Data driven knowledge extraction of materials properties

Author

Kandola, J.S. ; Gunn, S.R. ; Sinclair, I. ; Reed, P.A.S.

Author_Institution

Sch. of Eng. Sci., Southampton Univ., UK

Volume

1

fYear

1999

fDate

36342

Firstpage

361

Abstract

The problem of modelling a large commercial materials dataset using advanced adaptive numeric methods is described. The various approaches are outlined, emphasising their characteristics with respect to generalisation, performance and transparency. A highly novel support vector machine (SVM) approach is taken incorporating a high degree of transparency via a full analysis of variance (ANOVA) expansion. Using an example which predicts 0.2% proof stress from a set of materials features, different modelling techniques are compared by benchmarking against independent test data

Keywords

Bayes methods; knowledge acquisition; materials properties; multilayer perceptrons; ANOVA expansion; advanced adaptive numeric methods; analysis of variance expansion; data driven knowledge extraction; generalisation; large commercial materials dataset; performance; proof stress; support vector machine approach; transparency; Analysis of variance; Data engineering; Data mining; Gunn devices; Intersymbol interference; Material properties; Predictive models; Production; Support vector machines; Thermomechanical processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Processing and Manufacturing of Materials, 1999. IPMM '99. Proceedings of the Second International Conference on

Conference_Location

Honolulu, HI

Print_ISBN

0-7803-5489-3

Type

conf

DOI

10.1109/IPMM.1999.792507

Filename

792507