BETONUN BASINÇ MUKAVEMETİNİN TAZE BETON ÖZELLİKLERİNDEN TAHMİNİ İÇİN ANFIS MODELİ

Öz

Betonun sertleşme süreci geri dönüştürülemezdir ve taze beton özellikleri hem sertleşme sürecini hem de sertleşmiş özelliklerini doğrudan etkilemektedir. Betonun basınç mukavemeti eğilme, çekme, elastisitesi ve durabilitesi gibi birçok özellikleri ile yakından ilişkili olduğu için en önemli özelliklerinden biridir. Bu çalışmada beton bileşenlerinin kısmi hacim oranları ve akış özelliklerinden betonun basınç mukavemetinin tahmini için Adaptif Ağ Tabanlı Bulanık Çıkarım Sistemi (ANFIS) kullanılarak model geliştirilmiştir. Modellerden en düşük determinasyon katsayısı yalnızca akış özelliklerinin girdi olarak kullanıldığı modelden (R2= 0.369) elde edilmişken yalnızca kısmi hacim oranlarının girdi olarak kullanıldığı modelden (R2= 0.673) akış özelliklerine göre daha yüksek elde edilmiştir. En yüksek determinasyon katsayısı ise her iki değişkenin girdi olarak kullanıldığı modelden (R2= 0.961) elde edilmiştir. Kısmi hacim oranı ve akış özellikleri kullanılarak betonun basınç mukavemetini belirlemek için ANFIS yönteminin alternatif bir metot olarak kullanılabileceği sonucuna varılmıştır.

Anahtar Kelimeler

• betonun basınç mukavemeti, akış özellikleri, ANFIS modelleme

ANFIS MODEL FOR THE PREDICTION OF COMPRESSIVE STRENGTH OF CONCRETE FOR FRESH CONCRETE PROPERTIES

Öz

The hardening process of concrete is irreversible, and properties of fresh concrete directly affect the hardening process and afterwards its hardened properties. Compressive strength is one of the most important mechanical properties of hardened concrete because it is related to other properties or performance of concrete such as bending, tensile, elasticity and durability. In this study, the ANFIS models were developed to estimate the concrete compressive strength from partial-volume ratio of concrete components and flow properties. While lowest coefficient of determination is obtained (R2= 0.369) from modeling using of only flow properties as input parameters, modeling using of only partial-volume ratio of concrete components as input parameters is higher (R2= 0.673) than modeling of flow properties. However, the best results (R2= 0.961) is obtained from modeling using both variables as input parameters. As a result suggest that ANFIS can be used as an alternative approach to estimate compressive strength when it is used together partial-volume ratio of concrete components with flow properties as input parameters.

Anahtar Kelimeler

• compressive strength of concrete, flow properties, ANFIS modeling

Kaynakça

1. Akman MS (1999). Role of admixtures on high performance concrete, RILEM TC 158 AHC, Monterrey, Mexico.
2. Al-Martini S, Nehdi M (2009). Genetic algorithm-based yield stress equations for concrete at high temperature and prolonged mixing time, Comput Concr, 6(4), 343-356.
3. Atici U (2011). Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network, Expert Syst Appl, 38(8), 9609- 9618.
4. Banfill, P.F.G., 1991. Rheology of Fresh Cement and Concrete. E.&F.N. Spon Publisher, p.373, London.
5. Banfill, P.F.G., 2003. The Rheology of Fresh Cement and Concrete - A Review. 11th International Cement Chemistry Congress, p. 13, Durban.
6. Bartos, P., 1992. Fresh Concrete Properties and Tests. Elsevier Science Publisher, 291s., Amsterdam.
7. Bassuoni MT, Nehdi ML (2008). Neuro-Fuzzy Based Prediction of the Durability of Self- Consolidating Concrete to Various Sodium Sulfate Attack Exposure Regimes, Comput Concr, 5(6), 573-597.
8. Bilgehan MA (2011). Comparative study for the concrete compressive strength estimation using neural network and neuro-fuzzy modelling approaches, Nondestructive Test Eval, 26(1), 35-55.

