Journal of the Korean Geotechnical Society (한국지반공학회논문집)

Korean Geotechnical Society (한국지반공학회)
권호 표지
DOI QR코드

DOI QR Code

Time Series Analysis for Predicting Deformation of Earth Retaining Walls

시계열 분석을 이용한 흙막이 벽체 변형 예측

  • 서승환 (한국건설기술연구원 지반연구본부) ;
  • 정문경 (한국건설기술연구원 지반연구본부)
  • Received : 2024.03.08
  • Accepted : 2024.03.28
  • Published : 2024.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study employs traditional statistical auto-regressive integrated moving average (ARIMA) and deep learning-based long short-term memory (LSTM) models to predict the deformation of earth retaining walls using inclinometer data from excavation sites. It compares the predictive capabilities of both models. The ARIMA model excels in analyzing linear patterns as time progresses, while the LSTM model is adept at handling complex nonlinear patterns and long-term dependencies in the data. This research includes preprocessing of inclinometer measurement data, performance evaluation across various data lengths and input conditions, and demonstrates that the LSTM model provides statistically significant improvements in prediction accuracy over the ARIMA model. The findings suggest that LSTM models can effectively assess the stability of retaining walls at excavation sites. Additionally, this study is expected to contribute to the development of safety monitoring systems at excavation sites and the advancement of time series prediction models.

본 연구는 전통적인 통계기반 ARIMA(Auto-Regressive Integrated Moving Average) 모델과 딥러닝 기반 LSTM(Long Short-Term Memory) 모델을 활용하여 굴착 현장의 지중경사계 데이터를 통한 흙막이 벽체 변형을 예측하고, 두 모델의 예측 성능을 비교 분석하였다. ARIMA 모델은 시간의 흐름에 따른 시계열 데이터의 선형적 패턴을 분석하는 데 강점을 보이는 반면, LSTM은 데이터의 복잡한 비선형 패턴과 장기 의존성을 포착하는 데 우수한 능력을 보여주었다. 본 연구는 흙막이 벽체 변형 예측을 위해 지중경사계 계측 데이터에 대한 전처리, 다양한 시계열 데이터 길이 및 입력변수 조건 등에 따른 성능 평가를 포함하였으며, LSTM 모델이 ARIMA 모델에 비해 통계적으로 유의미한 예측 성능 향상을 확인하였다. 본 연구의 결과는 굴착 현장에서의 지중경사계 데이터를 활용한 흙막이 벽체의 안정성 평가에 LSTM 모델을 효과적으로 적용할 수 있음을 보여준다. 또한 이를 바탕으로 향후 굴착 현장 전체에 대한 안전모니터링 시스템 구축과 시계열 예측 모델 발전에 기여할 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 한국건설기술연구원 주요사업으로 수행되었습니다(과제번호 20240133-001, 지반분야 재난재해 대응과 미래 건설산업 신성장을 위한 지반 기술 연구).

