한국압력기기공학회 논문집 (Transactions of the Korean Society of Pressure Vessels and Piping)

한국압력기기공학회 (Korean Society of Pressure Vessels and Piping)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 알고리즘을 이용한 매설 배관 피복 결함의 간접 검사 신호 진단에 관한 연구

Indirect Inspection Signal Diagnosis of Buried Pipe Coating Flaws Using Deep Learning Algorithm

  • 조상진 (한국전력기술 스마트융합연구소) ;
  • 오영진 (한국전력기술 스마트융합연구소) ;
  • 신수용 (금오공과대학교 IT융복합공학과)
  • Sang Jin Cho ;
  • Young-Jin Oh ;
  • Soo Young Shin
  • 투고 : 2023.11.07
  • 심사 : 2023.12.21
  • 발행 : 2023.12.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

키워드

과제정보

본 연구는 산업통상자원부(MOTIE)와 한국에너지기술평가원(KETEP)의 지원을 받아 수행한 연구 과제입니다(No. 20217910100010).

참고문헌

  1. KOGAS-TECH, A good world to live in without underground accident, Safety Management of Underground facility.
  2. M. G. Kim, B. T. Lim, K. T. Kim, H. Y. Chang, H.B. Park, and Y.S Kim, 2020, "Enhancing the Reliability of Coating Flaw Detection for Pipes Buried in Soil Using a Multi-Electrode Detector", CORROSION SCIENCE AND TECHNOLOGY, Vol.19, No.5, pp.265-280.
  3. Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra, 2017, "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization", ICCV.
  4. KISTEK, 1999, Divelopment of corrosion envirionment survey and anlaysis method for buried pipe II.
  5. KOGAS, Protection technique handbook, pp.18, 2003.
  6. Jae-Won Kim, Bu-Taek Lim, Heung-Bae Park, and Hyun-Young Chang, 2018, "Technology for the Detection of Corrosion Defects in Buried Pipes of Nuclear Power Plants with 3D FEM", CORROSION SCIENCE AND TECHNOLOGY, Vol.17, No.6, pp.292-300.
  7. H. Y. Chang, K. T. Kim, B. T. Lim, K. S. Kim, J. W. Kim, H. B. Park, and Y. S. Kim, 2017, "Protection Performance Simulation of Coal Tar-Coated Pipes Buried in a Domestic Nuclear Power Plant Using Cathodic Protection and FEM Method", CORROSION SCIENCE AND TECHNOLOGY, Vol.16, No.3, pp.115-127.
  8. S. H. Choi, S. Y. Won, Y. R. Yoo, and Y. S. Kim, 2022, "Relationship between the Cathodic Protection of Pipe Buried in Soil and Enviro-mental Factors", CORROSION SCIENCE AND TECHNOLOGY, Vol.21, No.5, pp.372-380.
  9. J. J. Kim, M. S. Seo, and D. K. Kim, 2014, "The Study on Development of Cathodic Protection on Underground Pipeline Meauring System", KIGAS, Vol.18, No.5, pp. 66-71.
  10. M. E. Orazem, 2014, Underground Pipeline Corrosion, 1st ed., p. 227, Woodhead Publishing, Cambridge. https://doi.org/10.1533/9780857099266.2.227
  11. COMSOLTM, 2014, Guidebook of COMSOLTM Multiphysics (Chemistry-Electrochemistry), ALTSOFT, pp. 174.
  12. M. G. Kim, B. T. Lim, K. T. Kim, H. Y. Chang, H. B. Park, and Y. S. Kim, 2020, "Effects of Rectifier and Copper Grid Interference on the Detection Reliability of Coating Flaws on Buried Pipes", CORROSION SCIENCE AND TECHNOLOGY, Vol.19, No.4, pp.211-223.
  13. J B. Park, H. M. Kim, and G. S. Park, 2016, "A study on the Signal Correction for Multibple Defects in MFL Type Nondestructive Testing System", J. Korean Magn. Soc., Vol.26, No.1, pp.24-30.
  14. Y. D. Ryou, J. H. Lee, Y. K. Yoon, and H. S. Lim, 2014, "The Development and Introduction of External Corrosion Direct Assessment Measures for Urban Gas Pipelines", KIGAS, Vol.18, No.5, pp.12-19.
  15. H. Y. Chang, H. B. Park, K. T. Kim, Y. S. Kim, and Y. Y. Jang, 2014, "Evaluation of Corrosion Protection Efficiency and Analysis of Damage Detectability in Buried Pipes of a Nuclear Power Plant with 3D FEM", Trans. of the KPVP, Vol.11, No.2, pp.61-67.
  16. WIKIPEDIA, 2023, Confusion matrix, https://en.wikipedia.org/wiki/Confusion_matrix.