9. Bilgehan M, Turgut P (2010). The use of neural networks in concrete compressive strength estimation, Comput Concr, 7(3), 271–283.
10. Chen CW, Huang ST (2011). Implementing KM programmes using fuzzy QFD, Total Qual Man & Business Excel, 22(4), 387-406.
11. Chen HS, Sun W, Stroeven P (2003). Prediction of compressive strength and optimization of mixture proportioning in ternary cementitious systems, Mater Struct, 36(260), 396-401.
12. Chen L, Wang TS (2010). Modeling slump of concrete using the group method data handling algoritm Indian J Eng Mater Sci, 17, 179-185.
13. Chidiac SE, Habibbeigi F (2005). Modeling the rheological behavior of fresh concrete: an elasto-viscoplastic finite element approach, Comput Concr, 2(2), 97–110.
14. Dağ, A., Alkan, B., Çıra, C.S., (2011). Bulanık modelleme yaklaşımının çimento hammadde sahası kalınlık kestiriminde kullanılabilirliğinin araştırılması, e-Journal of New World Sciences Academy, Engineering Sciences, NWSA (www.newwsa.com), 6 (1), 88-97.
15. Demir, F., (2005a). Normal ve Yüksek Dayanımlı Betonların Elastisite Modülü Belirlenmesi İçin Bir Bulanık Yaklaşımı, Deprem Sempozyumu, 23-24.
16. Demir F (2005b). A new way of prediction elastic modulus of normal and high strength concrete-fuzzy logic, Cem Concr Res, 35, 1531-1538.
17. Do J, Song H, So S, Soh Y (2005). Fuzzy methodology application for modeling uncertainties in chloride ingress models of RC building structure, Comput Concr, 2(4), 325-343.
18. Do JY (2006). Fuzzy inference based cover thickness estimation of reinforced concrete structure quantitatively considering salty environment impact, Comput Concr, 3(2), 145–162.
19. Dubois D, Prade H (1980). Fuzzy Sets and Systems: Theory and Applications, Academic Pres. Inc. Ltd., London.
20. Ebrahimi E, Mollazade K (2010). Intelligent fault classification of a tractor starter motor using vibration monitoring and adaptive neuro-fuzzy inference system, INSIGHT, 52 (10), 561-566.
21. Erdik T (2009). Discussion on Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic, Comput Mater Sci, 44, 1022.
22. Erdoğan TY (2003). Concrete, Metu Pres, Ankara, Turkey.
23. Ferraris CF (1999). Measurement of the rheological properties of high performance concrete. J Res Nat Inst Stand and Tech, 104(5), 461-478.
24. Ferraris CF, Obla KH, Hill R (2001). The influence of mineral admixtures on the rheology of cement paste and concrete, Cem Concr Res, 31(2), 245-255.
25. Gupta R, Kewalramani MA, Goel A (2006). Prediction of concrete strength using neural- expert system, J Mat Civ Engrg, 18(3), 462-466.
26. Haimoni A, Hannant DJ (1993). Hydraulic transport of solids in pipes: a simple method for the prediction of pressure, Drop Mat Struc, 26, 144-151.
27. Han SH, Kim JK, Park YD (2003). Prediction of compressive strength of fly ash concrete by new apparent activation energy function, Cem Concr Res, 33(7), 965-971.
28. Hashina Z, Monteiro PJM (2002). An inverse method to determine the elastic properties of the interphase between the aggregate and the cement paste, Cem Concr Res, 32(8), 1291-1300.
29. Hocaoğlu FO ve Kurban M, (2005). Adaptif Ağ Tabanlı Bulanık Mantık Çıkarım Sistemi ile Eskişehir Bölgesi için Güneşlenme Süreleri Tahmini, Elektrik-Elektronik-Bilgisayar Mühendisliği 11. Ulusal Kongresi ve Fuarı, İstanbul.
