Research Article
BibTex RIS Cite

Yapay Sinir Ağı Eğitim Algoritmaları ile İki Yönlü Fonksiyonel Kademelendirilmiş Plakalarda Termal Gerilme Analizi

Year 2019, Volume: 11 Issue: 2, 442 - 450, 30.06.2019
https://doi.org/10.29137/umagd.485604

Abstract

Fonksiyonel kademelendirilmiş malzemelerin (FKM) henüz seri üretiminin
yapılmaması nedeniyle hacimsel dağılımının belirlenmesi oldukça önemlidir.
Çünkü hacimsel dağılımın belirlenmesi ile malzemenin emniyetli gerilme
sınırları belirlenmektedir. FKM yüksek sıcaklık tesirinde kullanılmakta olup
termal gerilme sınırları oldukça önemli olmaktadır. Termal gerilme dağılımının
ve seviyelerinin hesaplanması için ise sayısal analiz yöntemleri
kullanılmaktadır. Bu çalışmada, 2B-FK plakaların ısı akısı tesirindeki
termo-mekanik davranışının tespitindeki en önemli parametre olan eşdeğer
gerilme seviyeleri için hacimsel dağılıma bağlı modeller sonlu farklar metodu
(SFM) kullanılarak oluşturulmuştur. Bu modeller yapay sinir ağında (YSA) üç
farklı eğitim algoritması ile elde edilmiştir.

 

Çalışmamızda, 2B-FK
plakaların mevcut şartlar için farklı kompozisyonel gradyant üst değerlerin de
eşdeğer gerilme seviyesinin belirlene bileceği modeller sunulmuştur. Bu
modeller vasıtasıyla SFM göre 340 kat daha hızlı çözüm elde edilmektedir.
Önerilen modeller henüz seri üretimi gerçekleştirilemeyen FKM hem üretiminde
hem de yapılacak teorik çalışmalarda optimum hacimsel dağılıma ulaşmak için yol
gösterici olacaktır. Yapılan çalışmada farklı eğitim algoritmaları için eğitim
aşamaları, performans değerleri ve işlevsellikleri detaylı olarak incelenmiş ve
yorumlanmıştır.

References

  • Shabana Y.M., Noda N. (2001). Thermo-elastic-plastic stresses in functionally graded materials subjected to thermal loading taking residual stresses of the fabrication process into consideration, Composites Part B: Engineering, 32(2). 111-121.
  • Koizumi M., Niino M. (1995 ).Overview of FGM research in Japan, MRS Bulletin. 20(1).19-21.
  • Cho J.R., Ha D.Y. (2002). Optimal tailoring of 2D volume-fraction distributions for heat-resisting functionally graded materials using FDM. Computer Methods in Applied Mechanics and Engineering. 191 (29-30). 3195-3211.
  • Moitaa J.S,. Araújoa A.L., Correia F.V., Soaresa C.M.M, Herskovitsc J. (2018). Material distribution and sizing optimization of functionally graded plateshell structures, Composites Part B: Engineering.142. 263-272.
  • Ootao Y., Tanigawa Y., Nakamura T., (1999). Optimization of material composition of FGM hollow circular cylinder under thermal loading a neural network approach. Composites Part B: Engineering. 30(4). 415-422.
  • Nemat-Alla M. (2003). Reduction of thermal stresses by developing two-dimensional functionally graded materials, International Journal of Solids and Structures, 40(26). 7339-7356.
  • Xu.Y., You.T. (2013). Minimizing thermal residual stresses in ceramic matrix composites by using Iterative MapReduce guided particle swarm optimization algorithm. Composite Structures. 99. 388-396.
  • Jodaei, A. Jalal, M.,Yas, M.H. (2012). Free vibration analysis of functionally graded annular plates by state-space based differential quadrature method and comparative modeling by ANN. Composites: Part B. 43(2). 340-353.
  • Öztürk C. (2011). Yapay Sinir Ağlarının Yapay Arı Kolonisi Algoritması İle eğitilmesi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği. Ocak 2011.
  • Parlos A.G., Muthusami J., Atiya A.F. (2017). Incipient fault detection and identification in progress systems using accelerated neural network learning. Nuclear Technology. 105(2). 145-161.
  • Haykin. S.,2005, Neural networks. Prentice Hall. New Jersey.
  • MATLAB.Mathematical software, version 2009a, TheMathWorks.Available: http://www.mathworks.com.
  • Demirbaş M.D, Çakır D.,(2018). Thermal stress control in functionally graded plates with artificial neural network. ISVOS Journal. 2(1). 39-55.

