Title: Using neural network techniques to predict crack growth rates of stress corrosion

Authors: Pai-Chuan Lu

Addresses: Department of Mechanical Engineering, National Lien Ho College of Technology and Commerce, 1 Lien Kung Rd., Miaoli 36012, Taiwan, ROC

Abstract: An artificial neural network (ANN) with the learning rule of a stochastic process has been developed to describe intergranular stress corrosion cracking (IGSCC) in sensitized Type 304 stainless steel in high temperature aqueous solutions. The ANN predictions of crack growth rate (CGR) versus oxygen concentration, flow velocity, stress intensity, hydrogen concentration and ECP have been successfully presented. Finally, the steady state crack growth rate predicted by the ANN at low ECP values has been verified by Wilkinson|s theory.

Keywords: artificial neural networks; ANNs; crack growth rate; IGSCC; intergranular stress corrosion cracking; stochastic processes; stainless steel; stress corrosion; oxygen concentration; flow velocity; stress intensity; hydrogen concentration; ECP; electrochemical corrosion potential.

DOI: 10.1504/IJMPT.1997.036370

International Journal of Materials and Product Technology, 1997 Vol.12 No.4/5/6, pp.329 - 345

Published online: 02 Nov 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article