Loading…

Deep Learning Used to Detect Gear Inspection

Automatic gear defect detection equipment is relatively expensive, so small and medium-sized enterprises cannot afford the cost of such equipment. Therefore, most companies still use manual inspection methods for gear defect detection. Manual inspection methods not only take a long time but also has...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian, Jia-Xian, Wang, Chuin-Mu
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 219
container_issue
container_start_page 216
container_title
container_volume
creator Jian, Jia-Xian
Wang, Chuin-Mu
description Automatic gear defect detection equipment is relatively expensive, so small and medium-sized enterprises cannot afford the cost of such equipment. Therefore, most companies still use manual inspection methods for gear defect detection. Manual inspection methods not only take a long time but also has uneven detection quality. This paper proposes to use AI technology to build a cheap and fast gear defect detection method. And this method is used to complete the detection of gear tooth profile defects, tooth pitch defects and central hole defects. The method proposed in this paper is divided into four steps. In the first step, the ResNet model [1] is used to classify whether the gear image is complete or not. In the second step, the YOLOv4 model [2] is used to find the rectangular area of the tooth shape and tooth pitch in the image and cut it out. The third step is to use the UNet model [3] to segment the tooth profile and pitch profile, and calculate the area occupied by the profile. Finally, whether the difference from the average area is too large is used as the basis for judging whether the gear is defective. In the experiment result, 186 gear images are used for detection, and the obtained accuracy is about 91%. This result in addition to verifying the feasibility of the proposed method, it is also found that the proposed method can quickly and accurately detect gear defects that are difficult to judge by human eyes.
doi_str_mv 10.1109/SNPD54884.2022.10051817
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10051817</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10051817</ieee_id><sourcerecordid>10051817</sourcerecordid><originalsourceid>FETCH-LOGICAL-i119t-3b42d2b4f7aab99a0cf36ed936cd9e78900f8fb7c9c885710caf393d1c62b3ce3</originalsourceid><addsrcrecordid>eNo1j8FKw0AURUdBsNT8geB8gKnvzZtk5i2l0VoIKmjXZTJ5IxFNQ5KNf29Bu7qcszhwlbpBWCEC3709v1aF9d6uDBizQoACPbozlbFjTwUQgkVzrhamZMq9NXipsmn6BAAyYIH8Qt1WIoOuJYx913_o3SStng-6klnirDdHr7f9NByhO_RX6iKFr0my_12q3ePD-_opr1822_V9nXeIPOfUWNOaxiYXQsMcICYqpWUqY8viPAMknxoXOXpfOIQYEjG1GEvTUBRaquu_bici-2HsvsP4sz8dpF8ZCUP7</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Deep Learning Used to Detect Gear Inspection</title><source>IEEE Xplore All Conference Series</source><creator>Jian, Jia-Xian ; Wang, Chuin-Mu</creator><creatorcontrib>Jian, Jia-Xian ; Wang, Chuin-Mu</creatorcontrib><description>Automatic gear defect detection equipment is relatively expensive, so small and medium-sized enterprises cannot afford the cost of such equipment. Therefore, most companies still use manual inspection methods for gear defect detection. Manual inspection methods not only take a long time but also has uneven detection quality. This paper proposes to use AI technology to build a cheap and fast gear defect detection method. And this method is used to complete the detection of gear tooth profile defects, tooth pitch defects and central hole defects. The method proposed in this paper is divided into four steps. In the first step, the ResNet model [1] is used to classify whether the gear image is complete or not. In the second step, the YOLOv4 model [2] is used to find the rectangular area of the tooth shape and tooth pitch in the image and cut it out. The third step is to use the UNet model [3] to segment the tooth profile and pitch profile, and calculate the area occupied by the profile. Finally, whether the difference from the average area is too large is used as the basis for judging whether the gear is defective. In the experiment result, 186 gear images are used for detection, and the obtained accuracy is about 91%. This result in addition to verifying the feasibility of the proposed method, it is also found that the proposed method can quickly and accurately detect gear defects that are difficult to judge by human eyes.</description><identifier>EISSN: 2693-8421</identifier><identifier>EISBN: 9798350310412</identifier><identifier>DOI: 10.1109/SNPD54884.2022.10051817</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Deep learning ; Gear defect ; Gears ; Inspection ; Manuals ; Object detection ; ResNet ; Shape ; UNet ; YOLOv4</subject><ispartof>2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2022, p.216-219</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10051817$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10051817$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jian, Jia-Xian</creatorcontrib><creatorcontrib>Wang, Chuin-Mu</creatorcontrib><title>Deep Learning Used to Detect Gear Inspection</title><title>2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)</title><addtitle>SNPD</addtitle><description>Automatic gear defect detection equipment is relatively expensive, so small and medium-sized enterprises cannot afford the cost of such equipment. Therefore, most companies still use manual inspection methods for gear defect detection. Manual inspection methods not only take a long time but also has uneven detection quality. This paper proposes to use AI technology to build a cheap and fast gear defect detection method. And this method is used to complete the detection of