Anomaly Detection of DC Nut Runner Processes in Engine Assembly

Flynn, James Simon; Giannetti, Cinzia; Dijk, Hessel Van

doi:10.3390/ai4010010

Journal article 426 views 59 downloads

Anomaly Detection of DC Nut Runner Processes in Engine Assembly

James Simon Flynn

, Cinzia Giannetti

, Hessel Van Dijk

AI, Volume: 4, Issue: 1, Pages: 234 - 254

Swansea University Author: Cinzia Giannetti

PDF | Version of Record

© 2023 by the authors. 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/)
Download (15.08MB)

Check full text

DOI (Published version): 10.3390/ai4010010

Abstract

In many manufacturing systems, anomaly detection is critical to identifying process errors and ensuring product quality. This paper proposes three semi-supervised solutions to detect anomalies in Direct Current (DC) Nut Runner engine assembly processes. The nut runner process is a challenging anomal...

Full description

Published in:	AI
ISSN:	2673-2688
Published:	MDPI AG 2023
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa62914
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2023-03-11T08:25:50Z
last_indexed	2023-04-19T03:23:51Z
id	cronfa62914
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2023-04-18T11:31:32.2201924</datestamp><bib-version>v2</bib-version><id>62914</id><entry>2023-03-11</entry><title>Anomaly Detection of DC Nut Runner Processes in Engine Assembly</title><swanseaauthors><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-03-11</date><deptcode>MECH</deptcode><abstract>In many manufacturing systems, anomaly detection is critical to identifying process errors and ensuring product quality. This paper proposes three semi-supervised solutions to detect anomalies in Direct Current (DC) Nut Runner engine assembly processes. The nut runner process is a challenging anomaly detection problem due to the manual nature of the process inducing high variability and ambiguity of the anomalous class. These characteristics lead to a scenario where anomalies are not outliers, and the normal operating conditions are difficult to define. To address these challenges, a Gaussian Mixture Model (GMM) was trained using a semi-supervised approach. Three dimensionality reduction methods were compared in pre-processing: PCA, t-SNE, and UMAP. These approaches are demonstrated to outperform the current approaches used by a major automotive company on two real-world datasets. Furthermore, a novel approach to labelling real-world data is proposed, including the concept of an ‘Anomaly No Concern’ class, in addition to the traditional labels of ‘Anomaly’ and ‘Normal’. Introducing this new term helped address knowledge gaps between data scientists and domain experts, as well as providing new insights during model development and testing. This represents a major advancement in identifying anomalies in manual production processes that use handheld tools.</abstract><type>Journal Article</type><journal>AI</journal><volume>4</volume><journalNumber>1</journalNumber><paginationStart>234</paginationStart><paginationEnd>254</paginationEnd><publisher>MDPI AG</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2673-2688</issnElectronic><keywords>GMM, UMAP, PCA, t-SNE, quality assurance, anomaly detection, nut runner</keywords><publishedDay>7</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-03-07</publishedDate><doi>10.3390/ai4010010</doi><url>http://dx.doi.org/10.3390/ai4010010</url><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm>External research funder(s) paid the OA fee (includes OA grants disbursed by the Library)</apcterm><funders>Funded by M2A COATED2 CDT</funders><projectreference>European Social Fund via the Welsh Government (c80816); EP/L015099/1</projectreference><lastEdited>2023-04-18T11:31:32.2201924</lastEdited><Created>2023-03-11T08:17:50.0986132</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering</level></path><authors><author><firstname>James Simon</firstname><surname>Flynn</surname><orcid>0000-0002-3602-1458</orcid><order>1</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>2</order></author><author><firstname>Hessel Van</firstname><surname>Dijk</surname><order>3</order></author></authors><documents><document><filename>62914__26882__530f9ae13723407cbdf82a9f6d37e878.pdf</filename><originalFilename>62914.pdf</originalFilename><uploaded>2023-03-17T15:07:06.6054212</uploaded><type>Output</type><contentLength>15811565</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2023 by the authors. 