Role of Grain Size and Oxide Dispersion Nanoparticles on the Hot Deformation Behavior of AA6063: Experimental and Artificial Neural Network Modeling Investigations

다국어 초록 (Multilingual Abstract)

The hot deformation behavior of coarse-grained (CG), ultrafine-grained (UFG), and oxide dispersion-strengthened (ODS)AA6063 is experimentally recognized though carrying out compression tests at different temperatures (300–450 °C) andstrain rates (0.01–1 s−1). Microstructural studies conducted by TEM and EBSD indicate that dynamic softening mechanismsincluding dynamic recovery and dynamic recrystallization become operative in all the investigated materials depending on theregime of deformation. Moreover, the high temperature flow behavior is considerably influenced by the initial grain structureand the presence of reinforcement particles. The constitutive and artificial neural network (ANN) models were used to studythe high-temperature flow behavior of the investigated alloys. To establish an accurate ANN model, material characteristicsalong with the processing parameters are deliberated. An Arrhenius type constitutive model with a strain-compensation termis employed to predict the flow stress of AA6063 alloys. The relative error associated with the constitutive and ANN modelsin the prediction of the flow stress is obtained 9.56% and 2.02%, respectively. The analysis indicates that the developed ANNmodel is more accurate in the prediction of flow stress with at least 78% less error in comparison to the constitutive model.

참고문헌 (Reference)

1 C. Bruni, 177 : 323-, 2006

2 A. Asgharzadeh, 106 : 315-, 2020

3 N. S. Reddy, 492 : 276-, 2008

4 Y. H. Xiao, 528 : 6510-, 2011

5 Y. B. Tan, 741 : 85-, 2018

6 X. Qin, 770 : 507-, 2019

7 J. Yan, 27 : 638-, 2017

8 L. Liu, 29 : 448-, 2019

9 Y. Xia, 30 : 134-, 2020

10 S. Kumar, 27 : 2024-, 2018

11 C. Huang, 11 : 855-, 2018

12 S. Mandal, 9 : 237-, 2009

13 J. Liu, 103 : 200-, 2000

14 G. Ji, 528 : 4774-, 2011

15 O. Sabokpa, 39 : 390-, 2012

16 R. Kapoor, 169 : 199-, 2005

17 A. Gholamzadeh, 36 : 252-, 2009

18 I. S. Jalham, 166 : 392-, 2005

19 L. X. Kong, 102 : 84-, 2000

20 P. D. Hodgson, 87 : 131-, 1999

21 M. Li, 49 : 203-, 2002

22 A. Canakci, 78 : 305-, 2015

23 H. Asgharzadeh, 527 : 4897-, 2010

24 H. Asgharzadeh, 528 : 3981-, 2011

25 H. Asgharzadeh, 42 : 816-, 2011

26 C. M. Sellars, 14 : 1136-, 1966

27 H. Asgharzadeh, 75 : 108-, 2013

28 H. Asgharzadeh, 66 : 911-, 2012

29 Ö. Kişi, 12 : 434-, 2005

30 C. Lv, 14 : 3436-, 2018

31 S. Karsoliya, 3 : 714-, 2012

32 K. P. Rao, 56 : 897-, 1996

33 Y. C. Lin, 43 : 752-, 2008

34 A. Asgharzadeh, 25 : 1076-, 2016

35 C. Chen, 25 : 411-, 2007

36 A. Asgharzadeh, 55 : 7938-, 2020

37 R. H. Wu, 116 : 211-, 2001

38 Q. Dai, 29 : 2252-, 2019

39 M. Berry, "Data Mining Techniques" Wiley 1997