30. Hsu HH, Chen L, Kou CH, Chiu CH (2011). Modeling slump flow of concrete using genetic programming, Adv Mater Res, 211-212, 374-378.
31. Jain A, Jha SK, Misra S (2008). Modeling and analysis of concrete slump using artificial neural networks, J Mat Civ Engrg, 20(9), 628-633.
32. Jang JSR (1993). ANFIS: Adaptive-Network-Based Fuzzy Inference System, IEE Transactions on Systems, Man, and Cybernetics, 23(3), 665-685.
33. Keskin ME, Taylan D, Terzi Ö, (2006). ANFIS Approach for Modeling Hydrological Time Series, Hydrol Sci J, 51(4), 588-598.
34. Long, W J, Khayat KH, Xing F (2010). Statistical models to predict fresh properties of self- consolidating concrete, Adv Mater Res, 129–131, 853-856.
35. Negnevitsky M (2005). Artificial Intelligence; A Guide to Intelligent Systems, Second Edition, Addison-Wesley, New York.
36. Neville AM (1996). Properties of Concrete, 4th Edition, John Wiley & Sons, Inc., New York.
37. Ozbay E, Oztas A, Baykasoglu A (2010). Cost optimization of high strength concretes by soft computing techniques, Comput Concr, 7(3), 221-237.
38. Özel C (2007). Katkılı Betonların Reolojik Özeliklerinin Taze Beton Deney Yöntemlerine Göre Belirlenmesi, S.D.Ü. Fen Bilimleri Enstitüsü İnşaat Mühendisliği A.B.D., Isparta.
39. Peng CH, Yeh IC, Lien LC (2009). Modeling strength of high-performance concrete using genetic operation trees with pruning techniques, Comput Concr, 6(3), 203-223.
40. Ramezanianpour AA, Shahhosseini V, Moodi F (2009). A fuzzy expert system for diagnosis assessment of reinforced concrete bridge decks, Comput Concr, 6(4). 281-303.
41. Sobhani J, Najimi M, Pourkhorshidi AR, Parhizkar T (2010). Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models, Const Build Mat, 24, 709–718.
42. Şentürk S, (2010). Faktöriyel Tasarıma Adaptif Ağ Tabanlı Bulanık Mantık Çıkarım Sistemi İle Farklı Bir Yaklaşım, Dumlupınar Üniversitesi, Fen Bilimleri Enstitüsü Dergisi, 22, 57-74
43. Tattersall, G. H. ve Banfill P. F. G., 1983. The Rheology of Fresh Concrete, Pitman Books Limited, p. 353, London.
44. Tattersall G. H., 1991. Workability and Quality Control of Concrete, E.&F.N. Spon Publ., p.262, London.
45. Terzi Ö, Keskin ME, Taylan ED, (2006). Estimating Evaporation Using ANFIS, J Irrign Drain Engrg, 132(5), 503-507.
46. Terzi S, Morova N, Karaşahin M (2009), Determining of Flexible Pavement Condition Rating Deduct Value with Fuzzy Logic Algorithm, Int Symp on Innov in Intel Syst and App, 161-168, Trabzon, Turkey.
47. Topcu IB, Saridemir M (2008a). Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic, Comp Mat Sci, 41(3), 305-311.
48. Topcu IB, Saridemir M (2008b). Prediction of rubberized concrete properties using artificial neural network and fuzzy logic, Const Build Mat, 22, 532–540.
49. Yeh IC (2008a). Prediction of workability of concrete using design of experiments for mixtures, Comput Concr, 5(1), 1-20.
50. Yeh IC (2008b). Modeling slump of concrete with fly ash and superplasticizer, Comput Concr, 5(6), 559-572.
51. Zadeh LA (1965). Fuzzy sets, Inf Control 8(3): 338–353.
52. Zongjin L, (2011). CIVL 111 Construction Materials, Department of Civil Engineering http://teaching.ust.hk/~civl111/CIVL111-lecture-5.pdf (Erişim Tarihi: 28.01.2012)