Constitutive flow behaviour of austenitic stainless steels under hot deformation: artificial neural network modelling to understand, evaluate and predict

An artificial neural network (ANN) model is developed to predict the constitutive flow behaviour of austenitic stainless steels during hot deformation. The input parameters are alloy composition and process variables whereas flow stress is the output. The model is based on a three-layer feed-forward ANN with a back-propagation learning algorithm. The neural network is trained with an in-house database obtained from hot compression tests on various grades of austenitic stainless steels. The performance of the model is evaluated using a wide variety of statistical indices. Good agreement between experimental and predicted data is obtained. The correlation between individual alloying elements and high temperature flow behaviour is investigated by employing the ANN model. The results are found to be consistent with the physical phenomena. The model can be used as a guideline for new alloy development.

[1]  John G. Lenard,et al.  Using neural networks to predict parameters in the hot working of aluminum alloys , 1999 .

[2]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[3]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[4]  James A. Anderson,et al.  An Introduction To Neural Networks , 1998 .

[5]  D. L. Baragar,et al.  The high temperature and high strain-rate behaviour of a plain carbon and an HSLA steel , 1987 .

[6]  Z. Guo,et al.  Modelling beta transus temperature of titanium alloys using artificial neural network , 2005 .

[7]  W. Sha,et al.  Modelling the correlation between processing parameters and properties of maraging steels using artificial neural network , 2004 .

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Zhongya Zhang,et al.  Artificial neural networks applied to polymer composites: a review , 2003 .

[10]  S. Venugopal,et al.  Optimum design of a hot extrusion process for AISI type 304L stainless steel using a model for the evolution of microstructure , 2002 .

[11]  Ashu Jain,et al.  A comparative analysis of training methods for artificial neural network rainfall-runoff models , 2006, Appl. Soft Comput..

[12]  Y. Prasad,et al.  Effect of stacking fault energy on the dynamic recrystallization during hot working of FCC metals: A study using processing maps , 1991 .

[13]  Kamineni Pitcheswara Rao,et al.  Development of Constitutive Relationships Using Compression Testing of a Medium Carbon Steel , 1992 .

[14]  K. G. Samuel,et al.  Influence of temperature and grain size on the tensile ductility of AISI 316 stainless steel , 1985 .

[15]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[16]  U. F. Kocks,et al.  Kinetics of flow and strain-hardening☆ , 1981 .

[17]  J. Morris.  Dynamic strain aging in a Ti-modified 316 stainless steel , 1971 .

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

[19]  Yuri Estrin,et al.  A unified phenomenological description of work hardening and creep based on one-parameter models , 1984 .

[20]  Julian D. Olden,et al.  Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks , 2002 .

[21]  P. Sivaprasad,et al.  Activation energy for serrated flow in a 15Cr5Ni Ti-modified austenitic stainless steel , 1992 .

[22]  Bart Kosko,et al.  Neural networks and fuzzy systems , 1998 .

[23]  Peter Hodgson,et al.  The prediction of the hot strength in steels with an integrated phenomenological and artificial neural network model , 1999 .

[24]  Y. Bergström,et al.  A dislocation model for the stress-strain behaviour of polycrystalline α-Fe with special emphasis on the variation of the densities of mobile and immobile dislocations , 1970 .

[25]  Robert A. Varin,et al.  The Effects of Temperature and Strain Rate on the Plastic Flow and Ductility of Ultrafine-Grained Type 316 Austenitic Stainless Steel , 1987 .

[26]  S. Venugopal,et al.  Processing map for cold and hot working of stainless steel type AISI 304 , 1993 .

[27]  D. Ponge,et al.  Necklace formation during dynamic recrystallization: mechanisms and impact on flow behavior , 1998 .

[28]  G. Gottstein,et al.  Nucleation mechanisms of dynamic recrystallization in austenitic steel alloy 800H , 1998 .

[29]  A. T. C. Goh,et al.  Back-propagation neural networks for modeling complex systems , 1995, Artif. Intell. Eng..

[30]  Prasad K. Yarlagadda,et al.  Neural network approach to flow stress evaluation in hot deformation , 1995 .

[31]  S. Venugopal,et al.  Processing map for hot working of stainless steel type AISI 316L , 1993 .

[32]  Wei Sha,et al.  Comment on “Prediction of the flow stress of 0.4C–1.9Cr–1.5Mn–1.0Ni–0.2Mo steel during hot deformation” by R.H. Wu et al. [J. Mater. Process. Technol. 116 (2001) 211] , 2006 .

[33]  H. Feichtinger,et al.  On the Solubility of Nitrogen in Liquid Iron and Steel Alloys Using Elevated Pressure / Über die Löslichkeit von Stickstoff in Eisen- und Stahllegierungen unter erhöhtem Druck , 1991 .

[34]  W. Sha,et al.  Application of artificial neural networks for modelling correlations in titanium alloys , 2004 .

[35]  K. G. Samuel,et al.  Serrated yielding in AISI 316 stainless steel , 1988 .

[36]  J. Simmons,et al.  Overview: high-nitrogen alloying of stainless steels , 1996 .

[37]  Sungil Kim,et al.  Dynamic recrystallization behavior of AISI 304 stainless steel , 2001 .

[38]  Maysam F. Abbod,et al.  Hybrid modelling of aluminium–magnesium alloys during thermomechanical processing in terms of physically-based, neuro-fuzzy and finite element models , 2003 .

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

[40]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[41]  C. M. Sellars,et al.  Development of constitutive equations for modelling of hot rolling , 2000 .

[42]  Y. Prasad,et al.  Identification of processing parameters for Fe–15Cr–2.2Mo–15Ni–0.3Ti austenitic stainless steel using processing maps , 2001 .

[43]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .