맞대기 V형 그루브의 GMA 초층용접에서 합성곱 신경망을 이용한 이면비드 발생 예측 모델 개발open accessConvolutional Neural Network Model for the Prediction of Back-Bead Occurrence in GMA Root Pass Welding of V-groove Butt Joint
- Other Titles
- Convolutional Neural Network Model for the Prediction of Back-Bead Occurrence in GMA Root Pass Welding of V-groove Butt Joint
- Authors
- 이형원; 유지영; 김광국; 김영민; 황인성; 이승환; 김동윤
- Issue Date
- Oct-2021
- Publisher
- 대한용접접합학회
- Keywords
- Gas metal arc welding (GMAW); V-Groove; Back-bead; Root pass; Full penetration; Deep learning; Convolutional neural network (CNN); Laser vision
- Citation
- 대한용접접합학회지, v.39, no.5, pp.463 - 470
- Indexed
- KCI
- Journal Title
- 대한용접접합학회지
- Volume
- 39
- Number
- 5
- Start Page
- 463
- End Page
- 470
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/140732
- DOI
- 10.5781/JWJ.2021.39.5.1
- ISSN
- 2466-2232
- Abstract
- Gas metal arc (GMA) welding is widely used in the machinery industry. The quality of a welded joint is affected by the penetration of root pass welding in the V-groove joint. Automation using GMA welding is continuously re- quired, and root pass welding automation is required to automate the entire welding process. In particular, the devel- opment of a prediction model that can ensure full penetration back-bead is required for the automation of root pass welding. In this study, a convolutional neural network (CNN) model was applied to predict the occurrence of back-bead in V-groove butt joint GMA root pass welding. The bead profile was measured using a laser vision sensor system and it was used as the input data for the prediction model, and the bead occurrence was used as the output data for the model. A total of 12,873 bead profiles were extracted and pre-processed through cutting, resizing, and thresholding. The CNN model consists of nine layers, and performs three convolution and two pooling operations. The accuracy of the prediction model was 99.5%, and through this study, it was demonstrated that the quality of root-pass welding can be controlled by using convolutional neural network and it can contribute to automation.
- Files in This Item
-
- 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/140732)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.