Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/26282

Title: The real time analysis of acoustic weld emissions using neural networks
Authors: Burge, K.L.
Harris, T.J.
Stroud, Raymond
McCardle, John
Issue Date: 1993
Publisher: European Institute for the Joining of Materials
Citation: BURGE, K.L. ...et al., 1993. The real time analysis of acoustic weld emissions using neural networks. IN: Al-Erhayem, O.E. (ed.) Proceedings of the 6th International Conference on the Joining of Materials, Helsingor, Denmark, April 5-7th., pp. 60-67.
Abstract: Artificial Neural Networks (ANNs) are becoming an increasingly viable computing tool in control scenarios where human expertise is so often required. The development of software emulations and dedicated VLSI devices is proving successful in real world applications where complex signal analysis, pattern recognition and discrimination are important factors. An established observation is that a skilled welder is able to monitor a manual arc welding process by subconsciously changing the position of the electrode in response to an adverse change in audible process noise. Expert systems applied to the analysis of chaotic acoustic emissions have failed to establish any salient information due to the inabilities of conventional architectures in processing vast quantities of erratic data at real time speeds. This paper describes the application of a hybrid ANN system, utilising a combination of multiple ANN architectures and conventional techniques, to establish system parameter acoustic signatures for subsequent on line control.
Description: This is a conference paper.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/26282
ISBN: 8789582020
ISSN: 2246-0160
Appears in Collections:Conference Papers and Presentations (Design School)

Files associated with this item:

File Description SizeFormat
JOM+Apr+93.pdfAccepted version1.73 MBAdobe PDFView/Open


SFX Query

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