DOI QR코드

DOI QR Code

Feature Analysis of Ultrasonic Signals for Diagnosis of Welding Faults in Tubular Steel Tower

관형 철탑 용접 결함 진단을 위한 초음파 신호의 특징 분석

  • Min, Tae-Hong (Department of Energy and Mechanical Engineering, Gyeongsang National University) ;
  • Yu, Hyeon-Tak (Department of Energy and Mechanical Engineering, Gyeongsang National University) ;
  • Kim, Hyeong-Jin (Department of Energy and Mechanical Engineering, Gyeongsang National University) ;
  • Choi, Byeong-Keun (Department of Energy and Mechanical Engineering, Gyeongsang National University) ;
  • Kim, Hyun-Sik (Mattron Corp.) ;
  • Lee, Gi-Seung (Mattron Corp.) ;
  • Kang, Seog-Geun (Department of Semiconductor Engineering, Gyeongsang National University)
  • Received : 2021.01.29
  • Accepted : 2021.04.02
  • Published : 2021.04.30

Abstract

In this paper, we present and analyze a method of applying a machine learning to ultrasonic test signals for constant monitoring of the welding faults in a tubular steel tower. For the machine learning, feature selection based on genetic algorithm and fault signal classification using a support vector machine have been used. In the feature selection, the peak value, histogram lower bound, and normal negative log-likelihood from 30 features are selected. Those features clearly indicate the difference of signals according to the depth of faults. In addition, as a result of applying the selected features to the support vector machine, it has been possible to perfectly distinguish between the regions with and without faults. Hence, it is expected that the results of this study will be useful in the development of an early detection system for fault growth based on ultrasonic signals and in the energy transmission related industries in the future.

본 논문에서는 관형 철탑의 용접부 결함을 상시적으로 감시하기 위하여 초음파 탐상 신호에 대한 기계학습 알고리즘의 적용 방법을 제시하고 분석하였다. 기계학습 방법으로는 유전자 알고리즘에 의한 특징 선택과 서포트 벡터머신을 이용한 탐상 신호 분류 방법을 사용하였다. 특징 선택에서는 30개의 후보 특징들 가운데 피크, 히스토그램 하한 경계, 정규 음로그우도가 선택되었으며, 이들은 결함의 깊이에 따른 신호의 차이를 명확하게 나타내었다. 또한, 선택된 특징들을 서포트 벡터 머신에 적용한 결과 정상 부위와 결함 부위를 완벽하게 분류할 수 있는 것으로 나타났다. 따라서 본 연구의 결과는 향후 초음파 신호 기반 결함 성장 조기 감지시스템의 개발과 이를 통한 에너지 송전 관련 산업에 유용하게 사용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

This work was partly supported by the Gyeongsang National University Fund for Professors on Sabbatical Leave (2019), and supported in part by the Industrial Technology Innovation Program of the Korean Institute of Energy Technology Evaluation and Planning (KETEP) granted financial resource from the Ministry of Trade, Industry & Energy, Republic of Korea (No. 20203510200060). A part of this work has also been supported by the Local Government-University Cooperation-based Regional Innovation Project (Smart Manufacturing Engineering, Gyeonsangnam-do Regional Innovation Platform) funded by the Ministry of Education (National Research Foundation of Korea, NRF).

References

  1. W. S. Choi, K. W. Song, N. K. Jeong, and J. S. Ha, "A study on crack stability of pipe-type transmission tower," Proceedings of the KSME Annual Spring Conference, Yeosu, pp. 127-128, 2013.
  2. J. Y. Kim, J. M. Yu, D. H. Lee, H. J. Jo, and S. M. Kang, "Development of monitoring system for safety of Petrochemical Plantand Guided Wave Devices," Proceedings of the KOSEE Annual Autumn Conference, Jeju, pp. 15-16, 2013.
  3. W. H. Han and J. Y. Lee, "A Study on the Treatment of Shipborne Waste Oils by Ultrasonic Cavitation," The Journal of Korean Tribology Society, vol. 19, no. 5, pp. 285-291, Oct. 2003.
  4. J. Yoon and H. J. Kim "A study on effective disinfection methods of medical Ultrasound Probe resident Floras," Korea Academy Industrial Cooperation Society, vol. 19, no. 1, pp. 346-354, Jan. 2018.
  5. S. G. Kwon, J. M. Seo, J. A. Gu, Y. S. Kim, and D. Y. Sung "Field application of Phased Array Ultrasonic Equipment," Journal of the Korean Society for Railway, vol. 23, no. 8, pp. 715-724, Aug. 2020. https://doi.org/10.7782/jksr.2020.23.8.715
  6. S. J. Lim, E. C. Kim, I. H. Cho, J. S. Kim, and S. J. Kim "Phased Array Ultrasonic Testing Verification Technic to Evaluate the Integrity of Welded Zone on Inner Shell of LNG Storage Tank," Proceedings of the KIGAS Annual Autumn Conference, Daejeon, pp. 74-75, Oct. 2020.
  7. M. S. Kim, J. W. Park, D. Y. Lee, and S. I. Baek, "Detection of the Crack on Propeller Blade by Using Phased Array Ultrasonic Testing," The Korean Society For Nondestructive Testing, vol. 40, no. 5, pp. 318-325, Oct. 2020. https://doi.org/10.7779/JKSNT.2020.40.5.318
  8. J. M. Ha, B. H. Ahn, H. T. Yu, and B. K. Choi "Feature analysis based on Genetic Algorithm for diagnosis of Misalignment," Korean Society for Noise and Vibration Engineering, vol. 27, no. 2, pp. 189-194, Apr. 2017. https://doi.org/10.5050/KSNVE.2017.27.2.189
  9. D. H. Park, B. H. Ahn, H. J. Kim, G. M. Lim, and B. K. Choi "Application of feature analysis of Ultrasound for diagnosis," Korean Society for Noise and Vibration Engineering, vol. 27, no. 5, pp. 566-572, Oct. 2017. https://doi.org/10.5050/KSNVE.2017.27.5.566
  10. J. M. Kim, B. H. Ahn, J. M. Lee, H. T. Yu, and B. K. Choi "Feature Analysis of Vibration and Acoustic Emission According to Pipe Cracking and Valve Opening/Closing," Transactions of the Korean Society for Noise and Vibration Engineering, vol. 27, no. 7, pp. 857-862, Dec. 2017. https://doi.org/10.5050/ksnve.2017.27.7.857