The application of neural computing methods to the modelling of fatigue in Ni-base superalloys
The application of neural computing methods to the modelling of fatigue in Ni-base superalloys
The current financial climate is driving a move towards increased use of computer modelling techniques in alloy design and development in order to reduce cost. In this paper the potential for use of neural computing methods in the prediction of fatigue resistance in Ni-base superalloys is assessed. Initial work has been conducted on the Stage II (Paris regime) behaviour, as the literature indicates that this is the simplest region of the fatigue crack growth curve to predict, with an approximately linear relationship existing between log(da/dN and log(AK), and the crack growth rates being principally affected by temperature, Young’s modulus and yield strength. These three parameters were chosen for initial data collection and modelling. The predictions made are of fatigue life, calculated from the slope and intercept values of the linear portion of the log-log fatigue crack growth curve. A test dataset has been successfully predicted along with the trends in the data. The effect of adding ultimate tensile strength and electron valencies as inputs to the model is assessed. It is shown that validation of models produced against metallurgical experience, and careful construction of the database are important conditions for effective use of neural network models for fatigue life predictions.
087339352X
409-417
Schooling, J.M.
1bc4491f-376d-4fb5-b6b6-204bb2448199
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
1996
Schooling, J.M.
1bc4491f-376d-4fb5-b6b6-204bb2448199
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
Schooling, J.M. and Reed, P.A.S.
(1996)
The application of neural computing methods to the modelling of fatigue in Ni-base superalloys.
In,
Kissinger, R.D., Deye, D.J., Anton, D.L., Cetel, A.D., Nathal, M.V., Pollock, T.M. and Woodford, D.A.
(eds.)
Superalloys 1996.
Eighth International Symposium on Superalloys (21/09/96 - 25/09/96)
Warrendale, USA.
TMS, .
Record type:
Book Section
Abstract
The current financial climate is driving a move towards increased use of computer modelling techniques in alloy design and development in order to reduce cost. In this paper the potential for use of neural computing methods in the prediction of fatigue resistance in Ni-base superalloys is assessed. Initial work has been conducted on the Stage II (Paris regime) behaviour, as the literature indicates that this is the simplest region of the fatigue crack growth curve to predict, with an approximately linear relationship existing between log(da/dN and log(AK), and the crack growth rates being principally affected by temperature, Young’s modulus and yield strength. These three parameters were chosen for initial data collection and modelling. The predictions made are of fatigue life, calculated from the slope and intercept values of the linear portion of the log-log fatigue crack growth curve. A test dataset has been successfully predicted along with the trends in the data. The effect of adding ultimate tensile strength and electron valencies as inputs to the model is assessed. It is shown that validation of models produced against metallurgical experience, and careful construction of the database are important conditions for effective use of neural network models for fatigue life predictions.
This record has no associated files available for download.
More information
Published date: 1996
Venue - Dates:
Eighth International Symposium on Superalloys, Champion, USA, 1996-09-21 - 1996-09-25
Identifiers
Local EPrints ID: 21649
URI: http://eprints.soton.ac.uk/id/eprint/21649
ISBN: 087339352X
PURE UUID: 7619d983-0a16-4aa0-b102-5b7afa23a904
Catalogue record
Date deposited: 14 Mar 2007
Last modified: 12 Dec 2021 02:47
Export record
Contributors
Author:
J.M. Schooling
Editor:
R.D. Kissinger
Editor:
D.J. Deye
Editor:
D.L. Anton
Editor:
A.D. Cetel
Editor:
M.V. Nathal
Editor:
T.M. Pollock
Editor:
D.A. Woodford
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics