Please use this identifier to cite or link to this item:
Title: Support vector machines for quality monitoring in a plastic injection molding process
Authors: Ribeiro, Bernardete 
Keywords: Fault detection and diagnosis; Kernel learning methods; Model selection; Radial basis function (RBF) neural networks (NNS); Support vector machines (SVMs)
Issue Date: Aug-2005
Publisher: IEEE
Citation: IEEE Transactions on Systems, Man, and Cybernetics - Part C: Applications and Reviews. 35:3 (2005) 401-410
Abstract: Support vector machines (SVMs) are receiving increased attention in different application domains for which neural networks (NNs) have had a prominent role. However, in quality monitoring little attention has been given to this more recent development encompassing a technique with foundations in statistic learning theory. In this paper, we compare C-SVM and ν-SVM classifiers with radial basis function (RBF) NNs in data sets corresponding to product faults in an industrial environment concerning a plastics injection molding machine. The goal is to monitor in-process data as a means of indicating product quality and to be able to respond quickly to unexpected process disturbances. Our approach based on SVMs exploits the first part of this goal. Model selection which amounts to search in hyperparameter space is performed for study of suitable condition monitoring. In the multiclass problem formulation presented, classification accuracy is reported for both strategies. Experimental results obtained thus far indicate improved generalization with the large margin classifier as well as better performance enhancing the strength and efficacy of the chosen model for the practical case study
ISSN: 1094-6977
DOI: 10.1109/TSMCC.2004.843228
Rights: openAccess
Appears in Collections:FCTUC Eng.Informática - Artigos em Revistas Internacionais

Files in This Item:
File Description SizeFormat
Support vector machines for quality monitoring.pdf794.17 kBAdobe PDFView/Open
Show full item record


checked on Oct 2, 2021

Page view(s)

checked on Oct 20, 2021

Download(s) 10

checked on Oct 20, 2021

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.