TOZ METALURJİSİ YÖNTEMİYLE ÜRETİLMİŞ Ni-Ti-Cu ALAŞIMLARININ DİFÜZYON KAYNAĞINDA (BİNDİRME-KAYMA) SONUÇLARININ YAPAY SİNİR AĞLARI (ANN) İLE BELİRLENMESİ

Year 2008, Volume: 6 Issue: 2, 75 - 83, 30.03.2008

Haluk Kejanlı Mustafa Taşkın Uğur Çalıgülü

Abstract

Bu
çalışmada, toz metalurjisi yöntemiyle üretilmiş Ni-Ti-Cu alaşımlarının difüzyon
kaynağı sonrasında yapılan bindirme-kayma (Shear-Strength) test sonuçlarının Yapay Sinir Ağları (Artificial Neural
Network) yöntemi kullanılarak yapılan
eğitme sonrası elde edilen sonuçlarla tutarlılığı araştırılmıştır. Ni-Ti-Cu
kompo-zit malzemelerin kimyasal bileşimi % 49 
Ni - %51  Ti olup, tozlar 45mm boyutundadır. Difüzyon kaynakları, argon atmosferi
altında, 5 MPa sabit basınçta, 940-970 ºC sıcaklıklarda ve 40-60 dk. sürelerde
yapılmıştır. Kaynaklı numuneler birleşme bölgesine dik doğrultuda kesilerek,
numunelerin optik mikroskop, SEM-EDS analizleri yapılmıştır. Numunelerin kaynak
sonrası birleşme kalitesini tespit etmek için bindirme-kayma testleri
yapılmıştır ve elde edilen sonuçlar bilgisayar ortamında Yapay Sinir Ağları
programında test edilmiş-tir. Test programında kaynak sıcaklıkları ve kaynak
süreleri girdi, bindirme-kayma sonuçları da çıktı olarak kullanılmıştır. Gerçek
sonuçlar ile Yapay Sinir Ağları test analizi sonuçları birbirleriyle
karşılaştırılmış, so-nuçlar arasında bir tutarlılığın olduğu bilgisayar ortamında
tespit edilmiştir.

Keywords

Ni-Ti, Difüzyon Kaynağı, Bindirme-Kayma, Yapay Sinir Ağları

ARTIFICIAL NEURAL NETWORK (ANN) APPROACH THE PREDICTION OF DIFFUSION BONDING BEHAVIOR (SHEAR STRENGTH) OF Ni-Ti-Cu ALLOYS MANUFACTURED BY POWDER METALLURGY METHOD

Abstract

In this study, Artificial Neural Network approach to prediction of diffusion
bonding behavior of Ni-Ti-Cu alloys, manufactured by powder metallurgy process,
were obtained using a back-propagation neural network that uses gradient
descent learning algorithm. Ni-Ti-Cu composite was manufactured with a chemical
composition of 49 % Ni - 51 % Ti in weight percent as mixture with an average
dimension of 45mm. Diffusi-on
welding process have been made under argon atmosphere, with a constant load of
5 MPa, under the temperature of 940 and 970 ºC, in 40 and 60 minutes experiment
time. Microstructure examination at bond interface were investigated by optical
microscopy, SEM-EDS. Specimens were tested for shear strength and
metallographic evaluations.  After the
completion of experimental process and relevant test, to prepare the training
and test (checking) set of the network, results were recorded in a file on a
computer. In neural networks training module, different temperatures and
welding periods were used as input, shear strength of bonded specimens at
interface were used as outputs. Then, the neural network was trained using the
prepared training set (also known as learning set). At the end of the training
process, the test data were used to check the system accuracy. As a result the
neural network was found successful in the prediction of diffusion bonding
shear strength and behavior.  

Keywords

Ni-Ti, Diffusion Bonding, Shear Strength, Artificial Neural Network

References

• 1. Igata, N., Urahashi, N., Sasaki, M., Kogo, Y., “Internal friction of Ni-Cu and Ni-Ti-Cu plates produced by lamination process”, Materials Science and Engineering, A 370, 560-563, 2004.
• 2. Lindroos, V.K., Talvitie, M.J., Mater, J., Proc. Technol. 53 273–284, 1995.
• 3. Koker, R., Altinkok, N., “Modeling of The Prediction of Tensile and Density Properties in Particle Reinforced Metal Matrix Composites by Using Neural Networks”, Materials and Design, p. 1-7, 2005.
• 4. Altinkok, N. Koker, R., “Neural Network Approach to Prediction of Bending Strength and Hardening Behavior of Particulate Reinforced (Al–Si–Mg)-Aluminum Matrix Composites”, Materials and Design, 25, 595–602, 2005.
• 5. Avci, E., Turkoglu I., and Poyraz, M., “Intelli-gent Target Recognition on Based Wavelet Pac-ket Neural Network”, Elsevier Expert Systems with Applications, vol. 29, pp.175-182, July, 2005.
• 6. Avci, E., Turkoglu I., and Poyraz, M., “Intelli-gent Target Recognition Based on Wavelet Adaptive Network Based Fuzzy Inference System”, Lecture Notes in Computer Science, Springer-Verlag, vol. 3522, pp. 594-601, May, 2005.
• 7. Chun, M.S., Biglou, J., Lenard, J.G., and Kim, J.G., “Using Neural Networks to Predict Para-meters in The Hot Working of Aluminum Alloys” Journal of Materials Processing Techno-logy, 86, 245–25, 1999.
• 8. Ganesan,G., Raghukandan, K., Karthikeyan, R. and Pai,B.C., “Development of Processing Map for 6061 Al/15% SiCp Through Neural Net-works”, Journal of Materials Processing Techno-logy, 166, 423–429, 2005.
• 9. Jalham, I.S., “A comparative study of some network approaches to predict the effect of the reinforcement content on the hot strength of Al–base composites”, Journal of Materials Proces-sing Technology,166, 392–397, 2005.
• 10. Li, H. J., Qi, L.H., Han, H.M.and Guo, L.J., “Neural Network Modeling and Optimization of Semi-Solid Extrusion for Aluminum Matrix Composites”, Journal of Materials Processing Technology, 151, 126–132, 2004.
• 11. Caligulu, U., “The Investigation of Joinability of Diffusion Bonding with Hot Pressing Manufac-tured AlSiMg-SiCp Reinforced Composites”, Fı-rat Uni. Graduate School of Natural and Applied Sciences Department of Metallurgy Education, Master Thesis, Elazig, 2005.
• 12. Taskin, M. and Caligulu, U., Modelling of microhardness values by means of artificial neural networks of Al/SiCp metal matrix compo-site material couples processed with diffusion method, Mathematical and Computational Applications 11(3), 163-172, 2006.
• 13. Taskin, M., “Diffusion bonding of fine grained high carbon steels in the super plasticity temperature range”, Firat University Graduate School of Natural and Applied Sciences Depart-ment of Metallurgy Education, PhD Thesis, Elazig, 2000.
• 14. Anijdan, S.H.M., Bahrami, A., Hosseini, H.R.M., and Shafyei, A., “Using genetic algorithm and artificial neural network analyses to design an Al–Si casting alloy of minimum porosity”, Materials and Design, 2005.
• 15. Okuyucu, H., Kurt, A., and Arcaklioglu, E., “Artificial neural network application to the friction stir welding of aluminum plates”, Materials and Design, 2005.
• 16. Aydın, M., TR2002 02710 U Patented Diffusion Bonding Machine, Department of Machine Engineering, Faculty of Engineering, University of Dumlipinar, Kütahya, Turkey.