References

  1. Box, G. E. P., Jenkins, G. M., Reinsel, G. C., and Ljung, G. M. (2015), Time Series Analysis: Forecasting and Control (5th edition), Hoboken, New Jersey, USA, John Wiley & Sons.
  2. Clough, G. W. and O'Rourke, T. D. (1990), Construction Induced Movements of in Situ Walls, Proceedings of the Specialty Conference on Design and Performance of Earth Retaining Structures, ASCE, Reston, VA, USA, pp.439-470.
  3. Goh, A. T. C., Zhang, R. H., Wang, W., Wang, L., Liu, H. L., and Zhang, W. G. (2020), Numerical Study of the Effects of Groundwater Drawdown on Ground Settlement for Excavation in Residual Soils, Acta Geotechnica, Vol.15, pp.1259-1272.
  4. Goh, A. T. C., Zhang, F., Zhang, W., Zhang, Y., and Liu, H. (2017), A Simple Estimation Model for 3D Braced Excavation Wall Deflection, Computers and Geotechnics, Vol.83, No.3, pp.106-113.
  5. Goh, A. T. C., Wong, K. S., and Broms, B. B. (1995), Estimation of Lateral Wall Movements in Braced Excavations Using Neural Networks, Canadian Geotechnical Journal, Vol.32, No.6, pp.1059-1064.
  6. Hsieh, P. G. and Ou, C. Y. (1998), Shape of Ground Surface Settlement Profiles Caused by Excavation, Can. geotechnical J., Vol.35, No.6, pp.1004-1017.
  7. Hochreiter, S. and Schmidhuber, J. (1997), Long Short-Term Memory, Neural Comput., Vol.9, No.8, pp.1735-1780.
  8. Hou, Y. M., Wang, J. H., and Zhang, L. L. (2009), Finite-element Modeling of a Complex Deep Excavation in Shanghai, Acta Geotechnica, Vol.4, pp.7-16.
  9. Hsiung, BC. B. (2020), Observations of the Ground and Structural Behaviors Induced by a Deep Excavation in Loose sands, Acta Geotechnica, Vol.15, pp.1577-1593.
  10. Kim, H. T., Park, S. W., Kwon, Y. H., and Kim, J. H. (2000), Development of a System Predicting Maximum Displacement of Earth Retaining Walls at Various Excavation Stages Using Artificial Neural Network, J. of the Korean Geotechnical Society, Vol.16, No.1, pp.83-97.
  11. Kung, G. T. C., Hsiao, E. C. L., Schuster, M., and Juang, C. H. (2007), A Neural Network Approach to Estimating Deflection of Diaphragm Walls Caused by Excavation in Clays, Computers and Geotechnics, Vol.34, No.5, pp.385-396.
  12. Lee, S. J., Song, T. W., Lee, Y. S., Song, Y. H., and Kim, H. K. (2007), A Case Study of Building Damage Risk Assessment Due to the Multi-propped Deep Excavation in Deep Soft Soil, Proceedings of the 4th Int. Conf. Soft Soil Eng., Vancouver, London, Taylor Francis.
  13. Lee, S. and Kim, S. K. (2008), A Study on Deformation Analysis of the Earth Retaining Wall, J. of the Korean Geotechnical Society, Vol.24, No.2, pp.27-36.
  14. Li, M. G., Xiao, X., Wang, J. H., and Chen, J. J. (2019), Numerical Study on Responses of an Existing Metro Line to Staged Deep Excavations, Tunn. Undergr. Space Technol., Vol.85, pp.268-281. https://doi.org/10.1016/j.tust.2018.12.005
  15. Li, S., Li, W., Cook, C., Zhu, C., and Gao, Y. (2018), Independently Recurrent Neural Network (IndRNN): Building a Longer and Deeper RNN, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, pp.5457-5466.
  16. Lim, A., Ou, C. Y., and Hsieh, P. G. (2018), Investigation of the Integrated Retaining System to Limit Deformations Induced by Deep Excavation, Acta Geotechnica, Vol.13, pp.973-995.
  17. Long, M. (2001), Database for Retaining Wall and Ground Movements Due to Deep Excavations, J. Geotech. Geoenviron. Eng., Vol.127, No.3, pp.203-224. https://doi.org/10.1061/(ASCE)1090-0241(2001)127:3(203)
  18. Mahmoodzadeh, A., Mohammadi, M., Daraei, A., Ali, H.F.H., Al-Salihi, N.K., and Omer, R.M.D. (2020), Forecasting Maximum Surface Settlement Caused by Urban Tunneling, Automation in Construction, Vol.120, 103375.
  19. Meng, F. F., Chen, R. P., Wu, H.N., Xie, S.W., and Liu, Y. (2020), Observed Behaviors of a Long and Deep Excavation and Collinear Underlying Tunnels in Shenzhen Granite Residual Soil, Tunn. Undergr. Space Technol., 103:103504.
