터널과지하공간 (Tunnel and Underground Space)

  • 제32권6호
  • /
  • Pages.502-517
  • /
  • 2022
  • /
  • 1225-1275(pISSN)
  • /
  • 2287-1748(eISSN)
한국암반공학회 (Korean Society for Rock Mechanics and Rock Engineering)
권호 표지
DOI QR코드

DOI QR Code

TBM 데이터와 머신러닝 기법을 이용한 디스크 커터마모 예측에 관한 연구

A Study on the Prediction of Disc Cutter Wear Using TBM Data and Machine Learning Algorithm

  • 강태호 (한국건설기술연구원 지반연구본부 ) ;
  • 최순욱 (한국건설기술연구원 지반연구본부 ) ;
  • 이철호 (한국건설기술연구원 지반연구본부 ) ;
  • 장수호 (한국건설기술연구원 지반연구본부 )
  • Tae-Ho, Kang (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Soon-Wook, Choi (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Chulho, Lee (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Soo-Ho, Chang (Department of Geotechnical Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • 투고 : 2022.11.24
  • 심사 : 2022.12.01
  • 발행 : 2022.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

TBM의 활용이 증가하면서 최근 국내외에서 머신러닝 기법으로 TBM 데이터를 분석하여 디스크커터의 교환주기 예측 및 굴진율을 예측하는 연구가 증가하고 있다. 본 연구에서는 굴진 시 획득되는 기계 데이터와 지반 데이터를 기반으로 최근에 다양한 분야에서 널리 사용되고 있는 머신러닝 기법들 중 회귀 모델을 접목하여 슬러리 쉴드 TBM 현장의 디스크 커터 마모 예측을 하였다. 디스크 커터 마모 예측을 위해서 Training과 Test 데이터를 7:3으로 분할하였으며, 최적의 파라미터를 선정을 위해서 분할 교차검증을 포함하는 그리드 서치를 활용하였다. 그 결과, 앙상블 계열의 그레디언트 부스팅 모델이 결정계수가 0.852, 평균 제곱근 오차가 3.111로 좋은 성능을 보여주었고 특히 학습성능과 더불어 학습속도에서 우수한 결과를 보여주었다. 현재 도출된 결과로 볼 때, 슬러리 쉴드 TBM의 기계데이터와 지반정보가 포함된 데이터를 활용한 디스크 커터 마모 예측 모델의 적합성은 높다고 보인다. 추가적으로 지반조건의 다양성과 디스크 마모 측정 데이터양을 늘리는 연구가 필요한 것으로 판단된다.

As the use of TBM increases, research has recently increased to to analyze TBM data with machine learning techniques to predict the exchange cycle of disc cutters, and predict the advance rate of TBM. In this study, a regression prediction of disc cutte wear of slurry shield TBM site was made by combining machine learning based on the machine data and the geotechnical data obtained during the excavation. The data were divided into 7:3 for training and testing the prediction of disc cutter wear, and the hyper-parameters are optimized by cross-validated grid-search over a parameter grid. As a result, gradient boosting based on the ensemble model showed good performance with a determination coefficient of 0.852 and a root-mean-square-error of 3.111 and especially excellent results in fit times along with learning performance. Based on the results, it is judged that the suitability of the prediction model using data including mechanical data and geotechnical information is high. In addition, research is needed to increase the diversity of ground conditions and the amount of disc cutter data.

키워드

과제정보

본 연구는 국토교통부 국토교통과학기술진흥원의 스마트건설기술개발사업(과제번호: 22SMIP-A158708-03)인 "교량 및 터널의 원격, 자동화 시공을 위한 핵심기술 개발"의 지원으로 수행되었습니다.

