Adaptive numerical modelling of commercial aluminium plate performance
Adaptive numerical modelling of commercial aluminium plate performance
Adaptive numerical methods, such as neural networks, have received considerable attention in recent years in relation to the modelling of complex physical systems. In this work a variety of such methods have been applied to the modelling/data mining of commercial materials production data, thereby avoiding the scale-up problems associated with laboratory scale investigations of materials behaviour. It is shown that adaptive numerical methods may determine valuable empirical models from such complex databases, whilst the value of transparent modelling methods (where the underlying relationships between input variables and modelled characteristics may be clearly visualised) is highlighted in providing model confidence and the potential to extract novel physical understanding.
adaptive numeric methods, data mining, empirical modelling, fuzzy logic, neural networks, support vector machines
533-538
Trans Tech Publications Ltd
Christensen, S.W.
c5995cdb-2a14-478a-8c98-6c9f11d65b09
Kandola, J.S.
c976459a-d502-4688-b741-334c06796ca8
Femminella, O.P.
be8a8548-2f97-4d11-bd06-012e27609627
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
Sinclair, I.
b7a58838-8f58-4010-a06b-91c6512bcfaa
November 2000
Christensen, S.W.
c5995cdb-2a14-478a-8c98-6c9f11d65b09
Kandola, J.S.
c976459a-d502-4688-b741-334c06796ca8
Femminella, O.P.
be8a8548-2f97-4d11-bd06-012e27609627
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Reed, P.A.S.
8b79d87f-3288-4167-bcfc-c1de4b93ce17
Sinclair, I.
b7a58838-8f58-4010-a06b-91c6512bcfaa
Christensen, S.W., Kandola, J.S., Femminella, O.P., Gunn, S.R., Reed, P.A.S. and Sinclair, I.
(2000)
Adaptive numerical modelling of commercial aluminium plate performance.
Starke, Jr., E.A., Sanders, T.H. and Cassada, W.A.
(eds.)
In Aluminium Alloys: Their Physical and Mechanical Properties.
Trans Tech Publications Ltd.
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
Adaptive numerical methods, such as neural networks, have received considerable attention in recent years in relation to the modelling of complex physical systems. In this work a variety of such methods have been applied to the modelling/data mining of commercial materials production data, thereby avoiding the scale-up problems associated with laboratory scale investigations of materials behaviour. It is shown that adaptive numerical methods may determine valuable empirical models from such complex databases, whilst the value of transparent modelling methods (where the underlying relationships between input variables and modelled characteristics may be clearly visualised) is highlighted in providing model confidence and the potential to extract novel physical understanding.
This record has no associated files available for download.
More information
Published date: November 2000
Additional Information:
Series ISSN 0255-5476
Venue - Dates:
7th International Conference ICAA7, Charlottesville, Virginia, 2000-04-09 - 2000-04-14
Keywords:
adaptive numeric methods, data mining, empirical modelling, fuzzy logic, neural networks, support vector machines
Organisations:
Electronic & Software Systems
Identifiers
Local EPrints ID: 252079
URI: http://eprints.soton.ac.uk/id/eprint/252079
ISSN: 0255-5476
PURE UUID: 61ed082e-9794-45b5-9bf8-369c1018a3df
Catalogue record
Date deposited: 29 Nov 2003
Last modified: 08 Dec 2023 02:33
Export record
Contributors
Author:
S.W. Christensen
Author:
J.S. Kandola
Author:
O.P. Femminella
Author:
S.R. Gunn
Author:
I. Sinclair
Editor:
E.A. Starke, Jr.
Editor:
T.H. Sanders
Editor:
W.A. Cassada
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
