You are not logged in.

Improvement of the prediction accuracy and efficiency of hot strength of austenitic steels with optimised ANN training schemes

Wang,B, Kong, L.X., Hodgson, P.D. and Collinson, D.C. 1998, Improvement of the prediction accuracy and efficiency of hot strength of austenitic steels with optimised ANN training schemes, Metals and materials international, vol. 4, no. 4, pp. 823-826.

Attached Files
Name Description MIMEType Size Downloads

Title Improvement of the prediction accuracy and efficiency of hot strength of austenitic steels with optimised ANN training schemes
Author(s) Wang,B
Kong, L.X.
Hodgson, P.D.
Collinson, D.C.
Journal name Metals and materials international
Volume number 4
Issue number 4
Start page 823
End page 826
Total pages 4
Publisher Springer Verlag
Place of publication Berlin, Germany
Publication date 1998-08
ISSN 1598-9623
Keyword(s) artificial neural network
austenitic steels
hot strength
model generalisation
prediction accuracy
Summary The hot strength of austenitic steels of different carbon contents was modelled using an artificial neural network (ANN) model with optimum training data. As training data employed in a traditional neural network model were randomly selected from experimental data, they were not representative and the prediction accuracy and efficiency were therefore significantly affected. In this work, only representatively experimental data were used for training and during the procedure, one tenth of the training data extracted from experiment were used for testing the training model and terminating the modelling. The effects of the carbon con tent on flow stress, peak strains and peak stresses observed from the experiment for both training and test data were accurately represented with the ANN scheme reported in this work.
Language eng
Field of Research 0912 Materials Engineering
Socio Economic Objective 970112 Expanding Knowledge in Built Environment and Design
HERDC Research category C1.1 Refereed article in a scholarly journal
Copyright notice ©1998, Springer Verlag
Persistent URL http://hdl.handle.net/10536/DRO/DU:30070630

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 2 times in TR Web of Science
Scopus Citation Count Cited 2 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 24 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Thu, 12 Mar 2015, 14:20:56 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.