2026-09-19T08:31:59Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1329032026-06-06T00:56:32Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Brian Anthony. Yu, Kaili, S.M. Massachusetts Institute of Technology. Massachusetts Institute of Technology. Department of Mechanical Engineering. Massachusetts Institute of Technology. Department of Mechanical Engineering 2021-10-08T17:11:03Z 2021-10-08T17:11:03Z 2020 2020 https://hdl.handle.net/1721.1/132903 1263359209 Thesis: M. Eng. in Advanced Manufacturing and Design, Massachusetts Institute of Technology, Department of Mechanical Engineering, September, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 92-97). Defect detection in industries is typically conducted manually. While there are state-of-the-art machine vision techniques for automated inspection systems, there is still a gap between research advancement and practical applications, especially for manufactures with high volume and low margin. The thesis aims to develop a computer vision system for automated galvanized steel tube defect detection. Based on images collected from a Japanese steel tube producer, multiple methods were explored and tested. Firstly, inception v4 was used as an image classification model. Its performance was first tested on an online dataset, then on our own cleaned dataset. In the next step, since classification only labels a whole image, object detection algorithms were then used for indicating locations as well as the defect class. Several object detection algorithms were adopted and compared: Faster R-CNN, YOLO v4, and YOLO v5. They achieved mAP@0.5 of 94.31%, 95.22%, 75.5% respectively, and recall rates of 67%, 89%, 73.5% respectively, which demonstrated promising results for applications on the production line. However, the results were primarily limited by the quantity and quality of images. Future work could focus on advanced data augmentation, further cleaning on collected data, and improvement in raw image quality. Furthermore, the algorithms need to be validated with real-time inspection speed and on more classes of defects. by Kaili Yu. M.Eng. in Advanced Manufacturing and Design M.Eng.inAdvancedManufacturingandDesign Massachusetts Institute of Technology, Department of Mechanical Engineering 97 pages eng Massachusetts Institute of Technology MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 Mechanical Engineering. Multi-classification and object detection in intelligent manufacturing Thesis application/pdf 2021-10-08T17:11:03Z Publication Master MechE unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="a90d6f88-5f50-40f4-912c-c5f7b83e9a34"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Multi-classification and object detection in intelligent manufacturing</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2020</PublicationDate> <Authors> <Author> <DisplayName>Yu, Kaili, S.M. Massachusetts Institute of Technology.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Mechanical Engineering.</Keyword> <Abstract>Defect detection in industries is typically conducted manually. While there are state-of-the-art machine vision techniques for automated inspection systems, there is still a gap between research advancement and practical applications, especially for manufactures with high volume and low margin. The thesis aims to develop a computer vision system for automated galvanized steel tube defect detection. Based on images collected from a Japanese steel tube producer, multiple methods were explored and tested. Firstly, inception v4 was used as an image classification model. Its performance was first tested on an online dataset, then on our own cleaned dataset. In the next step, since classification only labels a whole image, object detection algorithms were then used for indicating locations as well as the defect class. Several object detection algorithms were adopted and compared: Faster R-CNN, YOLO v4, and YOLO v5. They achieved mAP@0.5 of 94.31%, 95.22%, 75.5% respectively, and recall rates of 67%, 89%, 73.5% respectively, which demonstrated promising results for applications on the production line. However, the results were primarily limited by the quantity and quality of images. Future work could focus on advanced data augmentation, further cleaning on collected data, and improvement in raw image quality. Furthermore, the algorithms need to be validated with real-time inspection speed and on more classes of defects.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>