Zero-shot motor health monitoring by blind domain transition

<p>Continuous long-term monitoring of motor health is crucial for the early detection of abnormalities such as bearing faults (up to 51% of motor failures are attributed to bearing faults). Despite numerous methodologies proposed for bearing fault detection, most of them require normal (health...

Full description

Saved in:
Bibliographic Details
Main Author: Serkan Kiranyaz (3762058) (author)
Other Authors: Ozer Can Devecioglu (17910575) (author), Amir Alhams (17910578) (author), Sadok Sassi (17823461) (author), Turker Ince (14150610) (author), Osama Abdeljaber (14246798) (author), Onur Avci (14246801) (author), Moncef Gabbouj (2276533) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513528302403584
author Serkan Kiranyaz (3762058)
author2 Ozer Can Devecioglu (17910575)
Amir Alhams (17910578)
Sadok Sassi (17823461)
Turker Ince (14150610)
Osama Abdeljaber (14246798)
Onur Avci (14246801)
Moncef Gabbouj (2276533)
author2_role author
author
author
author
author
author
author
author_facet Serkan Kiranyaz (3762058)
Ozer Can Devecioglu (17910575)
Amir Alhams (17910578)
Sadok Sassi (17823461)
Turker Ince (14150610)
Osama Abdeljaber (14246798)
Onur Avci (14246801)
Moncef Gabbouj (2276533)
author_role author
dc.creator.none.fl_str_mv Serkan Kiranyaz (3762058)
Ozer Can Devecioglu (17910575)
Amir Alhams (17910578)
Sadok Sassi (17823461)
Turker Ince (14150610)
Osama Abdeljaber (14246798)
Onur Avci (14246801)
Moncef Gabbouj (2276533)
dc.date.none.fl_str_mv 2024-03-15T03:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.ymssp.2024.111147
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Zero-shot_motor_health_monitoring_by_blind_domain_transition/25151669
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Aerospace engineering
Control engineering, mechatronics and robotics
Mechanical engineering
Operational Neural Networks
Bearing fault detection
1D operational GANs
Machine Health Monitoring
Blind domain transition
dc.title.none.fl_str_mv Zero-shot motor health monitoring by blind domain transition
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Continuous long-term monitoring of motor health is crucial for the early detection of abnormalities such as bearing faults (up to 51% of motor failures are attributed to bearing faults). Despite numerous methodologies proposed for bearing fault detection, most of them require normal (healthy) and abnormal (faulty) data for training. Even with the recent deep learning (DL) methodologies trained on the labeled data from the same machine, the classification accuracy significantly deteriorates when one or few conditions are altered, e.g., a different speed or load, or for different fault types/severities with sensors placed in different locations. Furthermore, their performance suffers significantly or may entirely fail when they are tested on another machine with entirely different healthy and faulty signal patterns. To address this need, in this pilot study, we propose a zero-shot bearing fault detection method that can detect any fault on a new (target) machine regardless of the working conditions, sensor parameters, or fault characteristics. To accomplish this objective, a 1D Operational Generative Adversarial Network (Op-GAN) first characterizes the transition between normal and fault vibration signals of (a) source machine(s) under various conditions, sensor parameters, and fault types. Then for a target machine, the potential faulty signals can be generated, and over its actual healthy and synthesized faulty signals, a compact, and lightweight 1D Self-ONN fault detector can then be trained to detect the real faulty condition in real time whenever it occurs. To validate the proposed approach, a new benchmark dataset is created using two different motors working under different conditions and sensor locations. Experimental results demonstrate that this novel approach can accurately detect any bearing fault achieving an average recall rate of around 89% and 95% on two target machines regardless of its type, severity, and location.</p><h2>Other Information</h2> <p> Published in: Mechanical Systems and Signal Processing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ymssp.2024.111147" target="_blank">https://dx.doi.org/10.1016/j.ymssp.2024.111147</a></p>
eu_rights_str_mv openAccess
id Manara2_1462695ceb96bbc206671742d44e0ba1
identifier_str_mv 10.1016/j.ymssp.2024.111147
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25151669
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Zero-shot motor health monitoring by blind domain transitionSerkan Kiranyaz (3762058)Ozer Can Devecioglu (17910575)Amir Alhams (17910578)Sadok Sassi (17823461)Turker Ince (14150610)Osama Abdeljaber (14246798)Onur Avci (14246801)Moncef Gabbouj (2276533)EngineeringAerospace engineeringControl engineering, mechatronics and roboticsMechanical engineeringOperational Neural NetworksBearing fault detection1D operational GANsMachine Health MonitoringBlind domain transition<p>Continuous long-term monitoring of motor health is crucial for the early detection of abnormalities such as bearing faults (up to 51% of motor failures are attributed to bearing faults). Despite numerous methodologies proposed for bearing fault detection, most of them require normal (healthy) and abnormal (faulty) data for training. Even with the recent deep learning (DL) methodologies trained on the labeled data from the same machine, the classification accuracy significantly deteriorates when one or few conditions are altered, e.g., a different speed or load, or for different fault types/severities with sensors placed in different locations. Furthermore, their performance suffers significantly or may entirely fail when they are tested on another machine with entirely different healthy and faulty signal patterns. To address this need, in this pilot study, we propose a zero-shot bearing fault detection method that can detect any fault on a new (target) machine regardless of the working conditions, sensor parameters, or fault characteristics. To accomplish this objective, a 1D Operational Generative Adversarial Network (Op-GAN) first characterizes the transition between normal and fault vibration signals of (a) source machine(s) under various conditions, sensor parameters, and fault types. Then for a target machine, the potential faulty signals can be generated, and over its actual healthy and synthesized faulty signals, a compact, and lightweight 1D Self-ONN fault detector can then be trained to detect the real faulty condition in real time whenever it occurs. To validate the proposed approach, a new benchmark dataset is created using two different motors working under different conditions and sensor locations. Experimental results demonstrate that this novel approach can accurately detect any bearing fault achieving an average recall rate of around 89% and 95% on two target machines regardless of its type, severity, and location.</p><h2>Other Information</h2> <p> Published in: Mechanical Systems and Signal Processing<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.ymssp.2024.111147" target="_blank">https://dx.doi.org/10.1016/j.ymssp.2024.111147</a></p>2024-03-15T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.ymssp.2024.111147https://figshare.com/articles/journal_contribution/Zero-shot_motor_health_monitoring_by_blind_domain_transition/25151669CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/251516692024-03-15T03:00:00Z
spellingShingle Zero-shot motor health monitoring by blind domain transition
Serkan Kiranyaz (3762058)
Engineering
Aerospace engineering
Control engineering, mechatronics and robotics
Mechanical engineering
Operational Neural Networks
Bearing fault detection
1D operational GANs
Machine Health Monitoring
Blind domain transition
status_str publishedVersion
title Zero-shot motor health monitoring by blind domain transition
title_full Zero-shot motor health monitoring by blind domain transition
title_fullStr Zero-shot motor health monitoring by blind domain transition
title_full_unstemmed Zero-shot motor health monitoring by blind domain transition
title_short Zero-shot motor health monitoring by blind domain transition
title_sort Zero-shot motor health monitoring by blind domain transition
topic Engineering
Aerospace engineering
Control engineering, mechatronics and robotics
Mechanical engineering
Operational Neural Networks
Bearing fault detection
1D operational GANs
Machine Health Monitoring
Blind domain transition