Journal of Korean Tunnelling and Underground Space Association (한국터널지하공간학회 논문집)

Korean Tunnelling and Underground Space Association (한국터널지하공간학회)
권호 표지
DOI QR코드

DOI QR Code

A ground condition prediction ahead of tunnel face utilizing time series analysis of shield TBM data in soil tunnel

토사터널의 쉴드 TBM 데이터 시계열 분석을 통한 막장 전방 예측 연구

  • Jung, Jee-Hee (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Kim, Byung-Kyu (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Chung, Heeyoung (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Kim, Hae-Mahn (School of Civil, Environmental and Architectural Engineering, Korea University) ;
  • Lee, In-Mo (School of Civil, Environmental and Architectural Engineering, Korea University)
  • 정지희 (고려대학교 건축사회환경공학부) ;
  • 김병규 (고려대학교 건축사회환경공학부) ;
  • 정희영 (고려대학교 건축사회환경공학부) ;
  • 김해만 (고려대학교 건축사회환경공학부) ;
  • 이인모 (고려대학교 건축사회환경공학부)
  • Received : 2018.12.19
  • Accepted : 2019.01.24
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a method to predict ground types ahead of a tunnel face utilizing operational data of the earth pressure-balanced (EPB) shield tunnel boring machine (TBM) when running through soil ground. The time series analysis model which was applicable to predict the mixed ground composed of soils and rocks was modified to be applicable to soil tunnels. Using the modified model, the feasibility on the choice of the soil conditioning materials dependent upon soil types was studied. To do this, a self-organizing map (SOM) clustering was performed. Firstly, it was confirmed that the ground types should be classified based on the percentage of 35% passing through the #200 sieve. Then, the possibility of predicting the ground types by employing the modified model, in which the TBM operational data were analyzed, was studied. The efficacy of the modified model is demonstrated by its 98% accuracy in predicting ground types ten rings ahead of the tunnel face. Especially, the average prediction accuracy was approximately 93% in areas where ground type variations occur.

토압식(Earth Pressure-Balanced, EPB) 쉴드 TBM 기계데이터 분석을 통해 토사터널의 특징이 반영된 막장 전방 예측 방법을 제안하였다. 기존에 암반과 토사가 혼합된 복합 지반의 예측에 적용하였던 시계열 분석 모델을 토사터널에 적용가능하도록 수정하였다. 또한 수정된 모델을 사용하여, 토사 종류에 따라 쏘일 컨디셔닝 재료를 선택하는 것이 타당한지 연구하였다. 이를 위해 Self-Organizing Map (SOM) 군집화(clustering) 분석을 수행하였다. 그 결과 무엇보다도 지반타입이 #200체 통과량 35% 기준으로 분류되어야 한다는 것을 확인하였다. 또한 TBM 기계데이터 분석을 통해 수정된 모델이 지반 타입을 예측하는데 사용될 수 있음을 확인하였다. 수정된 기준에 따라 지반 타입을 분류하고 시계열 분석을 수행하면, 10막장 전방 지반에 대해서 98%의 높은 예측 정확도를 보였으며, 이를 통해 수정된 방법의 우수성이 입증되었다. 특히 지반 타입 변화 구간에 대한 예측 정확도도 약 93%로, 10막장 전방에서 지반 타입 변화 여부를 미리 확인할 수 있게 되었다.

Keywords

TNTNB3_2019_v21n2_227_f0001.png 이미지

Fig. 1. Example of deep neural networks

TNTNB3_2019_v21n2_227_f0002.png 이미지

Fig. 2. A time-delay neural network for one-dimensional input/output signals (Hassoun, 1995)

TNTNB3_2019_v21n2_227_f0003.png 이미지

Fig. 3. A result of the SOM clustering

TNTNB3_2019_v21n2_227_f0004.png 이미지

Fig. 4. The profile of machine data groups

TNTNB3_2019_v21n2_227_f0005.png 이미지

Fig. 5. Comparison between the soil conditioning materials and the machine data

TNTNB3_2019_v21n2_227_f0006.png 이미지

Fig. 6. The distribution of the percentage passing through the #200 sieve along the entire route

TNTNB3_2019_v21n2_227_f0007.png 이미지

Fig. 7. Comparison between the soil conditioning materials and the ground types

TNTNB3_2019_v21n2_227_f0008.png 이미지

Fig. 8. Comparison between the soil conditioning materials and the normalized machine data

TNTNB3_2019_v21n2_227_f0009.png 이미지

Fig. 9. Flow chart to run the developed time delay neural network (TDNN) engine (Jung at al., 2018)

