Journal of the Korean Geosynthetics Society (한국지반신소재학회논문집)

Korean Geosynthetics Society (한국지반신소재학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Development of Artificial Neural Network (ANN) for Deep Excavation Design

깊은굴착 설계를 위한 인공신경망 개발에 관한 연구

  • Yoo, Chungsik (School of Civil and Environmental Engineering, Sungkyunkwan Univ. Natural Sciences Campus) ;
  • Yang, Jaewon (School of Civil and Environmental Engineering, Sungkyunkwan Univ. Natural Sciences Campus) ;
  • Abbas, Qaisar (School of Civil and Environmental Engineering, Sungkyunkwan Univ. Natural Sciences Campus) ;
  • Aizaz, Haider Syed (School of Civil and Environmental Engineering, Sungkyunkwan Univ. Natural Sciences Campus)
  • Received : 2018.11.28
  • Accepted : 2018.12.14
  • Published : 2018.12.30
Download PDF
⟨ Previous Next ⟩

Abstract

This research concerns the prediction method for ground movement and wall member force due to determination structural stability check and failure check during deep excavation construction. First, research related with excavation influence parameters is conducted. Then, numerical analysis for various excavation conditions were conducted using Finite Element Method and Beam-column elasto-plasticity method. Excavation analysis database was then constructed. Using this database, development of ANN (artificial neural network) was performed for each ground movements and using structural member forces. By comparing the numerical analysis results with ANN's prediction, it is validated that development of ANN can be used efficient for prediction of ground movement and structural member forces in deep excavation site.

본 연구에서는 깊은 굴착에 따른 인접구조물의 손상 평가 및 벽체 구조물의 안정성 평가를 하기 위한 지표의 거동 및 벽체 부재력의 효율적인 예측기법에 대한 내용을 다루었다. 우선적으로 지표의 거동 및 벽체 부재력에 영향을 미치는 매개 변수에 대한 연구를 수행하였고, 이를 토대로 다양한 굴착 조건에 대해 수치해석을 실시한 결과를 통해 데이터베이스를 구축하였다. 구축된 데이터베이스를 토대로 벽체의 부재력과 지표의 거동 각각의 해석 결과에 대한 인공신경망 엔진 학습을 수행하였으며 학습된 인공신경망을 이용하여 예측된 결과와 사용된 데이터베이스의 결과를 비교하여 인공신경망 엔진이 벽체의 부재력 및 지표의 거동예측에 효율적임을 검증하였다.

Keywords

HKTHB3_2018_v17n4_199_f0001.png 이미지

Fig. 2. Flow chart of Artificial Neural Network (ANN)

HKTHB3_2018_v17n4_199_f0002.png 이미지

Fig. 1. Organization chart of Artificial Neural Network (ANN)

