Tsialiamanis, G.P., Wagg, D.J., Gardner, P.A. orcid.org/0000-0002-1882-9728 et al. (2 more authors) (2020) On partitioning of an SHM problem and parallels with transfer learning. In: Dilworth, B. and Mains, M., (eds.) Topics in Modal Analysis & Testing, Volume 8 : Proceedings of the 38th IMAC, A Conference and Exposition on Structural Dynamics 2020. 38th IMAC, A Conference and Exposition on Structural Dynamics 2020, 10-13 Feb 2020, Houston, TX, USA. Springer International Publishing , pp. 41-50. ISBN 9783030477165
Abstract
In the current work, a problem-splitting approach and a scheme motivated by transfer learning is applied to a structural health monitoring problem. The specific problem in this case is that of localising damage on an aircraft wing. The original experiment is described, together with the initial approach, in which a neural network was trained to localise damage. The results were not ideal, partly because of a scarcity of training data, and partly because of the difficulty in resolving two of the damage cases. In the current paper, the problem is split into two sub-problems and an increase in classification accuracy is obtained. The sub-problems are obtained by separating out the most difficult-to-classify damage cases. A second approach to the problem is considered by adopting ideas from transfer learning (usually applied in much deeper) networks to see if a network trained on the simpler damage cases can help with feature extraction in the more difficult cases. The transfer of a fixed trained batch of layers between the networks is found to improve classification by making the classes more separable in the feature space and to speed up convergence.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © 2021 The Society for Experimental Mechanics, Inc. This is an author-produced version of a paper subsequently published in Proceedings of the 38th IMAC. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Structural health monitoring (SHM); machine learning; classification; problem splitting; transfer learning |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Mechanical Engineering (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Science Research Council EP/N010884/1; EP/R004900/1; EP/R006768/1; EP/R003645/1 European Commission - Horizon 2020 764547 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 06 Jan 2021 08:24 |
Last Modified: | 23 Oct 2021 00:38 |
Status: | Published |
Publisher: | Springer International Publishing |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-030-47717-2_5 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:169411 |