Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning
Creating and consistently maintaining the weld shape during gas metal arc welding (GMAW) is vital for ensuring and maintaining the specified weld quality. However, the back-bead is often not uniformly generated owing to the change that occurs in the narrow gap between the base metals during butt joi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9272996/ |
| _version_ | 1818616896873824256 |
|---|---|
| author | Chengnan Jin Seungmin Shin Jiyoung Yu Sehun Rhee |
| author_facet | Chengnan Jin Seungmin Shin Jiyoung Yu Sehun Rhee |
| author_sort | Chengnan Jin |
| collection | DOAJ |
| description | Creating and consistently maintaining the weld shape during gas metal arc welding (GMAW) is vital for ensuring and maintaining the specified weld quality. However, the back-bead is often not uniformly generated owing to the change that occurs in the narrow gap between the base metals during butt joint GMAW, which substantially influences weldability. Automating the GMAW process requires the capability of real-time weld quality monitoring and diagnosis. In this study, we developed a convolutional neural network-based back-bead prediction model. Specifically, scalogram feature image data were acquired by performing Morlet wavelet transform on the welding current measured in the short-circuit transform mode of the GMAW process. The acquired scalogram feature image data were then analyzed and used to develop labeled weld quality training data for the convolutional neural network model. The model predictions were compared with welding data acquired through additional experiments to validate the proposed prediction model. The prediction accuracy was approximately 93.5%, indicating that the findings of this study could serve as a foundation for the future development of automated welding systems. |
| first_indexed | 2024-12-16T16:57:05Z |
| format | Article |
| id | doaj.art-ab00d87fddb841ce8efa7d8012216a6c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T16:57:05Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ab00d87fddb841ce8efa7d8012216a6c2022-12-21T22:23:51ZengIEEEIEEE Access2169-35362020-01-01822404422405810.1109/ACCESS.2020.30412749272996Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep LearningChengnan Jin0https://orcid.org/0000-0001-7964-5466Seungmin Shin1https://orcid.org/0000-0002-8348-3671Jiyoung Yu2https://orcid.org/0000-0002-0494-9497Sehun Rhee3https://orcid.org/0000-0002-0039-5650School of Mechanical Convergence Engineering, Hanyang University, Seoul, South KoreaSchool of Mechanical Convergence Engineering, Hanyang University, Seoul, South KoreaJoining R&D Group, Korea Institute of Industrial Technology, Incheon, South KoreaSchool of Mechanical Convergence Engineering, Hanyang University, Seoul, South KoreaCreating and consistently maintaining the weld shape during gas metal arc welding (GMAW) is vital for ensuring and maintaining the specified weld quality. However, the back-bead is often not uniformly generated owing to the change that occurs in the narrow gap between the base metals during butt joint GMAW, which substantially influences weldability. Automating the GMAW process requires the capability of real-time weld quality monitoring and diagnosis. In this study, we developed a convolutional neural network-based back-bead prediction model. Specifically, scalogram feature image data were acquired by performing Morlet wavelet transform on the welding current measured in the short-circuit transform mode of the GMAW process. The acquired scalogram feature image data were then analyzed and used to develop labeled weld quality training data for the convolutional neural network model. The model predictions were compared with welding data acquired through additional experiments to validate the proposed prediction model. The prediction accuracy was approximately 93.5%, indicating that the findings of this study could serve as a foundation for the future development of automated welding systems.https://ieeexplore.ieee.org/document/9272996/Gas metal arc weldingback-bead monitoringautomated weld quality controlsupervised deep learningtime-frequency analysis |
| spellingShingle | Chengnan Jin Seungmin Shin Jiyoung Yu Sehun Rhee Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning IEEE Access Gas metal arc welding back-bead monitoring automated weld quality control supervised deep learning time-frequency analysis |
| title | Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning |
| title_full | Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning |
| title_fullStr | Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning |
| title_full_unstemmed | Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning |
| title_short | Prediction Model for Back-Bead Monitoring During Gas Metal Arc Welding Using Supervised Deep Learning |
| title_sort | prediction model for back bead monitoring during gas metal arc welding using supervised deep learning |
| topic | Gas metal arc welding back-bead monitoring automated weld quality control supervised deep learning time-frequency analysis |
| url | https://ieeexplore.ieee.org/document/9272996/ |
| work_keys_str_mv | AT chengnanjin predictionmodelforbackbeadmonitoringduringgasmetalarcweldingusingsuperviseddeeplearning AT seungminshin predictionmodelforbackbeadmonitoringduringgasmetalarcweldingusingsuperviseddeeplearning AT jiyoungyu predictionmodelforbackbeadmonitoringduringgasmetalarcweldingusingsuperviseddeeplearning AT sehunrhee predictionmodelforbackbeadmonitoringduringgasmetalarcweldingusingsuperviseddeeplearning |