DOI QR코드

DOI QR Code

Development of deep learning algorithm for classification of disc cutter wear condition based on real-time measurement data

실시간 측정데이터 기반의 디스크커터 마모상태 판별 딥러닝 알고리즘 개발

  • Ji Yun Lee (Power System Research Laboratory, KEPCO Research Institute, KEPCO) ;
  • Byung Chul Yeo (Dept. of Energy Resources Engineering, Pukyong National University) ;
  • Ho Young Jeong (Dept. of Energy Resources Engineering, Pukyong National University) ;
  • Jung Joo Kim (Power System Research Laboratory, KEPCO Research Institute, KEPCO)
  • 이지윤 (한전 전력연구원 전력계통연구소) ;
  • 여병철 (부경대학교 에너지자원공학과) ;
  • 정호영 (부경대학교 에너지자원공학과) ;
  • 김정주 (한전 전력연구원 전력계통연구소)
  • Received : 2024.05.16
  • Accepted : 2024.05.28
  • Published : 2024.05.31

Abstract

The power cable tunnels which are part of the underground transmission line project, are constructed using the shield TBM method. The disc cutter among the shield TBM components plays an important role in breaking rock mass. Efficient tunnel construction is possible only when appropriate replacement occurs as the wear limit is reached or damage such as uneven wear occurs. A study was conducted to determine the wear conditions of disc cutter using a deep learning algorithm based on real-time measurement data of wear and rotation speed. Based on the results of full-scaled tunnelling tests, it was confirmed that measurement data was obtained differently depending on the wear conditions of disc cutter. Using real-time measurement data, an algorithm was developed to determine disc cutter wear characteristics based on a convolutional neural network model. Distributional patterns of data can be learned through CNN filters, and the performance of the model that can classify uniform wear and uneven wear through these pattern features.

송전선로 지중화 사업의 일환인 전력구 터널은 쉴드TBM 공법에 의해 건설된다. 쉴드TBM 구성요소 중 디스크커터는 암반을 파쇄하는 중요한 역할을 수행한다. 마모한계에 도달하거나 편마모와 같은 파손이 발생함에 따라 적절한 교체가 이루어져야 효율적인 터널 공사가 가능하다. 본 연구에서는 실시간으로 측정된 디스크커터의 마모량과 회전수를 기반으로 디스크커터의 마모상태를 판별하기 위한 딥러닝 알고리즘 개발을 수행하였다. 실대형 굴진시험 결과를 통해 디스크 커터의 마모상태에 따라 측정데이터가 상이하게 획득되는 것을 확인하였다. 합성곱신경망 모델을 기반으로 실시간 측정데이터를 활용하여 디스크커터의 마모특성을 판별할 수 있는 알고리즘을 개발하였다. 합성곱신경망의 필터를 통해 데이터의 분포 특성을 학습할 수 있고, 이러한 패턴 특징을 통해 균등마모와 편마모를 분류할 수 있는 모델의 성능을 확인하였다.

Keywords

Acknowledgement

본 연구는 한국전력공사 자체연구개발 과제(R22SA01) '전력구 공사 안전확보를 위한 디스크커터 마모측정 및 수명예측 기술 개발'의 지원으로 수행되었습니다. 연구지원에 감사드립니다.

References

  1. Bruland, A. (2000), Hard rock tunnel boring: advance rate and cutter wear, Ph.D. Dissertation, Department of Building and Construction Engineering, Norwegian University of Science and Technology, pp. 1-54.
  2. Gehring, K. (1995), "Prognosis of advance rates and wear for underground mechanized excavation", Felsbau, Vol. 13, No. 6, pp. 439-448.
  3. Hong, J.P., Ko, T.Y. (2023), "Application of multiple linear regression analysis and tree-based machine learning techniques for cutter life index (CLI) prediction", Tunnel and Underground Space, Vol. 33, No. 6, pp. 594-609. https://doi.org/10.7474/TUS.2023.33.6.594
  4. Ju, M.S., Park, M.S., Kim, J.J., Song, S.W., Do, S.C., Jeong, H. (2024), "Development and performance evaluation of real-time wear measurement system of TBM disc cutter", Tunnel and Underground Space, Vol. 34, No. 2, pp. 154-168. https://doi.org/10.7474/TUS.2024.34.2.154
  5. Kang, T.H., Choi, S.W., Lee, C., Chang, S.H. (2022), "A study on the prediction of disc cutter wear using TBM data and machine learning algorithm", Tunnel and Underground Space, Vol. 32, No. 6, pp. 502-517. https://doi.org/10.7474/TUS.2022.32.6.502
  6. Kang, Y.S., Ko, T.Y. (2024), "Prediction of disk cutter wear considering ground conditions and TBM operation parameters", Tunnel and Underground Space, Vol. 34, No. 2, pp. 143-153. https://doi.org/10.7474/TUS.2024.34.2.143
  7. Kim, J.J., Ryu, H.H., Song, S.W., Do, S.C., Lee, J.Y., Jeong, H.Y. (2024), "Development of disc cutter wear sensor prototype and its verification for ensuring construction safety of utility cable tunnels", Journal of Korean Tunnelling and Underground Space Association, Vol. 26, No. 2, pp. 91-111. https://doi.org/10.9711/KTAJ.2024.26.2.091
  8. Kim, K., Kim, J., Ryu, H., Rehman, H., Jafri, T.H., Yoo, H., Ha, S. (2020a), "Estimation method for TBM cutterhead drive design based on full-scale tunneling tests for application in utility tunnels", Applied Sciences, Vol. 10, No. 15, pp. 1-20.
  9. Kim, Y., Hong, J., Kim, B. (2020b), "Performance comparison of machine learning classification methods for decision of disc cutter replacement of shield TBM", Journal of Korean Tunnelling and Underground Space Association, Vol. 22, No. 5, pp. 575-589.
  10. La, Y.S., Kim, M.I., Kim, B. (2019), "Prediction of replacement period of shield TBM disc cutter using SVM", Journal of Korean Tunnelling and Underground Space Association, Vol. 21, No. 5, pp. 641-656. https://doi.org/10.9711/KTAJ.2019.21.5.641
  11. Lilly, J. M. (2017), "Element analysis: a wavelet-based method for analysing time-localized events in noisy time series", Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 473, No. 2200, pp. 1-28.
  12. Lilly, J. M., Olhede, S. C. (2012), "Generalized morse wavelets as a superfamily of analytic wavelets", IEEE Transactions on Signal Processing, Vol. 60, No. 11, pp. 6036-6041. https://doi.org/10.1109/TSP.2012.2210890
  13. Rostami, J., Ozdemir, L. (1993), "A new model for performance prediction of hard rock TBMs", Proceedings of the Rapid Excavation and Tunneling Conference, Boston, pp. 793-809.