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/)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2023-04-18T11:31:32.2201924 v2 62914 2023-03-11 Anomaly Detection of DC Nut Runner Processes in Engine Assembly a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2023-03-11 MECH In many manufacturing systems, anomaly detection is critical to identifying process errors and ensuring product quality. This paper proposes three semi-supervised solutions to detect anomalies in Direct Current (DC) Nut Runner engine assembly processes. The nut runner process is a challenging anomaly detection problem due to the manual nature of the process inducing high variability and ambiguity of the anomalous class. These characteristics lead to a scenario where anomalies are not outliers, and the normal operating conditions are difficult to define. To address these challenges, a Gaussian Mixture Model (GMM) was trained using a semi-supervised approach. Three dimensionality reduction methods were compared in pre-processing: PCA, t-SNE, and UMAP. These approaches are demonstrated to outperform the current approaches used by a major automotive company on two real-world datasets. Furthermore, a novel approach to labelling real-world data is proposed, including the concept of an ‘Anomaly No Concern’ class, in addition to the traditional labels of ‘Anomaly’ and ‘Normal’. Introducing this new term helped address knowledge gaps between data scientists and domain experts, as well as providing new insights during model development and testing. This represents a major advancement in identifying anomalies in manual production processes that use handheld tools. Journal Article AI 4 1 234 254 MDPI AG 2673-2688 GMM, UMAP, PCA, t-SNE, quality assurance, anomaly detection, nut runner 7 3 2023 2023-03-07 10.3390/ai4010010 http://dx.doi.org/10.3390/ai4010010 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University External research funder(s) paid the OA fee (includes OA grants disbursed by the Library) Funded by M2A COATED2 CDT European Social Fund via the Welsh Government (c80816); EP/L015099/1 2023-04-18T11:31:32.2201924 2023-03-11T08:17:50.0986132 Faculty of Science and Engineering School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering James Simon Flynn 0000-0002-3602-1458 1 Cinzia Giannetti 0000-0003-0339-5872 2 Hessel Van Dijk 3 62914__26882__530f9ae13723407cbdf82a9f6d37e878.pdf 62914.pdf 2023-03-17T15:07:06.6054212 Output 15811565 application/pdf Version of Record true © 2023 by the authors. 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/) true eng https://creativecommons.org/licenses/by/4.0/
title	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
spellingShingle	Anomaly Detection of DC Nut Runner Processes in Engine Assembly Cinzia Giannetti
title_short	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
title_full	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
title_fullStr	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
title_full_unstemmed	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
title_sort	Anomaly Detection of DC Nut Runner Processes in Engine Assembly
author_id_str_mv	a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv	a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia Giannetti
author	Cinzia Giannetti
author2	James Simon Flynn Cinzia Giannetti Hessel Van Dijk
format	Journal article
container_title	AI
container_volume	4
container_issue	1
container_start_page	234
publishDate	2023
institution	Swansea University
issn	2673-2688
doi_str_mv	10.3390/ai4010010
publisher	MDPI AG
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Aerospace, Civil, Electrical, General and Mechanical Engineering - Mechanical Engineering
url	http://dx.doi.org/10.3390/ai4010010
document_store_str	1
active_str	0
description	In many manufacturing systems, anomaly detection is critical to identifying process errors and ensuring product quality. This paper proposes three semi-supervised solutions to detect anomalies in Direct Current (DC) Nut Runner engine assembly processes. The nut runner process is a challenging anomaly detection problem due to the manual nature of the process inducing high variability and ambiguity of the anomalous class. These characteristics lead to a scenario where anomalies are not outliers, and the normal operating conditions are difficult to define. To address these challenges, a Gaussian Mixture Model (GMM) was trained using a semi-supervised approach. Three dimensionality reduction methods were compared in pre-processing: PCA, t-SNE, and UMAP. These approaches are demonstrated to outperform the current approaches used by a major automotive company on two real-world datasets. Furthermore, a novel approach to labelling real-world data is proposed, including the concept of an ‘Anomaly No Concern’ class, in addition to the traditional labels of ‘Anomaly’ and ‘Normal’. Introducing this new term helped address knowledge gaps between data scientists and domain experts, as well as providing new insights during model development and testing. This represents a major advancement in identifying anomalies in manual production processes that use handheld tools.
published_date	2023-03-07T04:23:19Z
_version_	1763663936536707072
score	11.012678

Anomaly Detection of DC Nut Runner Processes in Engine Assembly

Similar Items