Constructing processing map of Ti40 alloy using artificial neural network

Based on the experimental data of Ti40 alloy obtained from Gleeble-1500 thermal simulator, an artificial neural network model of high temperature flow stress as a function of strain, strain rate and temperature was established. In the network model, the input parameters of the model are strain, logarithm strain rate and temperature while flow stress is the output parameter. Multilayer perceptron (MLP) architecture with back-propagation algorithm is utilized. The present study achieves a good performance of the artificial neural network (ANN) model, and the predicted results are in agreement with experimental values. A processing map of Ti40 alloy is obtained with the flow stress predicted by the trained neural network model. The processing map developed by ANN model can efficiently track dynamic recrystallization and flow localization regions of Ti40 alloy during deforming. Subsequently, the safe and instable domains of hot working of Ti40 alloy are identified and validated through microstructural investigations.

[1]  Y. V. R. K. Prasad,et al.  Recent Advances in the Science of Mechanical processing , 1990 .

[2]  Wei Sha,et al.  Modelling the correlation between processing parameters and properties in titanium alloys using artificial neural network , 2000 .

[3]  J. T. Liu,et al.  PREDICTION OF FLOW STRESS OF HIGH-SPEED STEEL DURING HOT DEFORMATION BY USING BP ARTIFICIAL NEURAL NETWORK , 2000 .

[4]  M. P. Phaniraj,et al.  The applicability of neural network model to predict flow stress for carbon steels , 2003 .

[5]  Z. M. Wang,et al.  Titanium alloys and their machinability—a review , 1997 .

[6]  Zbigniew Gronostajski,et al.  The deformation processing map for control of microstructure in CuAl9.2Fe3 aluminium bronze , 2002 .

[7]  X. M. Zhang,et al.  Hot workability and microstructure evolution of highly β stabilised Ti–25V–15Cr–0·3Si alloy , 2008 .

[8]  H. K. D. H. Bhadeshia,et al.  Performance of neural networks in materials science , 2009 .

[9]  H. Wu,et al.  The second phases in Ti40 burn resistant alloy after high temperature exposure for a long time , 2002 .

[10]  Baldev Raj,et al.  Artificial neural network modeling of composition–process–property correlations in austenitic stainless steels , 2008 .

[11]  Y. S. Tarng,et al.  A comparison between the back-propagation and counter-propagation networks in the modeling of the TIG welding process , 1998 .

[12]  Y. Q. Zhao,et al.  The role of interface in the burning of titanium alloys , 1999 .

[13]  S. Venugopal,et al.  Artificial neural network modeling to evaluate and predict the deformation behavior of stainless steel type AISI 304L during hot torsion , 2009, Appl. Soft Comput..

[14]  Jiecai Han,et al.  Processing maps and hot workability of Super304H austenitic heat-resistant stainless steel , 2009 .

[15]  Weidong Zeng,et al.  Fracture criterion for predicting surface cracking of Ti40 alloy in hot forming processes , 2009 .

[16]  M. Yao,et al.  Characterization of hot deformation behavior of a Ni-base superalloy using processing map , 2009 .

[17]  K. L. Edwards,et al.  The use of artificial neural networks in materials science based research , 2007 .

[18]  S. M. Doraivelu,et al.  Modeling of dynamic material behavior in hot deformation: Forging of Ti-6242 , 1984 .

[19]  Y. Prasad,et al.  Hot deformation mechanisms in metastable beta titanium alloy Ti–10V–2Fe–3Al , 2001 .

[20]  Yongqing Zhao,et al.  Effect of major alloying elements on microstructure and mechanical properties of a highly β stabilized titanium alloy , 2009 .

[21]  Yongqing Zhao,et al.  Research on thermal stability of Ti40 alloy at 550 °C , 2008 .

[22]  J. K. Chakravartty,et al.  Use of artificial neural networks to predict the deformation behavior of Zr-2.5Nb-0.5Cu , 2005 .