참고문헌

  1. Armaghani, D.J., Mohamad, E.T., Narayanasamy, M.S., Narita, N., and Yagiz, S., 2017, "Development of hybrid intelligent models for predicting TBM penetration rate in hardrock condition", Tunn. Undergr. Space Technol., 63, 29-43. https://doi.org/10.1016/j.tust.2016.12.009
  2. Breiman, L., 1996. "Bagging predictors", Machine Learning, 24, 123-140. https://doi.org/10.1007/ BF00058655.
  3. Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A., 1984, "Classification and Regression Trees", CRC press.
  4. Bruland, A., 1998, "Hard rock tunnel boring advance rate and cutter wear", Doctoral Thesis at NTNU, 3, 81.
  5. Chen, R., Zhang, P., Wu, H., Wang, Z., and Zhong, Z., 2019, " Prediction of shield tunneling-induced ground settlement using machine learning techniques", Front. Struct. Civ. Eng., 13, 1363-1378. https://doi.org/10.1007/s11709-019-0561-3
  6. Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., and Chen, K., 2015, Xgboost: extreme gradient boosting, R package version 0.4-2, 1(4), 1-4.
  7. Cover, T. and Hart, P., 1967, "Nearest neighbor pattern classification", in IEEE Transactions on Information Theory, 13(1), 21-27, doi: 10.1109/TIT.1967.1053964.
  8. Friedman, J. H., 2001, Greedy function approximation: a gradient boosting machine, Annals of Statistics, 1189-1232.
  9. Gehring, K., 1995, "Leistungs-und verschleissprognosen im maschinellen tunnelbau", Felsbau, 13(6), 439-448.
  10. Jung, J.-H., Kim, B.-K., Chung, H., Kim, H.-M., and Lee, I.-M., 2019, "A ground condition prediction ahead of tunnel face utilizing time series analysis of shield TBM data in soil tunnel", Journal of Korean Tunnelling and Underground Space Association, 21(2), 227-242. https://doi.org/10.9711/KTAJ.2019.21.2.227
  11. Kang, T. H., Choi, S.W., Lee, C., and Chang, S.H., 2021, A Study on the Prediction of Rock Classification Using Shield TBM Data and Machine Learning Classification Algorithms, Tunnel and Underground Space, 31(6), 494-507. https://doi.org/10.7474/TUS.2021.31.6.494
  12. Kang, T.-H., Choi, S.-W., Lee, C., and Chang, S.-H., 2020, "A Study on Prediction of EPB shield TBM Advance Rate using Machine Learning Technique and TBM Construction Information", Tunnel and Underground Space, 30(6), 540-550. https://doi.org/10.7474/TUS.2020.30.6.540
  13. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T. Y., 2017, Lightgbm: A highly efficient gradient boosting decision tree, Advances in Neural Information Processing Systems, 30.
  14. Kearns, M. and Valiant, L.G., 1994, "Cryptographic limitations on learning Boolean formulae and finite automata", Journal of the Association for Computing Machinery, 41, 67-95. https://doi.org/10.1145/174644.174647
  15. Kim, D., Kwon, K., Pham, K., Oh, J.Y., and Choi, H., 2022, Surface settlement prediction for urban tunneling using machine learning algorithms with Bayesian optimization, Automation in Construction, 140, 104331. https://doi.org/10.1016/j.autcon.2022.104331
  16. Kim, T.H., Ko, T.Y., Park, Y.S., Kim, T.K., and Lee, D.H., 2020a, "Prediction of Uniaxial Compressive Strength of Rock using Shield TBM Machine Data and Machine Learning Technique", Tunnel & Underground Space, 30(3), 214-225. https://doi.org/10.7474/TUS.2020.30.3.214
  17. Kim, Y., Hong, J., and 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, 22(5), 575-589. https://doi.org/10.9711/KTAJ.2020.22.5.575
  18. Ko, T.Y., Yoon, H.J., and Son, Y.J., 2014, "A comparative study on the TBM disc cutter wear prediction model", Journal of Korean Tunnelling and Underground Space Association, 16(6), 533-542. https://doi.org/10.9711/KTAJ.2014.16.6.533
  19. La, Y. S., Kim, M.I., and Kim, B., 2019, "Prediction of replacement period of shield TBM disc cutter using SVM", Journal of Korean Tunnelling and Underground Space Association, 21(5), 641-656.
  20. Mokhtari, S. and Mooney, M.A., 2020, "Predicting EPBM advance rate performance using support vector regression modeling", Tunn. Undergr. Space Technol., 104, 103520. https://doi.org/10.1016/j.tust.2020.103520.
  21. Rosenblatt, F., 1958, The perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review, 65(6), 386.
  22. Rostami, J. and Ozdemir, L., 1993, "A new model for performance prediction of hard rock TBMs", Proceedings of the Rapid Excavation and Tunneling Conference (RETC), Boston, U.S.A., pp. 793-809.
  23. Rumelhart, D.E., Hinton, G.E., and Williams, R.J., 1986, "Learning Internal Representations by Error Propagation", David E. Rumelhart, James L. McClelland, and the PDP research group. (editors), Parallel distributed processing: Explorations in the microstructure of cognition, Volume 1: Foundation. MIT Press.
  24. Vapnik, V., 1995, "The Nature of Statistical Learning Theory. Springer", New York.
  25. Yagiz, S. and Karahan, H., 2011, "Prediction of hard rock TBM penetration rate using particle swarm optimization", Rock Mechanics and Mining Science, 48(3), 427-433. https://doi.org/10.1016/j.ijrmms.2011.02.013
  26. Yagiz, S., 2008, "Utilizing rock mass properties for predicting TBM performance in hard rock condition", Tunn. Undergr. Space Technol., 23(3), 326-339. https://doi.org/10.1016/j.tust.2007.04.011
  27. Yang, H., Song, K., and Zhou, J., 2022, "Automated recognition model of geomechanical information based on operational data of tunneling boring machines", Rock Mech. Rock Eng., 55, 1499-1516.  https://doi.org/10.1007/s00603-021-02723-5