http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
C형 용가재를 사용한 GTAW 공정에서 랩조인트 필릿 용접의 공정 강건성 검토를 위한 연구
김상열(Sang-Yeol Kim),서기정(Gi-Jeong Seo),주우현(Woo-Hyeon Ju),조상명(Sang-Myung Cho) 대한용접·접합학회 2019 대한용접·접합학회지 Vol.37 No.5
Thin plate stainless steel is mainly used for lap joint fillet welding in GTAW and GMAW pro- cesses. However, due to the machining tolerance of the product, gaps are generated, and the weld line of the product before welding is not consistent. As a result, welding defects such as burn through and discontinuous bead frequently occur. If C-Filler is used for lap joint fillet welding with GTAW, the gap bridging ability is improved compared to rod-type filler due to the wide C-Filler, and it is expected that it will be possible to prevent weld defect even if the weld line is not consistent. In this study, we examined the molten pool flow ahead of the arc by changing the push angle, inclined downward angle and deposition area in lap joint fillet welding. We also increased the gap and moved the weld line to test the process robustness.
와이어-아크 적층제조 공정의 비드 결함 감지를 위한 기계학습 모델
김준성(Jun-Seong Kim),서기정(Gi-Jeong Seo),김덕봉(Duck Bong Kim),신종호(Jong-Ho Shin),박형준(Hyungjun Park) (사)한국CDE학회 2021 한국CDE학회 논문집 Vol.26 No.2
In the wire-arc additive manufacturing (WAAM) process, which creates metal layers with weld beads, it is important to detect weld bead defects and resolve them properly and timely. In this paper, we propose a machine learning approach for automatically detecting weld bead defects based on voltage signature data captured during the WAAM process. We adopt multi-layer perceptron (MLP) and convolutional neural network (CNN) as machine learning models, and consider three types of beads: normal bead, abnormal bead with balling effects, and abnormal bead with cuts. After capturing voltage signatures while building weld beads, we separated each voltage signature into 17 to 19 segments, from each of which a set of features are extracted. We then constructed training and test data with feature datasets. We built total 75 voltage signatures: 45 for normal beads, 15 for abnormal beads with balling effects, and 15 for abnormal beads with cuts. After training the MLP and CNN models using TensorFlow, we tested and compared their performance. We found that the two types of models works well even though the amount of data used is small, but the CNN models are more appropriate for real-time detection of weld bead defects.