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic, Comput. Mater. Sci. 42 (2008) 74-82.
18. F. Altun, Ö. Kişi, K. Aydin, Predicting the compressive strength of steel fiber added lightweight concrete using neural network, Comput. Mater. Sci. 42 (2008) 259-265.
19. S.S.S. Sakla, A.F. Ashour, Prediction of tensile capacity of single adhesive anchors using neural networks, Comp. Struct. 83 (2005) 1792–1803.
20. R. Parichatprecha, P. Nimityongskul. “Analysis of durability of high performance concrete using artificial neural networks”, Construction and Building Materials 23 (2009) 910-917.
21. Rumellhert D, Hinto G, Williams R. “Learning internal representations by Error Propagation”. Cambridge, Mass: MIT Press; 1986.
22. H.R. Ashrafi, A.A Ramezanianpour, “The Assessment of Chloride Diffusion in concretes containing Silica-Fume”, Phd Thesis, 2007.
