SOĞUK HADDELENMİŞ TİCARİ ALÜMİNYUM LEVHALARIN YORULMA DAYANIMLARININ YAPAY SİNİR AĞLARI İLE TAHMİNİ

Year 2017, Volume: 2 Issue: 24, 39 - 49, 30.12.2017

Raif Sakin , Ayla Tekin , Nurcan Kumru

Abstract

Bu
çalışmanın temel amacı, soğuk haddelenmiş ticari alüminyum levhaların çekme,
eğilme,  ve sertlik gibi test verilerini
kullanarak yorulma dayanımını tahmin etmektir. Bu tahminler için Yapay Sinir
Ağları (YSA) aracı kullanılmıştır. Çalışmanın diğer önemli amacı ise YSA'nın
yorulma ile ilgili iyi tahminler yapıp yapmadığının anlaşılmasıdır. Yapay sinir
ağı MATLAB yazılımı ile geliştirilmiştir. Yorulma testleri için ankastre-tip ve
çok numuneli test makinesi tasarlanmış ve imal edilmiştir. AA1100 ve AA1050
alüminyum levhalar hadde yönüne paralel (HYP) ve hadde yönüne dik (HYD) şekilde
kesilmişlerdir. Yorulma testleri, farklı sehim genlikleri kullanılarak
sehim-kontrollü ve 50 Hz frekanslı tam değişken yükleme altında
gerçekleştirilmiştir. Yorulma testlerinden elde edilen veriler çok katmanlı,
ileri beslemeli ve hatanın geri yayılım algoritmasının kullanıldığı YSA
modelini eğitmek için kullanılmıştır. YSA modellemesinde giriş parametreleri
çekme dayanımı, eğilme dayanımı, sertlik ve yük tekrar sayısı olarak
belirlenmiştir. Bu modelleme ile yorulma dayanımı değerleri tahmin edilmiştir.
Test sonuçları ile YSA sonuçları olarak karşılaştırıldığında, tasarlanan
modelin başarılı bir şekilde uygulandığı ve gerçek test sonuçlarına çok yakın
sonuçlar verdiği görülmüştür. YSA'nın soğuk haddelenmiş ticari alüminyum
levhaların  yorulma dayanımı tahmin
etmede önemli bir araç olduğu sonucuna varılmıştır.

