딥 러닝 기반의 이미지학습을 통한 저항 용접품질 검증
Verification of Resistance Welding Quality Based on Deep Learning
1
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
Welding is one of the most popular joining methods and most welding quality estimation methods are executed using joined material. This paper propose welding quality estimation methods using dynamic current, voltage and resistance which are obtained during welding in real time. There are many kinds of welding method. Among them, we focused on the projection welding and gathered dynamic characteristics from two different types of projection welding. For image learning, graphs are drawn using obtained current, voltage and resistance, and the graphs are converted to images. The images are labeled with two sub-categories - normal and defect. For deep learning of images obtained from welding, Convolutional Neural Network (CNN) is applied, and Tensorflow was used as a framework for deep learning. With two resistance welding test datasets, we conclude that the Convolutional Neural Network helps in predicting the welding quality.
Abstract
Welding is one of the most popular joining methods and most welding quality estimation methods are executed using joined material. This paper propose welding quality estimation methods using dynamic current, voltage and resistance which are obtained during welding in real time. There are many kinds of welding method. Among them, we focused on the projection welding and gathered dynamic characteristics from two different types of projection welding. For image learning, graphs are drawn using obtained current, voltage and resistance, and the graphs are converted to images. The images are labeled with two sub-categories - normal and defect. For deep learning of images obtained from welding, Convolutional Neural Network (CNN) is applied, and Tensorflow was used as a framework for deep learning. With two resistance welding test datasets, we conclude that the Convolutional Neural Network helps in predicting the welding quality.
참고문헌 (13)
- Cho, Y., "A study of real-time weldability estimation of resistance spot welding using fuzzy algorithm", Journal of Welding and Joining, 16(5), pp.76~84 (1998)
- Esteva, A., , Nature, 542, pp.115~118 (2017)
- 황동수, "실시간 용접품질 모니터링 시스템의 개발 및 적용 동향", 대한용접접합학회지, 30(1), pp.44~50 (2012), 대한용접접합학회
- Hwang, I.S., "Prediction of irregular condition of resistance spot welding process using artificial neural metwork", Proceedings of 2017 Fall Conference of Society for The Korean Welding & Joining Society (2017)
- "Inception" (2019)[URL]
- Kim, G.C., "Welding and joining manual", Journal of Welding and Joining (2008)
- Lee, J.H., "Materials and Welding" (2013), The 21st Century History of Book Publishing
- "Matplotlib development team" (2019)[URL]
- "Weld Quality Monitoring System" (2018)[URL]
- Szegedy, C., "Going deeper with convolutions", Institute of Electrical and Electronics Engineers Conference on Computer Vision and Pattern Recognition, pp.1~9 (2015)
- "TensorFlow 2.0 Beta" (2019)[URL]
- 우창기, "음향방출 원신호를 이용한 저항점용접의 품질평가에 관한 연구", 한국기계기술학회지, 16(2), pp.1357~1363 (2014), 한국기계기술학회[DOI]
- Yoon, H. S., "Quality estimation of resistance spot welding using adaptive resonance theory Artificial neural network", Master's, pp.2017