Bull, L.A. orcid.org/0000-0002-0225-5010, Jones, M.R. orcid.org/0000-0001-7446-0833, Cross, E.J. orcid.org/0000-0001-5204-1910 et al. (2 more authors) (2024) Meta-models for transfer learning in source localization. Data-Centric Engineering, 5. e48. ISSN 2632-6736
Abstract
In practice, nondestructive testing (NDT) procedures tend to consider experiments (and their respective models) as distinct, conducted in isolation, and associated with independent data. In contrast, this work looks to capture the interdependencies between acoustic emission (AE) experiments (as meta-models) and then use the resulting functions to predict the model hyperparameters for previously unobserved systems. We utilize a Bayesian multilevel approach (similar to deep Gaussian Processes) where a higher-level <jats:italic>meta-model</jats:italic> captures the inter-task relationships. Our key contribution is how knowledge of the experimental campaign can be encoded <jats:italic>between</jats:italic> tasks as well as within tasks. We present an example of AE time-of-arrival mapping for source localization, to illustrate how multilevel models naturally lend themselves to representing aggregate systems in engineering. We constrain the meta-model based on domain knowledge, then use the inter-task functions for transfer learning, predicting hyperparameters for models of previously unobserved experiments (for a specific design).
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2024 The Authors. This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
Keywords: | damage localization; deep Gaussian processes; meta-models; multilevel models; transfer learning |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > School of Mechanical, Aerospace and Civil Engineering The University of Sheffield > Faculty of Engineering (Sheffield) |
Funding Information: | Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/W005816/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 03 Feb 2025 11:38 |
Last Modified: | 03 Feb 2025 11:38 |
Published Version: | https://doi.org/10.1017/dce.2024.43 |
Status: | Published |
Publisher: | Cambridge University Press (CUP) |
Refereed: | Yes |
Identification Number: | 10.1017/dce.2024.43 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:222579 |
Download
Filename: meta-models-for-transfer-learning-in-source-localization.pdf
Licence: CC-BY 4.0