Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Development of Welding Information Management and Defect Inspection Platform based on Artificial Intelligent for Shipbuilding and Maritime Industry

인공지능 기반 조선해양 용접 품질 정보 관리 및 결함 검사 플랫폼 개발

  • Hwang, Hun-Gyu (Division of Ocean ICT & Advanced Materials Technology Research, Research Institute of Medium & Small Shipbuilding) ;
  • Kim, Bae-Sung (Division of Ocean ICT & Advanced Materials Technology Research, Research Institute of Medium & Small Shipbuilding) ;
  • Woo, Yun-Tae (Division of Ocean ICT & Advanced Materials Technology Research, Research Institute of Medium & Small Shipbuilding) ;
  • Yoon, Young-Wook (ViewOn) ;
  • Shin, Sung-chul (Department of Naval Architecture and Ocean Engineering, Busan University) ;
  • Oh, Sang-jin (Department of Naval Architecture and Ocean Engineering, Busan University)
  • Received : 2020.12.18
  • Accepted : 2021.01.18
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The welding has a high proportion of the production and drying of ships or offshore plants. Non-destructive testing is carried out to verify the quality of welds in Korea, radiography test (RT) is mainly used. Currently, most shipyards adopt analog-type techniques to print the films through the shoot of welding parts. Therefore, the time required from radiography test to pass or fail judgment is long and complex, and is being manually carried out by qualified inspectors. To improve this problem, this paper covers a platform for scanning and digitalizing RT films occurring in shipyards with high resolution, accumulating them in management servers, and applying artificial intelligence (AI) technology to detect welding defects. To do this, we describe the process of designing and developing RT film scanning equipment, welding inspection information integrated management platform, fault reading algorithms, visualization software, and testing and verification of each developed element in conjunction.

용접은 선박 및 해양플랜트의 생산 및 건조에 있어 매우 높은 비중을 차지하는 작업이다. 용접부의 품질 검증을 위해 비파괴 검사를 수행하는데, 우리나라에서는 주로 방사선투과검사(RT)를 활용한다. 현재 대부분의 조선소에서는 용접부의 촬영을 통해 얻어진 필름을 인화하여 검사에 활용하는 아날로그 형태를 채택하고 있다. 이에 방사선 촬영에서부터 합부 판정까지 소요시간이 길고 복잡하며, 관련 분야의 자격을 보유한 검사자에 의해 수작업으로 진행되고 있는 실정이다. 본 논문에서는 이러한 문제를 개선하기 위해 조선소에서 발생하고 있는 RT 필름을 고해상도로 스캔하여 디지털화한 후, 관리 서버에 축적하고, 인공지능 기술을 적용하여 용접 결함을 판독하기 위한 플랫폼에 관한 내용을 다룬다. 이를 위한 일련의 요소인 아날로그 RT 필름 스캔장비, 용접 검사 정보 통합 관리 플랫폼, 결함 판독 알고리즘, 시각화 소프트웨어 등을 설계 및 개발하고, 개발한 각 요소를 상호 연계하여 테스트 및 검증하는 과정에 관하여 기술한다.

Keywords

References

  1. B. S. Kim, H. G. Hwang, C. S. Song, and K. T. Lee, "A development of automatic extraction system for welding inspection information based on shipbuilding and maritime CAD," Journal of the Korea Institute of Information and Communication Engineering, vol. 24, no. 1, pp. 28-36, Jan. 2020. https://doi.org/10.6109/JKIICE.2020.24.1.28
  2. C. S. Song, J. H. Cho, and B. S. Kim, "A Design of artificial intelligence reading platform for radiographic testing of welds," in Proceeding of the 42th Korean Society of Maine Engineering Fall Conference, Busan, pp. 223, 2018.
  3. B. S. Kim, J. H. Cho, and H. G. Hwang, "An implementation of integrated platform for management of welding quality in shipbuilding and marine engineering," in Proceeding of the 44th Korean Society of Maine Engineering Fall Conference, Online, pp. 170, 2020.
  4. B. S. Kim, J. H. Cho, C. S. Song, and H. G. Hwang, "An implementation of integrated welding inspection information management system for ships and offshore plant," in Proceeding of the 43th Korean Society of Maine Engineering Fall Conference, Busan, pp. 156, 2019.
  5. N. Nacereddine, M. Zelmat, S. S. Belaïfa, and M. Tridi, "Weld defect detection in industrial radiography based digital image processing," International Journal of Computer and Information Engineering, vol. 1, no. 2, Jan. 2007.
  6. S. E. Florence, R. V. Samsingh, and V. Babureddy, "Artificial intelligence based defect classification for weld joints," in Proceeding of the 2nd International Conference on Advances in Mechanical Engineering, Chennai, pp. 1-13, 2018.
  7. W. Hou, Y. Wei, Y. Jin, and C. Zhu, "Automatic detection of welding defects using deep neural network," in Proceeding of the 10th International Conference on Computer and Electrical Engineering, Edmonton, pp. 1-10, 2017.
  8. S. M. Shin, C. N. Jin, J. Y. Yu, and S. H. Rhee, "Real-time detection of weld defects for automated welding process base on deep neural network," Journal of Multidisciplinary Digital Publishing Institute, vol. 10, no. 3, pp. 1-16, Mar. 2020.
  9. Y. J. Cruz, M. Rivas, R. Quiza, G. Beruvides, and R. E. Haber, "Computer vision system for welding inspection of liquefied petroleum gas pressure vessels based on combined digital image processing and deep learning techniques," Journal of Multidisciplinary Digital Publishing Institute, vol. 20, no. 16, pp. 1-13, Aug. 2020.
  10. R. K. Kountchev, S. H. Rubin, V. T. Todorov, and R. A. Kountcheva, "A detection of welding defects," in International Journal of Reasoning-based Intelligent Systems, vol. 3, no. 1, pp. 34-43, Dec. 2011. https://doi.org/10.1504/IJRIS.2011.037739
  11. M. Sundaram, J. P. Jose, and G. Jaffino, "Welding defects extraction for radiographic images using c-means segmentation method," in Proceeding of the International Conference on Communication and Network Technologies, Sivakasi, pp. 79-83, 2014.
  12. H. G. Hwang, B. S. Kim, J. H. Cho, and C. S. Song, "A requirements analysis of integrated data platform for automatic testing of welding quality based on artificial intelligence in shipbuilding and maritime domain," in Proceeding of the 43th Korean Society of Maine Engineering Spring Conference, Mokpo, pp. 272, 2019.
  13. S. J. Oh, B. C. Park, D. S. Shin, C. O. Lim, and S. C. Shin, "Automatic detection of welding area using deep learning," in Proceeding of the Joint Academic Conference of the Korean Association of Ocean Science and Technology Societies, Jeju, pp. 454-460, 2018.
  14. S. J. Oh, B. C. Park, C. O. Lim, and S. C. Shin, "Automatic detection of welding defects using faster R-CNN," in Proceeding of the Society of Naval Architects of Korea Annual Autumn Conference, Changwon, pp. 236-240, 2018.
  15. S. Ren, K. He, R. Girshick, and J. Sun, "Faster R-CNN : Towards real-time object detection with region proposal networks," Advances in neural information processing systems (NIPS), 2015.