Prediction of crack growth propagation of a super alloy through ANN modeling
Linear-elastic fracture mechanics based technique was used to measure the fracture toughness in terms of K1C of a solid solution super alloy. Due to thermal fatigue and high temperature exposure for various application of Alloy 617, it was demanded to measure crack growth behaviour of this alloy. Pr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Trans Tech Publications Ltd., Switzerland
2015
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/49212/ http://irep.iium.edu.my/49212/1/CGR_paper.pdf |
| Summary: | Linear-elastic fracture mechanics based technique was used to measure the fracture toughness in terms of K1C of a solid solution super alloy. Due to thermal fatigue and high temperature exposure for various application of Alloy 617, it was demanded to measure crack growth behaviour of this alloy. Pre-cracked compact tension (CT) specimens ware used to determine the crack growth rate (CGR) of alloy 617 by direct current potential drop (DCPD) in-situ crack monitoring technique. Artificial Neural network (ANN) statistical model computed different fracture parameters from experimental inputs by feeding information to the network. This feed-forward network calculated the threshold fracture toughness, number of cycle to failure, slope of the Paris curve for the alloy at different temperatures and load ratios. The computational model correlates and converges with the experimental results with a maximum deviation of 6%. Thus, the model is recommended for complex and stochastic application of the nickel base super alloy 617. |
|---|