Use of the fuzzy pattern matching method for diagnosis of a plastic injection moulding process

Author

Devillez, A. ; Billaudel, P. ; Bourmaud, A. ; Lecolier, G. Villermain

Author_Institution

Lab. d´ Autom. et de Micro-Electron., Fac. des Sci., Univ. of Reims Champagne-Ardenne, Reims, France

fYear

1999

fDate

Aug. 31 1999-Sept. 3 1999

Firstpage

2114

Lastpage

2119

Abstract

In this paper we propose to use a fuzzy classification method called Fuzzy Pattern Matching for diagnosis of a plastic injection moulding process. We describe the process and we present the classification method. We propose an adaptation of this method to respect the shape of classes. Then we show how it can be used for diagnosis problems by integration of belonging and ambiguity reject options. To finish we present the entire application and we conclude on the performances of this method.

Keywords

fault diagnosis; fuzzy set theory; injection moulding; pattern classification; pattern matching; production engineering computing; ambiguity reject option; belonging option; fuzzy classification method; fuzzy pattern matching method; plastic injection moulding process; process diagnosis; Covariance matrices; Maintenance engineering; Pattern matching; Plastics; Process control; Prototypes; Shape; decision system; diagnosis; fuzzy logic; fuzzy pattern recognition; process control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1999 European

Conference_Location

Karlsruhe

Print_ISBN

978-3-9524173-5-5

Type

conf

Filename

7099631