Misalignment monitoring between electrodes and a rivet in three-sheet resistance element welding based on dynamic resistance
- Authors
- Kim, Mingyu; Jo, Sooyoung; Lee, Seung Hwan; Yu, Jiyoung
- Issue Date
- Oct-2023
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Keywords
- Dissimilar materials welding; Dynamic resistance; Misalignment; Pre-contact process; Resistance element welding; Weld quality
- Citation
- International Journal of Advanced Manufacturing Technology, v.128, no.9-10, pp.4061 - 4075
- Indexed
- SCIE
SCOPUS
- Journal Title
- International Journal of Advanced Manufacturing Technology
- Volume
- 128
- Number
- 9-10
- Start Page
- 4061
- End Page
- 4075
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192936
- DOI
- 10.1007/s00170-023-12188-1
- ISSN
- 0268-3768
- Abstract
- Resistance element welding (REW) has been applied to join various dissimilar materials such as steel and aluminum alloy. In this study, we propose a monitoring methodology that can predict misalignment between electrodes and a rivet in the REW of a three-sheet stack-up, where visual inspection technologies are not available for measuring the misalignment between electrodes and a rivet element. To that end, the effects of the misalignment between electrodes and a rivet on REW joint quality (tensile shear strength, nugget diameter) were investigated using a three-sheet stack-up of SPFC590 sheet (top sheet), Al6061 sheet (middle sheet) with a rivet inserted, and SABC1470 sheet (bottom sheet). A pre-contact process designed to predict the misalignment was added before the REW process. The characteristic of dynamic resistance and welding power according to the misalignment distance was analyzed, and features of dynamic resistance waveform in the pre-contact process were extracted to be used as input to a deep neural network (DNN) model that can predict the misalignment between electrodes and a rivet. A DNN model predicting the state of the misalignment between electrodes and a rivet was designed and trained, and the misalignment was predicted with 100% accuracy from the DNN model.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 기계공학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/192936)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.