Cargando…

Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis

Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches demand a large amount of labelled data to build reliable models. The performance of such lab-trained models degrades when deploy...

Descripción completa

Detalles Bibliográficos
Autores principales: Asutkar, Supriya, Tallur, Siddharth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10125977/
https://www.ncbi.nlm.nih.gov/pubmed/37095230
http://dx.doi.org/10.1038/s41598-023-33887-5
_version_ 1785030137754943488
author Asutkar, Supriya
Tallur, Siddharth
author_facet Asutkar, Supriya
Tallur, Siddharth
author_sort Asutkar, Supriya
collection PubMed
description Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches demand a large amount of labelled data to build reliable models. The performance of such lab-trained models degrades when deployed in practical use cases in the presence of distinct distribution target domain datasets. In this work, we present a novel deep transfer learning strategy that fine-tunes the trainable parameters of the lower (convolutional) layers with respect to the changing target domain datasets and transfers the parameters of the deeper (dense) layers from the source domain for efficient domain generalisation and fault classification. The performance of this strategy is evaluated by considering two different target domain datasets and studying the sensitivity of fine-tuning individual layers in the networks using time-frequency representations of the vibration signals (scalograms) as inputs. We observe that the proposed transfer learning strategy yields near-perfect accuracy, even for use cases where low-precision sensors are used for data collection and unlabelled run-to-failure data with a limited number of training samples.
format Online
Article
Text
id pubmed-10125977
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-101259772023-04-26 Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis Asutkar, Supriya Tallur, Siddharth Sci Rep Article Automated fault diagnosis algorithms based on vibration sensor recordings play an important role in determining the state of health of the machines. Data-driven approaches demand a large amount of labelled data to build reliable models. The performance of such lab-trained models degrades when deployed in practical use cases in the presence of distinct distribution target domain datasets. In this work, we present a novel deep transfer learning strategy that fine-tunes the trainable parameters of the lower (convolutional) layers with respect to the changing target domain datasets and transfers the parameters of the deeper (dense) layers from the source domain for efficient domain generalisation and fault classification. The performance of this strategy is evaluated by considering two different target domain datasets and studying the sensitivity of fine-tuning individual layers in the networks using time-frequency representations of the vibration signals (scalograms) as inputs. We observe that the proposed transfer learning strategy yields near-perfect accuracy, even for use cases where low-precision sensors are used for data collection and unlabelled run-to-failure data with a limited number of training samples. Nature Publishing Group UK 2023-04-24 /pmc/articles/PMC10125977/ /pubmed/37095230 http://dx.doi.org/10.1038/s41598-023-33887-5 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Asutkar, Supriya
Tallur, Siddharth
Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title_full Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title_fullStr Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title_full_unstemmed Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title_short Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
title_sort deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10125977/
https://www.ncbi.nlm.nih.gov/pubmed/37095230
http://dx.doi.org/10.1038/s41598-023-33887-5
work_keys_str_mv AT asutkarsupriya deeptransferlearningstrategyforefficientdomaingeneralisationinmachinefaultdiagnosis
AT tallursiddharth deeptransferlearningstrategyforefficientdomaingeneralisationinmachinefaultdiagnosis