Hostname: page-component-7b7567c8c-7pwfn Total loading time: 0 Render date: 2026-11-16T06:58:29.617Z Has data issue: false hasContentIssue false

Genetic optimisation of a neural network damage diagnostic

Published online by Cambridge University Press:  03 February 2016

G. Manson
Affiliation:
Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Sheffield, UK
E. Papatheou
Affiliation:
Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Sheffield, UK
K. Worden
Affiliation:
Dynamics Research Group, Department of Mechanical Engineering, University of Sheffield, Sheffield, UK
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

This paper presents an automated optimisation procedure for the feature selection stage of a previously proposed structural health monitoring methodology using a genetic algorithm. The same diagnostic is used in the attempt to progress up the levels of damage detection to location and severity. It was validated experimentally on a Gnat aircraft wing. An artificial neural network is used as a classifier and the work is compared with the previous selection strategy based on engineering judgement.

Information

Type
Research Article
Copyright
Copyright © Royal Aeronautical Society 2008