Thermal Stress Analysis in Two-Directional Functionally Graded Plates with Artificial Neural Network Training Algorithms

Year 2019, Volume: 11 Issue: 2, 442 - 450, 30.06.2019
https://doi.org/10.29137/umagd.485604

Abstract

It is very important to determine the volumetric distribution because Functionally Graded Materials (FGMs) are not mass-produced at present. By determining the volumetric distribution, the allowable stress limits of the material are also determined. FGMs are used in high temperature effects so thermal stress limits become very important. For the calculation of thermal stress distribution and levels, numerical analysis methods are used. In this study, the models based on volumetric distribution for the equivalent stress levels, which are the most important parameter for the determination of the thermo-mechanical behavior of the 2D-FG plates, were formed by using the finite difference method (FDM). These models were obtained by three different training algorithms in artificial neural network (ANN).

In this study, the models which can determine the equivalent stress level of different composition gradient exponent values for the existing conditions of the 2D-FGs are presented. These models provide 340 times faster solution than the FDM. Suggested models will be the guide to reach the optimum volumetric distribution in both production and theoretical studies of FGMs which cannot be mass-produced yet. In the study, the training stages, performance values and functionality of different training algorithms are examined and interpreted in detail.

References

  • Shabana Y.M., Noda N. (2001). Thermo-elastic-plastic stresses in functionally graded materials subjected to thermal loading taking residual stresses of the fabrication process into consideration, Composites Part B: Engineering, 32(2). 111-121.
  • Koizumi M., Niino M. (1995 ).Overview of FGM research in Japan, MRS Bulletin. 20(1).19-21.
  • Cho J.R., Ha D.Y. (2002). Optimal tailoring of 2D volume-fraction distributions for heat-resisting functionally graded materials using FDM. Computer Methods in Applied Mechanics and Engineering. 191 (29-30). 3195-3211.
  • Moitaa J.S,. Araújoa A.L., Correia F.V., Soaresa C.M.M, Herskovitsc J. (2018). Material distribution and sizing optimization of functionally graded plateshell structures, Composites Part B: Engineering.142. 263-272.
  • Ootao Y., Tanigawa Y., Nakamura T., (1999). Optimization of material composition of FGM hollow circular cylinder under thermal loading a neural network approach. Composites Part B: Engineering. 30(4). 415-422.
  • Nemat-Alla M. (2003). Reduction of thermal stresses by developing two-dimensional functionally graded materials, International Journal of Solids and Structures, 40(26). 7339-7356.
  • Xu.Y., You.T. (2013). Minimizing thermal residual stresses in ceramic matrix composites by using Iterative MapReduce guided particle swarm optimization algorithm. Composite Structures. 99. 388-396.
  • Jodaei, A. Jalal, M.,Yas, M.H. (2012). Free vibration analysis of functionally graded annular plates by state-space based differential quadrature method and comparative modeling by ANN. Composites: Part B. 43(2). 340-353.
  • Öztürk C. (2011). Yapay Sinir Ağlarının Yapay Arı Kolonisi Algoritması İle eğitilmesi. Erciyes Üniversitesi Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği. Ocak 2011.
  • Parlos A.G., Muthusami J., Atiya A.F. (2017). Incipient fault detection and identification in progress systems using accelerated neural network learning. Nuclear Technology. 105(2). 145-161.
  • Haykin. S.,2005, Neural networks. Prentice Hall. New Jersey.
  • MATLAB.Mathematical software, version 2009a, TheMathWorks.Available: http://www.mathworks.com.
  • Demirbaş M.D, Çakır D.,(2018). Thermal stress control in functionally graded plates with artificial neural network. ISVOS Journal. 2(1). 39-55.
There are 13 citations in total.

Details

Primary Language Turkish
Journal Section Articles
Authors

Munise Didem Demirbaş

Didem Çakır

Publication Date June 30, 2019
Submission Date October 23, 2018
Published in Issue Year 2019 Volume: 11 Issue: 2

Cite

APA Demirbaş, M. D., & Çakır, D. (2019). Yapay Sinir Ağı Eğitim Algoritmaları ile İki Yönlü Fonksiyonel Kademelendirilmiş Plakalarda Termal Gerilme Analizi. International Journal of Engineering Research and Development, 11(2), 442-450. https://doi.org/10.29137/umagd.485604

All Rights Reserved. Kırıkkale University, Faculty of Engineering and Natural Science.