The Fuzzy Logic Model for the Prediction of Marshall Stability of Lightweight Asphalt Concretes Fabricated using Expanded Clay Aggregate

Öz

In the study, predictability of Marshall Stability (MS) of light asphalt concrete that fabricated using expanded clay and had varied mix properties with Fuzzy Logic (FL) were researched. With this aim, asphalt concrete samples that added expanded clay aggregate (EC) in accordance with gradation determined in Highway Technical Specification, had different percentage of bitumen (POB) (4.5%, 5%, 5.5%, 6%, 6.5%, 7%, 7.5%, 8%, 8.5%, 9%, 9.5%, 10%, 10.5%) and unit weight (UW) (1,75–1,87 (gr/cm3)) were prepared and determined Marshall stabilities with Marshall test. After that Fuzzy Logic Model was conducted with the Marshall Stability results. In the model developed by FL method the amount of bitumen (%), transition speed of ultrasound (µs) and unit weight (gr/cm3) were used as input variable and Marshall Stability (kg) parameters were used as output variable. In the study rules were written depending on the membership functions determined for input variables. In the defuzzification process center of gravity method was used. As a result, Marshall Stability of asphalt concrete fabricated using expanded clay aggregate, with FL method, can be determined in a short time easily, in a very low error rates and without an experimental study.

Anahtar Kelimeler

• Lightweight asphalt
• concretes
• Expanded clay
• Marshall Stability
• Fuzzy logic

Genleştirilmiş Kil Agregası Kullanılarak Üretilmiş Hafif Asfalt Betonun Marshall Stabilite Tahmini İçin Bulanık Mantık Modeli

Öz

Çalışmada, genleştirilmiş kil kullanılarak üretilen çeşitli karışım özelliklerine sahip hafif asphalt betonun Marshall stabilitesinin Bulanık Mantık yöntemiyle tahmin edilebilirliği araştırılmıştır. Bu amaçla, Karayolları Teknik Şartnamesine gore belirlenen gradasyon limitlerinde genleştirilmiş kil agregası eklenen asphalt betonu numuneleri farklı bitüm yüzdelerinde (4.5%, 5%, 5.5%, 6%, 6.5%, 7%, 7.5%, 8%, 8.5%, 9%, 9.5%, 10%, 10.5%) ve (1,75–1,87 (gr/cm3) birim hacim ağırlıkta hazırlanmış ve Marshall Test yöntemiyle Marshall Stabiliteleri belirlenmiştir. Bununla birlikte Marshall Stabilite sonuçlarıyla Bulanık Mantık Modeli kurulmuştur. Geliştirilen modelde bitüm miktarı (%), ultrases geçiş hızı (µs) ve birim hacim ağırlık (gr/ cm3) girdi olarak, Marshall Stabilitesi (kg) parametreleri ise çıktı olarak kullanılmıştur. Çalışmada girdi değerleri için belirlenen üyelik fonksiyonlarına bağlı kural tabanı oluşturulmuştur. Durulaştırma işleminde ise ağırlık merkezi metodu kullanılmıştır. Sonuç olarak kısa sürede, kolaylıkla, düşük hata oranlarında ve deneysel çalışma gerektirmeden genleştirilmiş kil agregası kullanılarak üretilen asfalt numunelerinin Marshall Stabiliteleri Bulanık Mantık metoduyla belirlenebilmektedir.

Anahtar Kelimeler

• Hafif asfalt beton
• Genleştirilmiş kil
• Marshall Stabilitesi
• Bulanık mantık

Kaynakça

1. Aams, V., and Shah., S.C., 1974. Evaluation of Open
2. Graded Plan-Mix Seal Surfaces for Correction of Slippery Pavement. In Trasportation Research Record 523, TRB, National Research Council, Washington, D.C., pp.88-96. Agostinacchio, M., Olita, S., 2004. Use Of Expanded
3. Clay For High Grip Bituminous Wearing Courses - II° International Congress SIIV 2004, Florence, Italy.
4. Akkurt, I., Başyigit, C., Kilincarslan, S, & Beycioglu, A., 20 Prediction of photon attenuation coefficients of heavy concrete by fuzzy logic” Journal of the Franklin Institute, Volume 347, Issue 9, November 2010, Pages 1589-1597.
5. Alasha’ary, H., Moghtaderi, B., Page, A., & Sugo, H., 200 A neuro–fuzzy model for prediction of the indoor temperature in typical Australian residential buildings. Energy and Buildings, 41, 703–710. Area, P. J., Jr., 1969. Expanded Clay Hot Mix Study,
6. Final Report Part II, LDH Research Report No. 37, Ayata, T., Çam, E., & Yıldız, O., 2007. Adaptive Neuro
7. Fuzzy Inference Systems (ANFIS) Application to Investigate Potential Use of Natural Ventilation in New Building Designs in Turkey. Energy Conversion and Management, 48 (5), 1472-1479.
8. Azamathulla, H.M., Ghani, A.A., Fei, S.Y., 2012. ANFIS- based approach for predicting sediment transport in clean sewer. Applied Soft Computing, 12, 1227–1230.

