{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/112943"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/112943","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"An end-to-end online quality prediction system for ultrasonic metal welding based on deep learning","abstract":"Ultrasonic metal welding (UMW) is an important joining technology that is widely used in industry. In many UMW applications, there is a strong need for predicting joint quality quickly, reliably, and non-destructively. State-of-the-art quality assessment methods such as destructive tensile testing and quality monitoring cannot meet the high requirements in industrial-scale production. This thesis proposes a novel end-to-end online prediction algorithm for UMW based on deep learning that offers various benefits, including superior quality prediction, less reliance on prior knowledge of UMW processes (e.g., tool conditions), and not involving tedious data preprocessing and feature engineering. The effectiveness of the proposed method is shown using real-world data generated from a UMW process. A comparative case study is presented to compare three data fusion strategies (early fusion, middle fusion, and late fusion) and traditional feature engineering-based methods. The results show that the proposed end-to-end quality prediction system outperforms traditional methods. In addition, the middle fusion strategy achieves the best prediction performance.","abstract_html":"Ultrasonic metal welding (UMW) is an important joining technology that is widely used in industry. In many UMW applications, there is a strong need for predicting joint quality quickly, reliably, and non-destructively. State-of-the-art quality assessment methods such as destructive tensile testing and quality monitoring cannot meet the high requirements in industrial-scale production. This thesis proposes a novel end-to-end online prediction algorithm for UMW based on deep learning that offers various benefits, including superior quality prediction, less reliance on prior knowledge of UMW processes (e.g., tool conditions), and not involving tedious data preprocessing and feature engineering. The effectiveness of the proposed method is shown using real-world data generated from a UMW process. A comparative case study is presented to compare three data fusion strategies (early fusion, middle fusion, and late fusion) and traditional feature engineering-based methods. The results show that the proposed end-to-end quality prediction system outperforms traditional methods. In addition, the middle fusion strategy achieves the best prediction performance.","abstract_has_math":false,"creators":["Wu, Yulun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Mechanical Engineering","degree_department":null,"school":null,"contributors":["Shao, Chenhui"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T21:40:26Z","date_published":"2022-01-12T21:40:26Z","updated_at":"2026-07-22T22:24:52Z","subjects":["ultrasonic metal welding","quality prediction","welding signal","signal fusion","deep learning"],"languages":["en"],"rights":["Copyright 2021 Yulun Wu"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/112943","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Shao, Chenhui"]},{"key":"dc:creator","label":"Author","values":["Wu, Yulun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T21:40:26Z","2021-05-19","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mechanical Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["ultrasonic metal welding","quality prediction","welding signal","signal fusion","deep learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Yulun Wu"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/112943"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ultrasonic metal welding (UMW) is an important joining technology that is widely used in industry. In many UMW applications, there is a strong need for predicting joint quality quickly, reliably, and non-destructively. State-of-the-art quality assessment methods such as destructive tensile testing and quality monitoring cannot meet the high requirements in industrial-scale production. This thesis proposes a novel end-to-end online prediction algorithm for UMW based on deep learning that offers various benefits, including superior quality prediction, less reliance on prior knowledge of UMW processes (e.g., tool conditions), and not involving tedious data preprocessing and feature engineering. The effectiveness of the proposed method is shown using real-world data generated from a UMW process. A comparative case study is presented to compare three data fusion strategies (early fusion, middle fusion, and late fusion) and traditional feature engineering-based methods. The results show that the proposed end-to-end quality prediction system outperforms traditional methods. In addition, the middle fusion strategy achieves the best prediction performance.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Yulun Wu, accepted the attached license on 2021-04-30 at 13:58.","The student, Yulun Wu, submitted this Thesis for approval on 2021-04-30 at 14:21.","This Thesis was approved for publication on 2021-05-19 at 11:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16631 on 2022-01-12 at 12:42:25","Made available in DSpace on 2022-01-12T21:40:26Z (GMT). No. of bitstreams: 2 WU-THESIS-2021.pdf: 2027008 bytes, checksum: 662f7d473708d7561b7d9fc253b13726 (MD5) LICENSE.txt: 4205 bytes, checksum: 6376db32970e2c6aa7959f59ea3b42ec (MD5) Previous issue date: 2021-05-19"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["An end-to-end online quality prediction system for ultrasonic metal welding based on deep learning"]}]}],"canonical_facts":{"dc:contributor":["Shao, Chenhui"],"dc:creator":["Wu, Yulun"],"dc:date":["2022-01-12T21:40:26Z","2021-05-19","2021-08"],"dc:description":["Ultrasonic metal welding (UMW) is an important joining technology that is widely used in industry. In many UMW applications, there is a strong need for predicting joint quality quickly, reliably, and non-destructively. State-of-the-art quality assessment methods such as destructive tensile testing and quality monitoring cannot meet the high requirements in industrial-scale production. This thesis proposes a novel end-to-end online prediction algorithm for UMW based on deep learning that offers various benefits, including superior quality prediction, less reliance on prior knowledge of UMW processes (e.g., tool conditions), and not involving tedious data preprocessing and feature engineering. The effectiveness of the proposed method is shown using real-world data generated from a UMW process. A comparative case study is presented to compare three data fusion strategies (early fusion, middle fusion, and late fusion) and traditional feature engineering-based methods. The results show that the proposed end-to-end quality prediction system outperforms traditional methods. In addition, the middle fusion strategy achieves the best prediction performance.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Yulun Wu, accepted the attached license on 2021-04-30 at 13:58.","The student, Yulun Wu, submitted this Thesis for approval on 2021-04-30 at 14:21.","This Thesis was approved for publication on 2021-05-19 at 11:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16631 on 2022-01-12 at 12:42:25","Made available in DSpace on 2022-01-12T21:40:26Z (GMT). No. of bitstreams: 2 WU-THESIS-2021.pdf: 2027008 bytes, checksum: 662f7d473708d7561b7d9fc253b13726 (MD5) LICENSE.txt: 4205 bytes, checksum: 6376db32970e2c6aa7959f59ea3b42ec (MD5) Previous issue date: 2021-05-19"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/112943"],"dc:language":["en"],"dc:rights":["Copyright 2021 Yulun Wu"],"dc:subject":["ultrasonic metal welding","quality prediction","welding signal","signal fusion","deep learning"],"dc:title":["An end-to-end online quality prediction system for ultrasonic metal welding based on deep learning"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Mechanical Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:52Z"}