Meta-models for transfer learning in source localization
File(s)
Author(s)
Bull, Lawrence A
Jones, Matthew R
Cross, Elizabeth J
Duncan, Andrew
Girolami, Mark
Type
Journal Article
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 meta-model captures the inter-task relationships. Our key contribution is how knowledge of the experimental campaign can be encoded between 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).
Date Issued
2024-12-27
Date Acceptance
2024-09-26
Citation
Data-Centric Engineering, 2024, 5
ISSN
2632-6736
Publisher
Cambridge University Press
Journal / Book Title
Data-Centric Engineering
Volume
5
Copyright Statement
© The Author(s), 2024. Published by Cambridge University Press This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
License URL
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Interdisciplinary Applications
damage localization
deep Gaussian processes
Engineering
Engineering, Multidisciplinary
meta-models
multilevel models
Science & Technology
Technology
transfer learning
Publication Status
Published
Article Number
e48
Date Publish Online
2024-12-27