9. Bilgehan, M., (2011). Comparison of ANFIS and NN models—with a study in critical buckling load estimation. Applied Soft Computing, 11, 3779–3791.
10. Cabalar, A. F., Cevik, A., Gokceoglu, C., 2012. Some applications of Adaptive Neuro-Fuzzy Inference
11. Chen, W.F, & Richard Liew, J.Y., 2003. The Civil
12. Engineering Handbook, New Directions in Civil Engineering, CRC Press. Emiroglu, M. E., Kisi, O., & Bilhan, O., 2010. Predicting discharge capacity of triangular labyrinth side weir located on a straight channel by using an adaptive neuro-fuzzy technique. Advances in Engineering Software, 41 (2), pp. 154-160,
13. Emiroğlu, M., Beycioğlu, A., & Yildiz, S., 2012. ANFIS and statistical based approach to prediction the peak pressure load of concrete pipes including glass fiber.
14. Expert Systems with Applications, Volume 39, Issue 3, 15 February 2012, Pages 2877-2883.
15. Faisal, T., Taib, M.N., & Ibrahim, F., 2012. Adaptive
16. Neuro-Fuzzy Inference System for diagnosis risk in dengue patients. Expert Systems with Applications, 39, 4483–4495.
17. General Directorate of Highways, 2006. State
18. Highways Technical Specifications (KTŞ), Ankara, Turkey. Gündüz L., Şapcı N., Bekar M., 2006. Utilization of
19. Expanded Clay As Lightweight Aggregate, J. Clay Sci. Technol. Kibited 1(2): 43-49. Işık, H., & Arslan, S., 2011. The design of ultrasonic therapy device via fuzzy logic. Expert Systems with Applications, 38, 7342–7348.
20. Jansen, D.C., Kiggins, M.L. Swan, C.W., Malloy, R.A., Kashi, M.G., Chan, R.A., Javdekar, C., Siegal, C., and Weingram. J., 2001. Lightweight Fly Ash-Plastic
21. Aggregates in Concrete. In Trasportation Research Record: Journal of the Transportation Research Board, No. 1775, TRB, National Research Council, Washington, D.C., pp.44-52.
22. Kalyoncuoğlu, S.F., & Tığdemir, M., 2004. An alternative approach for modelling and simulation of traffic data: Artificial neural Networks. Simulation
23. Modeling Practice and Theory, 12(5), 351–362. Kisi, O., Haktanir, T., Ardiclioglu, M., Ozturk, O., Yalcin, E., & Uludag S., 2009. Adaptive neuro-fuzzy computing technique for suspended sediment estimation. Advances in Engineering Software,
24. Volume 40, Issue 6, Pages 438-444. Kucuk, K., Aksoy, C.O., Basarir, H., Onargan, T., Genis, M., & Ozacar, V., 2011. Prediction of the performance of impact hammers by adaptive neuro-fuzzy inference system modeling. Tunnelling and Underground Space Technology, 26, 38–45.
25. Kuşan, H., Aytekin, O., & Özdemir, I., 2010. The use of fuzzy logic in predicting house selling price. Expert
26. Systems with Applications 37, 1808–1813.
27. Lehmann, H. L., and Adam. V., 1956. Use of Expanded
28. Clay Aggregate in Bituminous Construction. Highway Research Board Proceeding. Vol.38, pp. 398-407
29. Losa, M. Leandri, P. and Bacci, R., 2008a. Mechanical and Performance-Related Properties of Asphalt Mixes
30. Containing Expanded Clay Aggregate, Transportation Research Record: Journal of the Transportation Research Board, No. 2051, Transportation Research
31. Board of the National Academies, Washington, D.C., pp. 23–30. Losa, M. Bacci, R. Leandri, P. Alfinito, L. Cerchiai, M., 2008b. Surface Characteristics of Asphalt Pavements with
32. Symposium on Pavement Surface Characteristics SURF 2008, Portoroz, Slovenia. Aggregate, 6th
33. Madandoust, R., Bungey, J.H., & Ghavidel, R., 2012.
34. Prediction of the concrete compressive strength by means of core testing using GMDH-type neural network and ANFIS models. Computational Materials Science, 51, 261–272. Mamdani, E.H., 1976. Application of fuzzy algorithms for control of simple dynamic plants. Proc IEEE, 121:1585–8.
35. Mashrei, M.A., Abdulrazzaq, N., Abdalla, T.Y., & Rahman, M.S., 2010. Neural networks model and adaptive neuro-fuzzy inference system for predicting the moment capacity of ferrocement members.
36. Engineering Structures, Volume 32, Issue 6, pp. 1723- 17
37. Mirzahosseini, M. R., Aghaeifar A., Alavi, A.H., Amir Gandomi, H., Seyednour, R., 2011. Permanent deformation analysis of asphalt mixtures using soft computing techniques. Expert Systems with
38. Moazami, D., Behbahani, H., Muniandy, R., 2011. Pavement prioritization of urban roads using fuzzy logic. Expert
39. Systems with Applications, 38, 12869–12879.
