Modeling hot deformation behavior of low-cost Ti-2Al-9.2Mo-2Fe beta titanium alloy using a deep neural network. Issue 5 (May 2019)

• Record Type: Journal Article
• Authors: Li, Cheng-Lin; Narayana, P.L.; Reddy, N.S.; Choi, Seong-Woo; Yeom, Jong-Taek; Hong, Jae-Keun; Park, Chan Hee
• Is Part Of: Journal of materials science & technology. Volume 35:Issue 5(2019)
• Page Start: 907
• Page End: 916
• Publication Date: 2019-05
• Subjects: Deep neural networks -- Back propagation -- Processing map -- Recrystallization -- Beta titanium; Metals -- Periodicals; Materials science -- Periodicals; Materials science; Metals; Periodicals; 620.1105
• DOI: 10.1016/j.jmst.2018.11.018
• Languages: English
• ISSNs: 1005-0302

Abstract

Graphical abstract: Highlights: A low-cost β Ti hot working process was optimized using a deep neural network. DNN flow stress prediction error was 13% lower than in conventional neural networks. A processing map was constructed using isothermal flow stress corrected by DNN. The reliability of the processing map was validated with actual microstructures. The DNN approach effectively predicted unstable and stable processing conditions. Abstract: Ti-2Al-9.2Mo-2Fe is a low-cost β titanium alloy with well-balanced strength and ductility, but hot working of this alloy is complex and unfamiliar. Understanding the nonlinear relationships among the strain, strain rate, temperature, and flow stress of this alloy is essential to optimize the hot working process. In this study, a deep neural network (DNN) model was developed to correlate flow stress with a wide range of strains (0.025–0.6), strain rates (0.01–10 s −1 ) and temperatures (750–1000 °C). The model, which was tested with 96 unseen datasets, showed better performance than existing models, with a correlation coefficient of 0.999. The processing map constructed using the DNN model was effective in predicting the microstructural evolution of the alloy. Moreover, it led to the optimization of hot-working conditions to avoid the formation of brittle precipitates (temperatures of 820–1000 °C and strain rates of 0.01–0.1 s −1 ).