gear tooth profile defects, tooth pitch defects and central hole defects. The method proposed in this paper is divided into four steps. In the first step, the ResNet model [1] is used to classify whether the gear image is complete or not. In the second step, the YOLOv4 model [2] is used to find the rectangular area of the tooth shape and tooth pitch in the image and cut it out. The third step is to use the UNet model [3] to segment the tooth profile and pitch profile, and calculate the area occupied by the profile. Finally, whether the difference from the average area is too large is used as the basis for judging whether the gear is defective. In the experiment result, 186 gear images are used for detection, and the obtained accuracy is about 91%. This result in addition to verifying the feasibility of the proposed method, it is also found that the proposed method can quickly and accurately detect gear defects that are difficult to judge by human eyes.</description><subject>Computational modeling</subject><subject>Deep learning</subject><subject>Gear defect</subject><subject>Gears</subject><subject>Inspection</subject><subject>Manuals</subject><subject>Object detection</subject><subject>ResNet</subject><subject>Shape</subject><subject>UNet</subject><subject>YOLOv4</subject><issn>2693-8421</issn><isbn>9798350310412</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2022</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1j8FKw0AURUdBsNT8geB8gKnvzZtk5i2l0VoIKmjXZTJ5IxFNQ5KNf29Bu7qcszhwlbpBWCEC3709v1aF9d6uDBizQoACPbozlbFjTwUQgkVzrhamZMq9NXipsmn6BAAyYIH8Qt1WIoOuJYx913_o3SStng-6klnirDdHr7f9NByhO_RX6iKFr0my_12q3ePD-_opr1822_V9nXeIPOfUWNOaxiYXQsMcICYqpWUqY8viPAMknxoXOXpfOIQYEjG1GEvTUBRaquu_bici-2HsvsP4sz8dpF8ZCUP7</recordid><startdate>20221207</startdate><enddate>20221207</enddate><creator>Jian, Jia-Xian</creator><creator>Wang, Chuin-Mu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20221207</creationdate><title>Deep Learning Used to Detect Gear Inspection</title><author>Jian, Jia-Xian ; Wang, Chuin-Mu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i119t-3b42d2b4f7aab99a0cf36ed936cd9e78900f8fb7c9c885710caf393d1c62b3ce3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computational modeling</topic><topic>Deep learning</topic><topic>Gear defect</topic><topic>Gears</topic><topic>Inspection</topic><topic>Manuals</topic><topic>Object detection</topic><topic>ResNet</topic><topic>Shape</topic><topic>UNet</topic><topic>YOLOv4</topic><toplevel>online_resources</toplevel><creatorcontrib>Jian, Jia-Xian</creatorcontrib><creatorcontrib>Wang, Chuin-Mu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jian, Jia-Xian</au><au>Wang, Chuin-Mu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Deep Learning Used to Detect Gear Inspection</atitle><btitle>2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)</btitle><stitle>SNPD</stitle><date>2022-12-07</date><risdate>2022</risdate><spage>216</spage><epage>219</epage><pages>216-219</pages><eissn>2693-8421</eissn><eisbn>9798350310412</eisbn><abstract>Automatic gear defect detection equipment is relatively expensive, so small and medium-sized enterprises cannot afford the cost of such equipment. Therefore, most companies still use manual inspection methods for gear defect detection. Manual inspection methods not only take a long time but also has uneven detection quality. This paper proposes to use AI technology to build a cheap and fast gear defect detection method. And this method is used to complete the detection of gear tooth profile defects, tooth pitch defects and central hole defects. The method proposed in this paper is divided into four steps. In the first step, the ResNet model [1] is used to classify whether the gear image is complete or not. In the second step, the YOLOv4 model [2] is used to find the rectangular area of the tooth shape and tooth pitch in the image and cut it out. The third step is to use the UNet model [3] to segment the tooth profile and pitch profile, and calculate the area occupied by the profile. Finally, whether the difference from the average area is too large is used as the basis for judging whether the gear is defective. In the experiment result, 186 gear images are used for detection, and the obtained accuracy is about 91%. This result in addition to verifying the feasibility of the proposed method, it is also found that the proposed method can quickly and accurately detect gear defects that are difficult to judge by human eyes.</abstract><pub>IEEE</pub><doi>10.1109/SNPD54884.2022.10051817</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2693-8421
ispartof 2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2022, p.216-219
issn 2693-8421
language eng
recordid cdi_ieee_primary_10051817
source IEEE Xplore All Conference Series
subjects Computational modeling
Deep learning
Gear defect
Gears
Inspection
Manuals
Object detection
ResNet
Shape
UNet
YOLOv4
title Deep Learning Used to Detect Gear Inspection
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A49%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Deep%20Learning%20Used%20to%20Detect%20Gear%20Inspection&rft.btitle=2022%20IEEE/ACIS%2023rd%20International%20Conference%20on%20Software%20Engineering,%20Artificial%20Intelligence,%20Networking%20and%20Parallel/Distributed%20Computing%20(SNPD)&rft.au=Jian,%20Jia-Xian&rft.date=2022-12-07&rft.spage=216&rft.epage=219&rft.pages=216-219&rft.eissn=2693-8421&rft_id=info:doi/10.1109/SNPD54884.2022.10051817&rft.eisbn=9798350310412&rft_dat=%3Cieee_CHZPO%3E10051817%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i119t-3b42d2b4f7aab99a0cf36ed936cd9e78900f8fb7c9c885710caf393d1c62b3ce3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10051817&rfr_iscdi=true