40. Moghaddamnia, A., Ghafari Gousheh, M., Piri, J., Amin, S., & Han D., 2009. Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. Advances in Water
41. Resources, Volume 32, Issue 1, Pages 88-97. Nazari, A., Milani, A.A., & Khalaj, G., 2011. Modeling ductile to brittle transition temperature of functionally graded steels by ANFIS. Applied Mathematical www.elsevier.com/locate/apm, in Press. journal homepage:
42. Omid, M., 2011. Design of an expert system for sorting pistachio nuts through decision tree and fuzzy logic classifier. Expert Systems with Applications, 38, 4339–4347.
43. Özgan, E., 2011. Artificial Neural Network Based
44. Modeling of the Marshall Stability of Asphalt Concrete. Expert Systems With Applications, 38, 6025-6030.
45. Prabha, N.R., Marimuthu, N.S., & Babulal, C.K. 2010.
46. Adaptive neuro-fuzzy inference system based representative quality power factor for power quality assessment, Neurocomputing 73, 2737–2743.
47. Saffarzadeh, M., & Heidaripanah, A., 2009. Effect of
48. Asphalt Content on the Marshall Stability of Asphalt Concrete Transaction A: Civil Engineering, 16, 1, 98-105. Neural Networks. Saltan, M., & Terzi, S., 2008. Modeling deflection basin using artificial neural networks with cross-validation technique in backcalculating flexible pavement layer moduli. Advances in Engineering Software, 39(7), 588–592.
49. Saltan, M., Terzi, S., & Küçüksille, E. U., 2011.
50. Backcalculation of pavement layer moduli and Poisson’s ratio using data mining, Expert Systems with Applications, 38, 2600–2608.
51. Sanders, S. R., Rath, D., Parker, F., 1994. Comparison of Measurements, Engineering, 120, 6, pp 953-966. Of Journal Transportation
52. Sobhani, J., Najimi, M., Pourkhorshidi, A. R., & Parhizkar T., 2010. Prediction of the compressive strength of no-slump concrete: A comparative study of regression, neural network and ANFIS models.
53. Construction and Building Materials, 24, 5, 709-718. Subaşı S., 2009a. The Effects of Using Fly Ash on High
54. Strength Lightweight Concrete Produced with Expanded Clay Aggregate, Scientific Research and Essay Vol. 4 (4) pp. 275-288. Subaşı, S., 2009b. Prediction of mechanical properties of cement containing class C fly ash by using artificial neural network and regression technique. Scientific
55. Research and Essays, 4(4), 289–297. Talei, A., Chua, L. H. C., & Wong, T.S.W., 2010.
56. Evaluation of Rainfall and Discharge Inputs Used by Adaptive Network-Based Fuzzy Inference Systems (ANFIS) in Rainfall-Runoff Modeling. Journal of Hydrology, In Press, Available online 24 July. Tanyildizi, H., 2009. Fuzzy logic model for prediction of mechanical properties of lightweight concrete exposed to high Temperature, Materials and Design 30, 2205–2210.
57. Taşdemir, Y., 2009. Artificial neural networks for predicting low temperature performance of modified asphalt mixtures. Indıan journal of engineering &
58. Materials Sciences, Vol. 16, pp 237. Tapkın, S., Çevik, A., & Uşar, Ü., 2010. Prediction of
59. Marshall test results for polypropylene modiŞed dense bituminous mixtures using neural networks. Expert Systems with Applications, 37(6),4660-4670,
60. Terzi, S., 2007. Modeling the pavement serviceability ratio of flexible highway pavements by artificial neural Networks. Construction & Building Materials, 21, 590–593.
61. Tiğdemir, M., Karaşahin, M., & Şen., Z., 2002.
62. Investigation of fatigue behaviour of asphalt concrete pavements with fuzzy logic approach. International Journal Fatigue, 24(8), 903–910. Topçu I.B., Sarıdemir, M., 2008. Prediction of rubberized concrete properties using artificial neural network and fuzzy logic. Construction and Building Materials, 22, 532–540.
63. Topcu, I.B, & Sarıdemir, M., 2008. Prediction of mechanical properties of recycled aggregate concretes containing silica fume using artificial neural networks and fuzzy logic. Comput. Mater. Sci., 42(1), 74–82.
64. Tutumluer, E., & Meier, R. W., 1996. Attempt at resilient modulus modeling using artificial neural
65. Networks, Transportation Research Record, 1560, TRB, Washington, DC, 1.
66. Yılmaz, I., & Kaynar, O., 2011. Multiple regression,
67. Turkey. Journal of Hydrology, 365, 3-4, 225-234. Zadeh, L.A., 1965. Fuzzy sets, Inf. Control 8, 338-353.