Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network
In the process of welding zinc-coated steel, zinc vapor causes serious porosity defects. The porosity defect is an important indicator of the quality of welds and degrades the durability and productivity of the weld. Therefore, this study proposes a deep neural network (DNN)-based non-destructive te...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/10/3/389 |
| _version_ | 1818108391867809792 |
|---|---|
| author | Seungmin Shin Chengnan Jin Jiyoung Yu Sehun Rhee |
| author_facet | Seungmin Shin Chengnan Jin Jiyoung Yu Sehun Rhee |
| author_sort | Seungmin Shin |
| collection | DOAJ |
| description | In the process of welding zinc-coated steel, zinc vapor causes serious porosity defects. The porosity defect is an important indicator of the quality of welds and degrades the durability and productivity of the weld. Therefore, this study proposes a deep neural network (DNN)-based non-destructive testing method that can detect and predict porosity defects in real-time, based on welding voltage signal, without requiring additional device in gas metal arc welding (GMAW) process. To this end, a galvannealed hot-rolled high-strength steel sheet applied to automotive parts was used to measure process signals in real-time. Then, feature variables were extracted through preprocessing, and correlation between the feature variables and weld porosity was analyzed. The proposed DNN based framework outperformed the artificial neural network (ANN) model by 15% or more. Finally, an experiment was conducted by using the developed porosity detection and prediction system to evaluate its field application. |
| first_indexed | 2024-12-11T02:14:37Z |
| format | Article |
| id | doaj.art-8169648da7c54a6d94c95f339642ac9a |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-12-11T02:14:37Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-8169648da7c54a6d94c95f339642ac9a2022-12-22T01:24:12ZengMDPI AGMetals2075-47012020-03-0110338910.3390/met10030389met10030389Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural NetworkSeungmin Shin0Chengnan Jin1Jiyoung Yu2Sehun Rhee3School of Mechanical Convergence Engineering, Hanyang University, Seoul 04763, KoreaSchool of Mechanical Convergence Engineering, Hanyang University, Seoul 04763, KoreaMonisys co., Ltd, 775, Gyeongin-ro, Seoul 07299, KoreaSchool of Mechanical Convergence Engineering, Hanyang University, Seoul 04763, KoreaIn the process of welding zinc-coated steel, zinc vapor causes serious porosity defects. The porosity defect is an important indicator of the quality of welds and degrades the durability and productivity of the weld. Therefore, this study proposes a deep neural network (DNN)-based non-destructive testing method that can detect and predict porosity defects in real-time, based on welding voltage signal, without requiring additional device in gas metal arc welding (GMAW) process. To this end, a galvannealed hot-rolled high-strength steel sheet applied to automotive parts was used to measure process signals in real-time. Then, feature variables were extracted through preprocessing, and correlation between the feature variables and weld porosity was analyzed. The proposed DNN based framework outperformed the artificial neural network (ANN) model by 15% or more. Finally, an experiment was conducted by using the developed porosity detection and prediction system to evaluate its field application.https://www.mdpi.com/2075-4701/10/3/389gas metal arc weldingporosityweld qualitydetectiondeep neural network |
| spellingShingle | Seungmin Shin Chengnan Jin Jiyoung Yu Sehun Rhee Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network Metals gas metal arc welding porosity weld quality detection deep neural network |
| title | Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network |
| title_full | Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network |
| title_fullStr | Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network |
| title_full_unstemmed | Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network |
| title_short | Real-Time Detection of Weld Defects for Automated Welding Process Base on Deep Neural Network |
| title_sort | real time detection of weld defects for automated welding process base on deep neural network |
| topic | gas metal arc welding porosity weld quality detection deep neural network |
| url | https://www.mdpi.com/2075-4701/10/3/389 |
| work_keys_str_mv | AT seungminshin realtimedetectionofwelddefectsforautomatedweldingprocessbaseondeepneuralnetwork AT chengnanjin realtimedetectionofwelddefectsforautomatedweldingprocessbaseondeepneuralnetwork AT jiyoungyu realtimedetectionofwelddefectsforautomatedweldingprocessbaseondeepneuralnetwork AT sehunrhee realtimedetectionofwelddefectsforautomatedweldingprocessbaseondeepneuralnetwork |