Capability of a Feed-Forward Artificial Neural Network to Predict the Constitutive Flow Behavior of As Cast 304 Stainless Steel Under Hot Deformation

[+] Author and Article Information
Sumantra Mandal1

Materials Technology Division, Indira Gandhi Centre for Atomic Research, Kalpakkam-603102, Tamil Nadu, Indiasumantra@igcar.gov.in

P. V. Sivaprasad, S. Venugopal

Materials Technology Division, Indira Gandhi Centre for Atomic Research, Kalpakkam-603102, Tamil Nadu, India


Corresponding author.

J. Eng. Mater. Technol 129(2), 242-247 (Aug 17, 2006) (6 pages) doi:10.1115/1.2400276 History: Received December 15, 2005; Revised August 17, 2006

A model is developed to predict the constitutive flow behavior of as cast 304 stainless steel during hot deformation using artificial neural network (ANN). The inputs of the neural network are strain, strain rate, and temperature, whereas flow stress is the output. Experimental data obtained from hot compression tests in the temperature range 10231523K, strain range 0.10.5, and strain rate range 103102s1 are employed to develop the model. A three-layer feed-forward ANN is trained with standard back propagation and some upgraded algorithms like resilient propagation (Rprop) and superSAB. The performances of these algorithms are evaluated using a wide variety of standard statistical indices. The results of this study show that Rprop algorithm performs better as compared to others and thereby considered as the most efficient algorithm for the present study. It has been shown that the developed ANN model can efficiently and accurately predict the hot deformation behavior of as cast 304 stainless steel. Finally, an attempt has been made to quantify the extrapolation ability of the developed network.

Copyright © 2007 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

Schematic of the ANN for flow stress prediction in as cast 304 stainless steel

Grahic Jump Location
Figure 2

Predicted flow stress (MPa) from the neural network versus experimental values for the: (a) training; and (b) test using Rprop algorithm

Grahic Jump Location
Figure 3

Simulated flow behavior of as cast 304 stainless steel at a strain rate: (a)10−3s−1; and (b)100s−1

Grahic Jump Location
Figure 4

Optical micrograph of the as cast 304 stainless steel: (a) initial microstructure, (b)1523K and 10−2s−1; (c)1173K and 10s−1; and (d)1273K and 1s−1 [strain level in (b), (c), and (d) is 0.5]

Grahic Jump Location
Figure 5

Extrapolation ability of the network at a strain of: (a) 0.2, and (b) 0.1

Grahic Jump Location
Figure 6

Performance of the ANN model with noisy data set during: (a) training; and (b) testing

Grahic Jump Location
Figure 7

Performance of the ANN model with noisy training data but original test data




Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In