대한조선학회논문집 (Journal of the Society of Naval Architects of Korea)

  • 제56권6호
  • /
  • Pages.473-479
  • /
  • 2019
  • /
  • 1225-1143(pISSN)
  • /
  • 2287-7355(eISSN)
대한조선학회 (The Society of Naval Architects of Korea)
권호 표지
DOI QR코드

DOI QR Code

딥 러닝 기반의 이미지학습을 통한 저항 용접품질 검증

Verification of Resistance Welding Quality Based on Deep Learning

  • 강지훈 (동의대학교 조선해양공학과) ;
  • 구남국 (동의대학교 조선해양공학과)
  • Kang, Ji-Hun (Dept. of Naval Architecture and Ocean Engineering, Dong-Eui University) ;
  • Ku, Namkug (Dept. of Naval Architecture and Ocean Engineering, Dong-Eui University)
  • 투고 : 2019.01.07
  • 심사 : 2019.08.23
  • 발행 : 2019.12.20
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

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.

키워드

참고문헌

  1. Cho, Y., Rhee, S., & Um, K.W., 1998. A study of real-time weldability estimation of resistance spot welding using fuzzy algorithm. Journal of Welding and Joining, 16(5), pp.76-84.
  2. Esteva, A., Kuprel, B., Novoa, B.A., Ko, J., Swetter, S.M., Blau, H.M. & Thrun, S., 2017. Nature, 542, pp.115-118. https://doi.org/10.1038/nature21056
  3. Hwang, D.S. & Gho, M.H., 2012. Development and application of realtime weld quality monitoring system. Journal of Welding and Joining, 30(1), pp.44-50. https://doi.org/10.5781/KWJS.2012.30.1.44
  4. Hwang, I.S., Yoon, H.S., Kim, Y.M., Kim, D.C., Kang, M.J., 2017, 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, November 2017.
  5. Inception, 2019, https://github.com/google/inception [Accessed 04 January 2019].
  6. Kim, G.C., 2008, Welding and joining manual. Journal of Welding and Joining.
  7. Lee, J.H., 2013, Materials and Welding, The 21st Century History of Book Publishing.
  8. Matplotlib development team, 2019, https://matplotlib.org/ [Accessed 04 January 2019].
  9. Monitec. Co. Ltd, 2018, Weld Quality Monitoring System, URL: http://www.monitech.co.kr [Accessed 04 January 2019].
  10. Szegedy, C., Liu, S., Jia Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V. & Rabinovich, A., 2015, Going deeper with convolutions, Institute of Electrical and Electronics Engineers Conference on Computer Vision and Pattern Recognition, Boston, MA, pp.1-9.
  11. TensorFlow 2.0 Beta, 2019, https://www.tensorflow.org/hub [Accessed 04 January 2019].
  12. Woo, C.K. & Rhee, Z.K., 2014. Quality assurance of the resistance spot-welding using acoustic emission raw signals classification. Journal of Korean Society of Mechanical Technology, 16(2), pp.1357-1363. https://doi.org/10.17958/ksmt.16.2.201404.1357
  13. Yoon, H.S., 2017. Quality estimation of resistance spot welding using adaptive resonance theory Artificial neural network. Master's Degree Dissertation, Inha University of Engineering.