TNTNB3_2019_v21n2_227_f0010.png 이미지

Fig. 10. The location of sections at job site

Table 1. Conditions at a job site

TNTNB3_2019_v21n2_227_t0001.png 이미지

Table 2. Properties of soils

TNTNB3_2019_v21n2_227_t0002.png 이미지

Table 3. Classification of ground types

TNTNB3_2019_v21n2_227_t0003.png 이미지

Table 4. Analysis cases

TNTNB3_2019_v21n2_227_t0004.png 이미지

Table 5. TDNN learning method and final model selection criteria (Jung at al., 2018)

TNTNB3_2019_v21n2_227_t0005.png 이미지

Table 6. The results of ANN engine

TNTNB3_2019_v21n2_227_t0006.png 이미지

Table 7. The results of analysis cases

TNTNB3_2019_v21n2_227_t0007.png 이미지

Table 8. Decision criteria for ground type classification in the TDNN model (modified from Jung et al. (2018))

TNTNB3_2019_v21n2_227_t0008.png 이미지

Table 9. Comparison of predicted and actual ground types

TNTNB3_2019_v21n2_227_t0009.png 이미지

Table 10. Comparison of average prediction accuracy

TNTNB3_2019_v21n2_227_t0010.png 이미지

Table 11. Soil conditioning materials according to predicted ground types

TNTNB3_2019_v21n2_227_t0011.png 이미지

References

  1. Beale, M.H., Hagan, M.T., Demuth, H.B. (2016), Neural network toolbox$^TM$ user's guide, version R2016a, The Math Works, Inc., Natick.
  2. Box, G.E.P., Jenkins, G.M. (1970), Time series analysis: forecasting and control, Holden-Day, San Francisco.
  3. Buduma, N., Locascio, N. (2017), Fundamentals of deep learning: designing next-generation machine intelligence algorithms (1st edition), O'Reilly Media, Sebastopol.
  4. Chung, H., Lee, I.M., Jung, J.H., Park, J. (2019), "Bayesian networks-based shield TBM risk management system: methodology development and application", KSCE Journal of Civil Engineering, Vol. 23, No. 1, pp. 452-465. https://doi.org/10.1007/s12205-018-0912-y
  5. Dorffner, G. (1996), "Neural networks for time series processing", Neural Network World, Vol. 6, No. 4, pp. 447-468.
  6. Han, H.Y. (2009), Pattern recognition, Hanbit Media, Inc., Seoul.
  7. Hassoun, M.H. (1995), Fundamentals of artificial neural networks, MIT Press, Cambridge.
  8. IBM Corp. (2016), IBM SPSS Forecasting 24, IBM Corp., New York.
  9. Jung, J.H., Chung, H., Kim, T.H., Lee, I.M. (2018). "A hybrid time series model to predict ground conditions ahead of tunnel face utilizing shield TBM operational data", Tunnelling and Underground Space Technology, Under Review.
  10. Kim, P. (2017), MATLAB deep learning: with machine learning, neural networks and artificial intelligence, Apress, New York, p. 53-80.
  11. Kim, S.P. (2016), Deep learning for beginners, Hanbit Media, Inc., Seoul.
  12. Kim, T.H., Kwon, Y.S., Chung, H., Lee, I.M. (2018), "A simple test method to evaluate workability of conditioned soil used for EPB Shield TBM", Journal of Korean Tunnelling and Underground Space Association, Vol. 20, No. 6, pp. 1049-1060. https://doi.org/10.9711/KTAJ.2018.20.6.1049
  13. Lee, I.M. (2016), Geotechnical aspects of tunnelling (3rd edition), CIR, Seoul, pp. 129-176.
  14. Lee, W.W. (2011), Time series analysis: Statistical method for predicting, Freedom Academy Inc., Paju.
  15. Patterson, D.W. (1995), Artificial neural networks: theory and applications, Springer, New York, pp. 1-179.
  16. Ripley, B.D. (1996), Pattern recognition and neural networks, Cambridge University Press, New York.
  17. Shin, C.H., Jeong, S.H. (2011), "A study on application of ARIMA and neural networks for time series forecasting of port traffic", Journal of Navigation and Port Research, Vol. 35, No. 1, pp. 83-91. https://doi.org/10.5394/KINPR.2011.35.1.83
  18. Taylor, K. (2017), Deep learning using MATLAB neural network applications, CreateSpace Independent Publishing Platform, Lavergne.
  19. Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J. (1989), "Phoneme recognition using time delay neural networks", IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 37, No. 3, pp. 328-339. https://doi.org/10.1109/29.21701
  20. Zumsteg, R., Langmaack, L. (2017), "Mechanized tunneling in soft soils: choice of excavation mode and application of soil-conditioning additives in glacial deposits", Engineering, Vol. 3, No. 6, pp. 863-870. https://doi.org/10.1016/j.eng.2017.11.006