Flow Stress Prediction of Ti-6Al-4V Alloy at Elevated Temperature Using Artificial Neural Network

Abstract:

Flow stress during hot deformation depends mainly on the strain, strain rate and temperature, and shows a complex nonlinear relationship with them. In this work, experimental flow stress have been predicted for Ti-6Al-4V alloy using isothermal uniaxial tensile tests ranging from 323K to 673K at an interval of 50K and strain rates 10^-5, 10^-4, 10^-3 and 10^-2 s^-1. Based on the input variables strain, strain rate and temperature, a back propagation neural network model has been developed to predict the flow stress as output. The whole experimental data is randomly divided in two parts: 90% data as training data and 10% data as testing data. The artificial neural network enhanced with differential evolution algorithm is successfully trained based on the training data and employed to predict the flow stress values for the testing data, which were compared with the experimental values. Correlation coefficient for training and testing data is found to be 0.9997 and 0.9985 respectively. Based on the correlation coefficient, it indicates that predicted flow stress by using artificial neural network is in good agreement with experimental results.

• Periodical: Applied Mechanics and Materials (Volume 612)
• Pages: 83-88
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.612.83
• Online since: August 2014
• Authors: Nitin Kotkunde*, Aditya Balu, Amit Kumar Gupta, Swadesh Kumar Singh
• Keywords: ANN, Flow Stress Prediction, Tensile Testing, Ti-6Al-4V Alloy

References

[1] Joseph D. Beal, Rodney Boyer, and Daniel Sanders, The Boeing Company, "Forming of Titanium and Titanium Alloys", ASM Handbook, Volume 14B: Metalworking: Sheet Forming, pp.656-669.

DOI: 10.31399/asm.hb.v14b.a0005146

[2] Rodney Boyer, Gerhard Welsch, E.W. Collings, "Materials Properties Handbook: Titanium Alloys", ASM International, ISBN 0-87170-481-1, pp.483-484.

[3] Y.C. Lin , Xiao-Min Chen, "A critical review of experimental results and constitutive descriptions for metals and alloys in hot working", Materials and Design 32 (2011) 1733–1759.

DOI: 10.1016/j.matdes.2010.11.048

[4] Guo Z, Sha W. "Modelling the correlation between processing parameters and properties of maraging steels using artificial neural network". Comput Mater Sci. 2004; 29:12–28.

DOI: 10.1016/s0927-0256(03)00092-2

[5] Carlos García-Garino, Felipe Gabaldónb, José M. Goicolea, "Finite element simulation of the simple tension test in metals", Finite Elements in Analysis and Design 42 (2006) 1187 – 1197.

DOI: 10.1016/j.finel.2006.05.004

[6] Nitin Kotkunde, Hansoge Nitin Krishnamurthy, Pavan Puranik, Amit Kumar Gupta, Swadesh Kumar Singh, "Microstructure study and constitutive modeling of Ti–6Al–4V alloy at elevated temperatures", Materials and Design 54 (2014) 96–103.

DOI: 10.1016/j.matdes.2013.08.006

[7] Madakasira Prabhakar Phaniraj, Ashok Kumar Lahiri, "The applicability of neural network model to predict flow stress for carbon steels", Journal of Materials Processing Technology 141 (2003) 219–227.

DOI: 10.1016/s0924-0136(02)01123-8

[8] Y.C. Lin a, Jun Zhang , Jue Zhong, "Application of neural networks to predict the elevated temperature flow behavior of a low alloy steel", Computational Materials Science 43 (2008) 752–758.

DOI: 10.1016/j.commatsci.2008.01.039

[9] Li Ping , Xue Kemin , Lu Yan, Tan Jianrong, "Neural network prediction of flow stress of Ti–15–3 alloy under hot compression", Journal of Materials Processing Technology 148 (2004) 235–238.

DOI: 10.1016/j.jmatprotec.2003.07.013

[10] Yanchun Zhu, Weidong Zeng , Yu Sun, Fei Feng, Yigang Zhou, "Artificial neural network approach to predict the flow stress in the isothermal compression of as-cast TC21 titanium alloy", Computational Materials Science 50 (2011) 1785–1790.

DOI: 10.1016/j.commatsci.2011.01.015