HKTHB3_2018_v17n4_199_f0003.png 이미지

Fig. 3. Cross section of excavation condition

HKTHB3_2018_v17n4_199_f0004.png 이미지

Fig. 4. Excavation construction steps

HKTHB3_2018_v17n4_199_f0005.png 이미지

Fig. 5. Excavation construction modelling using Abaqus 2018

HKTHB3_2018_v17n4_199_f0006.png 이미지

Fig. 6. Excavation construction modelling using MIDAS IT GeoXD

HKTHB3_2018_v17n4_199_f0007.png 이미지

Fig. 7. Process of Artificial Neural Network (ANN) result prediction

HKTHB3_2018_v17n4_199_f0008.png 이미지

Fig. 8. Validation for R2 of ground movement ANN

HKTHB3_2018_v17n4_199_f0009.png 이미지

Fig. 9. RSE for ground movement ANN

HKTHB3_2018_v17n4_199_f0010.png 이미지

Fig. 10. RI for ground movement ANN

HKTHB3_2018_v17n4_199_f0011.png 이미지

Fig. 11. Validation for R2 of structural member force ANN

HKTHB3_2018_v17n4_199_f0012.png 이미지

Fig. 12. RSE for structural member force ANN

HKTHB3_2018_v17n4_199_f0013.png 이미지

Fig. 13. RI for structural member force ANN

Table 1. Input parameters and output parameters

HKTHB3_2018_v17n4_199_t0001.png 이미지

Table 2. Ground conditions

HKTHB3_2018_v17n4_199_t0002.png 이미지

Table 3. Range of input parameters

HKTHB3_2018_v17n4_199_t0003.png 이미지

Table 4. Maximum and Minimum values of ground movement database

HKTHB3_2018_v17n4_199_t0004.png 이미지

Table 5. Validation of ground movement ANN

HKTHB3_2018_v17n4_199_t0005.png 이미지

Table 6. Maximum and Minimum values of structural member forces database

HKTHB3_2018_v17n4_199_t0006.png 이미지

Table 7. Validation of structural member forces ANN

HKTHB3_2018_v17n4_199_t0007.png 이미지

Table 8. Validation sets

HKTHB3_2018_v17n4_199_t0008.png 이미지

Table 9. Validation result

HKTHB3_2018_v17n4_199_t0009.png 이미지

References

  1. ABAQUS user's manual, Version 6.17. (2017). Hibbitt, Karlsson, and Sorensen, Inc., Pawtucket, Providence, R.I.
  2. Bae, G.J., Shin, H.S., Kim, D.G., Chang, S.H., Lim, J.J., Lee, G.P., Choi, S.W., KICT (2005), "Development of technologies for minimizing and preventing the disaster on tunnel construction 2", KICT, pp.73-87.
  3. Beale, M. H., Hagan, M. T. and Demuth, H. B. (2013), "Neural Network Toolbox User's Guide", Mathwork Inc.
  4. Jiao, Y. and Hudson, J. A. (1995), "The fully-coupled model for rock engineering system", Rock Mechanics and Mining Sciences & Geomechanics, Vol.32, Issue 5, pp.491-512. https://doi.org/10.1016/0148-9062(95)00038-I
  5. Kim, C. Y., Bae, G. J., Hong, S. W., Park, C. H., Moon, H. K. and Shin, H. S. (2001), "Neural network based prediction of ground surface settlements due to tunneling", Computers and Geotechnics, Vol.28, pp.517-547. https://doi.org/10.1016/S0266-352X(01)00011-8
  6. Matlab user manual version R2017 (2017), MathWorks, Inc.
  7. MIDAS (2010). "MIDAS GEOXD user's manual." MIDAS Information Technology Co.
  8. Woo S. J., Chung E. M. and Yoo C. S. (2016) "Development of optimized TBM segmental lining desing system", Journal of Korean Tunnelling and Underground Space Association, Vol.18, Issue 1, pp.13-30. https://doi.org/10.9711/KTAJ.2016.18.1.013
  9. Yang, Y. and Zhang, Q. (1997), "A hierarchical analysis for rock engineering using artificial neural networks", Rock Mechanics and Rock Engineering, Vol.30, Issue 4, pp.207-222. https://doi.org/10.1007/BF01045717
  10. Yang, Y. and Zhang, Q. (1998), "The application of neural networks to rock engineering system (RES)", Rock Mechanics and Mining Sciences, Vol.35, Issue 6, pp.727-745. https://doi.org/10.1016/S0148-9062(97)00339-2
  11. Yoo C. S. and Choi B. S. (2004) "Prediction of deep excavation induced ground surface movements using artificial neural network", Journal of Korean geotechnical society, Vol. 20, Issue 3, pp.53-65.
  12. Yoo C. S., Kim S. B., Joseph B. and Han D. H. (2006) "ANN-based prediction on tunnel behavior", Conference on Korean geotechnical society, Vol.10, pp.777.
  13. Yoo, C. S., Kim, S. B. and Yoo, K. H. (2008), "Development of IT-based tunnel design system", Journal of Korean Tunnelling and Underground Space Association, Vol.10, No.2, pp.153-166.