Cargando…

Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations

Development of predictive maintenance (PdM) solutions is one of the key aspects of Industry 4.0. In recent years, more attention has been paid to data-driven techniques, which use machine learning to monitor the health of an industrial asset. The major issue in the implementation of PdM models is a...

Descripción completa

Detalles Bibliográficos
Autores principales: Jakubowski, Jakub, Stanisz, Przemysław, Bobek, Szymon, Nalepa, Grzegorz J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749861/
https://www.ncbi.nlm.nih.gov/pubmed/35009832
http://dx.doi.org/10.3390/s22010291
_version_ 1784631331244736512
author Jakubowski, Jakub
Stanisz, Przemysław
Bobek, Szymon
Nalepa, Grzegorz J.
author_facet Jakubowski, Jakub
Stanisz, Przemysław
Bobek, Szymon
Nalepa, Grzegorz J.
author_sort Jakubowski, Jakub
collection PubMed
description Development of predictive maintenance (PdM) solutions is one of the key aspects of Industry 4.0. In recent years, more attention has been paid to data-driven techniques, which use machine learning to monitor the health of an industrial asset. The major issue in the implementation of PdM models is a lack of good quality labelled data. In the paper we present how unsupervised learning using a variational autoencoder may be used to monitor the wear of rolls in a hot strip mill, a part of a steel-making site. As an additional benchmark we use a simulated turbofan engine data set provided by NASA. We also use explainability methods in order to understand the model’s predictions. The results show that the variational autoencoder slightly outperforms the base autoencoder architecture in anomaly detection tasks. However, its performance on the real use-case does not make it a production-ready solution for industry and should be a matter of further research. Furthermore, the information obtained from the explainability model can increase the reliability of the proposed artificial intelligence-based solution.
format Online
Article
Text
id pubmed-8749861
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87498612022-01-12 Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations Jakubowski, Jakub Stanisz, Przemysław Bobek, Szymon Nalepa, Grzegorz J. Sensors (Basel) Article Development of predictive maintenance (PdM) solutions is one of the key aspects of Industry 4.0. In recent years, more attention has been paid to data-driven techniques, which use machine learning to monitor the health of an industrial asset. The major issue in the implementation of PdM models is a lack of good quality labelled data. In the paper we present how unsupervised learning using a variational autoencoder may be used to monitor the wear of rolls in a hot strip mill, a part of a steel-making site. As an additional benchmark we use a simulated turbofan engine data set provided by NASA. We also use explainability methods in order to understand the model’s predictions. The results show that the variational autoencoder slightly outperforms the base autoencoder architecture in anomaly detection tasks. However, its performance on the real use-case does not make it a production-ready solution for industry and should be a matter of further research. Furthermore, the information obtained from the explainability model can increase the reliability of the proposed artificial intelligence-based solution. MDPI 2021-12-31 /pmc/articles/PMC8749861/ /pubmed/35009832 http://dx.doi.org/10.3390/s22010291 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jakubowski, Jakub
Stanisz, Przemysław
Bobek, Szymon
Nalepa, Grzegorz J.
Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title_full Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title_fullStr Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title_full_unstemmed Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title_short Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations
title_sort anomaly detection in asset degradation process using variational autoencoder and explanations
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8749861/
https://www.ncbi.nlm.nih.gov/pubmed/35009832
http://dx.doi.org/10.3390/s22010291
work_keys_str_mv AT jakubowskijakub anomalydetectioninassetdegradationprocessusingvariationalautoencoderandexplanations
AT staniszprzemysław anomalydetectioninassetdegradationprocessusingvariationalautoencoderandexplanations
AT bobekszymon anomalydetectioninassetdegradationprocessusingvariationalautoencoderandexplanations
AT nalepagrzegorzj anomalydetectioninassetdegradationprocessusingvariationalautoencoderandexplanations