Tunnel and Underground Space (터널과지하공간)

Korean Society for Rock Mechanics and Rock Engineering (한국암반공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Prediction of Uniaxial Compressive Strength Classification Using Slurry TBM Data and Random Forest

이수식 TBM 데이터와 랜덤포레스트를 이용한 일축압축강도 분류 예측에 관한 연구

  • 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)
  • 강태호 (한국건설기술연구원 지반연구본부) ;
  • 최순욱 (한국건설기술연구원 지반연구본부 ) ;
  • 이철호 (한국건설기술연구원 지반연구본부) ;
  • 장수호 (한국건설기술연구원 지반연구본부 )
  • Received : 2023.12.05
  • Accepted : 2023.12.11
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, research on predicting ground classification using machine learning techniques, TBM excavation data, and ground data is increasing. In this study, a multi-classification prediction study for uniaxial compressive strength (UCS) was conducted by applying random forest model based on a decision tree among machine learning techniques widely used in various fields to machine data and ground data acquired at three slurry shield TBM sites. For the classification prediction, the training and test data were divided into 7:3, and a grid search including 5-fold cross-validation was used to select the optimal parameter. As a result of classification learning for UCS using a random forest, the accuracy of the multi-classification prediction model was found to be high at both 0.983 and 0.982 in the training set and the test set, respectively. However, due to the imbalance in data distribution between classes, the recall was evaluated low in class 4. It is judged that additional research is needed to increase the amount of measured data of UCS acquired in various sites.

최근 국내외에서 기계학습 기법으로 TBM 굴진 데이터와 지반데이터를 분석하는 지반 분류예측 연구가 증가하고 있다. 본 연구에서는 다양한 분야에서 널리 사용되고 있는 머신러닝 기법들 중 의사결정트리 기반 랜덤포레스트 모델을 3곳의 이수식 TBM 현장에서 획득한 기계 데이터와 지반 데이터에 적용하여 일축압축강도에 대한 다중 분류예측 연구를 하였다. 일축압축강도의 다중 분류 예측을 위해서 학습과 테스트 데이터를 7:3으로 분할하였으며, 최적의 파라미터를 선정을 위해서 분할 교차검증을 포함하는 그리드 서치를 활용하였다. 의사 결정 트리를 기반으로 한 랜덤 포레스트를 사용하여 일축압축강도 분류 학습을 수행한 결과, 다중 분류 예측 모델의 정확도는 학습 세트와 테스트 세트에서 각각 0.983 및 0.982로 모두 높게 나타났다. 다만, 클래스 간 데이터 분포의 불균형으로 인하여 클래스 4에서는 재현율이 낮게 평가되었다. 다양한 현장에서 획득한 일축압축강도의 측정 데이터양을 늘리는 연구가 필요한 것으로 판단된다.

Keywords

Acknowledgement

본 연구는 국토교통부 국토교통과학기술진흥원이 시행하고 한국도로공사가 총괄하는 "스마트건설기술개발 국가R&D사업(과제번호: 23SMIP-A158708-04)"의 지원으로 수행되었습니다.

References

  1. Anon, O.H., 1979, Classification of rocks and soils for engineering geological mapping, Part I: Rock and soil materials, Bulletin of the International Association of Engineering Geology, 19, 364-371. https://doi.org/10.1007/BF02600503
  2. Ayawah, P.E., Sebbeh-Newton, S., Azure, J.W., Kaba, A.G., Anani, A., Bansah, S., and Zabidi, H., 2022, A review and case study of Artificial intelligence and Machine learning methods used for ground condition prediction ahead of tunnel boring Machines, Tunnelling and Underground Space Technology, 125, 104497.
  3. Barton, N., Lien, R., and Lunde, J., 1974, Engineering classification of rock masses for the design of tunnel support, Rock Mech., 6, 189-236. https://doi.org/10.1007/BF01239496
  4. Bieniawski, Z.T., 1989, Engineering rock mass classifications. John Wiley & Sons.
  5. Breiman, L., 1996, Bagging predictors, Machine Learning, 24, 123-140. https://doi.org/10.1007/BF00058655
  6. Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A., 1984, Classification and Regression Trees. CRC press.
  7. Deere, D.U. and Miller, R.P., 1966, Engineering classification and index properties for intact rock, Tech. Rep. No. AFWL-TR-65-115, AirForce Weapons Lab., Kirtland Air Base, New Mexico.
  8. Deere, D.U., Hendron, A.J., Patton, F.D., and Cording, E.J., 1967, Design of surface and near surface construction in rock, 8th U.S. Symposium on Rock Mechanics: Failure and breakage of rock: New York, Society of Mining Engineers, American Institute of Mining, Metallurgical, and Petroleum Engineers.
  9. ISRM, 1979, Suggested methods for determining the uniaxial compressive strength and deformability of rock materials, International Journal of Rock Mechanics and Mining. Sciences and Geomechanics Abstracts, 16, 135-140. https://doi.org/10.1016/0148-9062(79)91451-7
  10. ISRM, 1981, Suggested method for laboratory determination of direct shear strength, Rock characterisation testing and monitoring(Brown ET ed.), International Society for Rock Mechanics, Pergamon: Oxford, UK.
  11. 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
  12. 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
  13. Kang, T.H., Choi, S.W., Lee, C., and Chang, S.H., 2022, Soil Classification by Machine Learning Using a Tunnel Boring Machine's Operating Parameters, Applied Sciences, 12(22), 11480.
  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(1), 67-95. https://doi.org/10.1145/174644.174647
  15. Mokhtari, S. and Mooney, M.A., 2020, Predicting EPBM advance rate performance using support vector regression modeling, Tunn. Undergr. Space Technol., 104, 103520.
  16. Terzaghi, K., 1946, Rock defects and load on tunnel supports, Introduction to rock tunnelling with steel supports, (R.V. Proctor & T.L. White eds.) Commercial Sheering & Stamping Co: Youngstown, USA.
  17. Wickham, G.E., Tiedemann, H.R., and Skinner, E.H., 1972, Support determination based on geologic predictions, In Lane, K.S., Garfield, L.A. (eds.). Proc. 1st North American Rapid Excavation &Tunnelling Conference (RETC), Chicago. 1. American Institute of Mining, Metallurgical and Petroleum Engineers (AIME), New York, 43-64.
  18. Yang, H., Song, K., and Zhou, J., 2022, Automated recognition model of geomechanical information based on operational data of tunneling boring machines, Rock Mechanics and Rock Engineering, 1-18.