Keywords

alüminyum levha, yapay sinir ağları (YSA), yorulma-dayanımı tahmini

References

• 1. Sadeler, R., Totik, Y., Gavgalı, M., and Kaymaz, I. (2004). Improvements of fatigue behaviour in 2014 Al alloy by solution heat treating and age-hardening. Mater Des 25, 439-445.
• 2. Rooy, E.L. (2005). ASM International Handbook, Properties and Selection : Nonferrous Alloys and Special-Purpose Materials. In Introduction to Aluminum and Aluminum Alloys, Volume 2. (USA: The Materials Information Company).
• 3. Sakin, R., and Er, M. (2010). Investigation of Plane-Bending Fatigue Behavior of 1100-H14 Aluminum Alloy. J Fac Eng Archit of Gazi University 25, 213-223.
• 4. Liao, M. (2009). Probabilistic modeling of fatigue related microstructural parameters in aluminum alloys. Eng Fract Mech 76, 668-680.
• 5. Miyazaki, T., Kang, H., Noguchi, H., and Ogi, K. (2008). Prediction of high-cycle fatigue life reliability of aluminum cast alloy from statistical characteristics of defects at meso-scale. International Journal of Mechanical Sciences 50, 152-162.
• 6. Fatemi, A., Plaseied, A., Khosrovaneh, A., and Tanner, D. (2005). Application of bi-linear log–log S–N model to strain-controlled fatigue data of aluminum alloys and its effect on life predictions. Int J Fatigue 27, 1040-1050.
• 7. Zhao, T., and Jiang, Y. (2008). Fatigue of 7075-T651 aluminum alloy. Int J Fatigue 30, 834-849.
• 8. Srivatsan, T.S., Kolar, D., and Magnusen, P. (2002). The cyclic fatigue and final fracture behavior of aluminum alloy 2524. Mater Des 23, 129-139.
• 9. Gruenberg, K. (2004). Predicting fatigue life of pre-corroded 2024-T3 aluminum. Int J Fatigue 26, 629-640.
• 10. Boob, G., and Deoghare, A.B. (2013). Estimation of Strain Controlled Fatigue Properties of Steels Using Tensile Test Data. In International and 16th National Conference on Machines and Mechanisms (iNaCoMM2013). (IIT Roorkee, India).
• 11. Allahverdi, N. (2011). Uzman Sistemler, Bir Yapay Zekâ Uygulaması, (İstanbul: Atlas Yayın Dağıtım).
• 12. Öztemel, E. (2012). Yapay Sinir Ağları, (İstanbul: Papatya Yayıncılık).
• 13. Durmuş, H.K., Özkaya, E., and Meriç, C. (2006). The use of neural networks for the prediction of wear loss and surface roughness of AA 6351 aluminium alloy. Mater Des 27, 156-159.
• 14. Esme, U., Sagbas, A., Kahraman, F., and Kulekci, M.K. (2008). Use of Artificial Neural Network In Ball Burnishing Process For The Prediction Of Surface Roughness Of AA 7075 Aluminyum Alloys. Materials And Technology 42, 215-219.
• 15. Mathew, M.D., Kim, D.W., and Ryu, W.-S. (2008). A neural network model to predict low cycle fatigue life of nitrogen-alloyed 316L stainless steel. Materials Science and Engineering: A 474, 247-253.
• 16. Karataş, C., Sozen, A., and Dulek, E. (2009). Modelling of residual stresses in the shot peened material C-1020 by artificial neural network. Expert Systems with Applications 36, 3514-3521.
• 17. Abdalla, J.A., and Hawileh, R. (2011). Modeling and simulation of low-cycle fatigue life of steel reinforcing bars using artificial neural network. Journal of the Franklin Institute 348, 1393-1403.
• 18. Karakas, Ö. (2011). Estimation of fatigue life for aluminium welded joints with the application of artificial neural networks. Materialwissenschaft und Werkstofftechnik 42, 888-893.
• 19. TSE (2010). TS EN 485-2: Aluminium and Aluminium Alloys Sheet Strip and Plate Part 2: Mechanical Properties. In Turkish Standards Institute (TS). (Ankara, Turkey).
• 20. ISO (2005). EN ISO 7438:2005(E), Metallic materials. Bend test. (Geneva, Switzerland).
• 21. Er, M. (2006). Investigation of Bending Fatigue Behaviour of the 1100-H14 Aluminium Plate and The Design of a Amplitude-Regulated, High Frequency Bending Fatigue Test Machine. In Institute of Science, Department of Mechanical Engineering. (Balikesir, Turkey: Balıkesir University).
• 22. Kumru, N. (2007). Design of Fatigue Test Apparatus for Etial-141, Etial-145 and Etial-160 Type Cast Aluminum and Plate Aluminum Materials and Investigation of Bending Fatigue Behaviours. In Institute of Science, Department of Mechanical Engineering. (Manisa, Turkey: Celal Bayar University).
• 23. Ay, I., and Sakin, R. (2006). Production and testing of glass-fiber reinforced plastic axial fan blades for replacement for aluminum ones that are produced in Balikesir. In Scientific Research Project, Volume 2002/14. (Balikesir, Turkey: Balikesir University Research Foundation).
• 24. Sakin, R., Kumru, N., Er, M., and Ay, I. (2010). Statistical Analysis of Fatigue-Life Data for Aluminum Alloys and Composites. In 2nd National Congress of Design, Manufacturing and Analysis, A. Oral, ed. (Balikesir, Turkey).
• 25. Sakin, R., and Ay, İ. (2008). Statistical analysis of bending fatigue life data using Weibull distribution in glass-fiber reinforced polyester composites. Mater Des 29, 1170-1181.
• 26. Sakin, R., Ay, İ., and Yaman, R. (2008). An investigation of bending fatigue behavior for glass-fiber reinforced polyester composite materials. Mater Des 29, 212-217.
• 27. Ay, İ., Sakin, R., and Okoldan, G. (2008). An improved design of apparatus for multi-specimen bending fatigue and fatigue behaviour for laminated composites. Mater Des 29, 397-402.
• 28. Sakin, R., Kumru, N., and Ay, İ. (2008). Design of Apparatus for the Stress-Controlled, Multi-Specimen Bending Fatigue Test and an Application for Composites. In 12th International Materials Symposium (IMSP’2008), Volume 531-541, C. Meran, ed. (Denizli, Turkey: Pamukkale University).
• 29. Kim, H.Y., Marrero, T.R., Yasuda, H.K., and Pringle, O.A. (1999). A Simple Multi-Specimen Apparatus for Fixed Stress Fatigue Testing. J Biomed Mater Res 48, 297-300.
• 30. Ben Zineb, T., Sedrakian, A., and Billoet, J.L. (2003). An original pure bending device with large displacements and rotations for static and fatigue tests of composite structures. Composites Part B 34, 447-458.
• 31. Khashaba, U.A. (2003). Fatigue and Reliability Analysis of Unidirectional GFRP Composites Under Rotating Bending Loads'. J Compos Mater 37, 317-331.
• 32. Abdallah, M.H., Abdin, E.M., Selmy, A.I., and Khashaba, U.A. (1996). Reliability analysis of GFRP pultruded composite rods. Int J Qual & Reliab Manage 13, 88-98.
• 33. Tai, N.-H., Yip, M.-C., and Tseng, C.-M. (1999). Influences of thermal cycling and low-energy impact on the fatigue behavior of carbon/PEEK laminates. Composites Part B 30, 849-865.