  20. Moormann, C. (2004), Analysis of Wall and Ground Movements Due to Deep Excavation in Soft Soil Based on a New Worldwide Database, Soils and Foundations, Vol.44, No.10, pp.87-98.
  21. Peck, R. B. (1969), Deep Excavations and Tunneling in Soft Ground, Proceedings of the 7th International Conference on Soil Mechanics and Foundation Engineering, Mexico City, pp.225-290.
  22. Seo, M. W., Seok, J. W., Yang, K. S., and Kim, M. M. (2006), Sequential Analysis of Adjacent Ground Behavior Caused by Deep Excavations, J. of the Korean Geotechnical Society, Vol.22, No.2, pp.19-28.
  23. Seo, S. and Chung, M. (2023), Development of an Ensemble Prediction Model for Lateral Deformation of Retaining Wall under Construction, J. of the Korean Geotechnical Society, Vol.39, No.4, pp.5-17.
  24. Seo, S., Park, J., Ko, Y., Kim, G., and Chung M. (2023), Geotechnical Factors Influencing Earth Retaining Wall Deformation During Excavations, Front. Earth Sci., 11:1263997.
  25. Seo, S. and Chung, M. (2022), Evaluation of Applicability of 1DCNN and LSTM to Predict Horizontal Displacement of Retaining Wall According to Excavation Work, Int. J. Adv. Comput. Sci. Appl., Vol.13, No.2, pp.86-91.
  26. Semenoglou, A. A., Spiliotis, E., and Assimakopoulos, V. (2023), Data Augmentation for Univariate Time Series Forecasting with Neural Networks, Pattern Recognition, Vol.134, 109132.
  27. Shan, J., Zhang, X., Liu, Y., Zhang, C., and Zhou, J. (2024), Deformation prediction of large-scale civil structures using spatiotemporal clustering and empirical mode decompostion-based long short-term memory network, Automation in Construction, 158, 105222,.
  28. Son, M. and Cording, E. J. (2005), Estimation of Building Damage Due to Excavation-induced Ground Movements, Geotech. Geoenvironmental. Eng., Vol.131, No.2, pp.162-177. https://doi.org/10.1061/(ASCE)1090-0241(2005)131:2(162)
  29. Son, M. and Cording, E. J. (2007), Evaluation of Building Stiffness for Building Response Analysis to Excavation-induced Ground Movements, Geotech. Geoenvironmental. Eng., Vol.133, No.8, pp. 995-1002.
  30. Suhermi, N., Permata, R. P., and Rahayu, S. P. (2019), Forecasting the Search Trend of Muslim Clothing in Indonesia on Google Trends Data Using ARIMAX and Neural Network, Proceedings of Soft Computing in Data Science: 5th International Conference, Lizuka, Japan, pp.272-286.
  31. Wong, I. H. and Poh, T. Y. (2000), Effects of Jet Grouting on Adjacent Ground and Structures, J. Geotechnical Geoenvironmental Eng. Vol.126, No.3, pp.247-256. https://doi.org/10.1061/(ASCE)1090-0241(2000)126:3(247)
  32. Yang, B.B., Yin, K.L., Lacasse, S., and Liu, Z.Q., (2019), Time Series Analysis and Long Short-term Memory Neural Network to Predict Landslide Displacement, Landslides, 16, pp.677-694.
  33. Zhao, H. J., Liu, W., Shi, P. X, Du, J. T., and Chen, X. M. (2021), Spatiotemporal Deep Learning Approach on Estimation of Diaphragm Wall Deformation Induced by Excavation, Acta Geotechnica, Vol.16, pp.3631-3645.
  34. Zhang, W., Zhang, R., Wu C., Goh, A.T.C., Lacasse, S., Liu, Z., and Liu H. (2020a), State-of-the-art Review of Soft Computing Application in Underground Excavations, Geoscience Frontiers, Vol.11, No.4, pp.1095-1106. https://doi.org/10.1016/j.gsf.2019.12.003
  35. Zhang, R., Wu, C., Goh, A. T. C., Bohlke, T., and Zhang, W. (2021), Estimation of Diaphragm Wall Deflections for Deep Braced Excavation in Anisotropic Clays Using Ensemble Learning, Geoscience Frontiers, Vol.12, No.1, pp.365-373.
  36. Zhang, P., Wu, H.N., Chen, R.P., Dai, T., Meng, F.Y., and Wang, H.B. (2020b), A Critical Evaluation of Machine Learning and Deep Learning in Shield-ground Interaction Prediction, Tunn. Undergr. Space Technol., Vol.106, 103593.
  37. Zhang, W., Goh, A. T., and Xuan, F. (2015), A Simple Prediction Model for Wall Deflection Caused by Braced Excavation in Clays, Comput. Geotechnics, Vol.63, pp.67-72.