All Issue

2023 Vol.33, Issue 4 Preview Page

Research Article

Analysis of the Impact on Prediction Models Based on Data Scaling and Data Splitting Methods - For Retaining Walls with Ground Anchors Installed

데이터 스케일링과 분할 방식에 따른 예측모델의 영향 분석 - 그라운드 앵커가 설치된 흙막이 벽체 대상

Jun Woo Shin1
,
Heui Soo Han2*
신 준우1
,
한 희수2*
1Ph.D. Student, Department of Civil Engineering, Kumoh National Institute of Technology
2Professor, Department of Civil Engineering, Kumoh National Institute of Technology
1국립금오공과대학교 토목공학과 박사과정
2국립금오공과대학교 토목공학과 교수
*Corresponding Author
31 December 2023. pp. 639-655
PDF XML Citation
Abstract

Recently, there has been a growing demand for underground space, leading to the utilization of earth retaining walls for deep excavations. Earth retaining walls are structures that are susceptible to displacement, and their measurement and management are carried out in accordance with the standards established by the Ministry of Land, Infrastructure, and Transport. However, managing displacement through measurement can be considered similar to post-processing. Therefore, in this study, we not only predicted the horizontal displacement of a retaining wall with ground anchors installed using machine learning, but also analyzed the impact of the prediction model based on data scaling and data splitting methods while learning measurement data using machine learning. Custom splitting was the most suitable method for learning and outputting measurement data. Data scaling demonstrated excellent performance, with an error within 1 and an R-squared value of 0.77 when the anchor tensile force and water pressure were standardized. Additionally, it predicted a negative displacement compared to a model that without scaling.

Keywords
SVR
displacement predicting
machine learning
retaining wall
data scaling
data splitting

최근 지하공간에 대한 수요가 많아지면서 대심도 굴착으로 흙막이 벽체가 활용되고 있다. 흙막이 벽체는 변위에 취약한 구조물로써 국토교통부에서 제시한 관리기준으로 계측관리를 수행하고 있으나 계측관리를 통한 대비는 후처리에 가깝다고 할 수 있다. 따라서 본 연구에서는 머신러닝을 이용한 그라운드 앵커가 설치된 흙막이 벽체의 수평변위 예측뿐만 아니라 머신러닝으로 계측데이터를 학습하는 과정에서 데이터 스케일링과 분할 방법에 따른 예측모델의 영향을 분석하였다. 이 연구의 분석결과에 따르면 사용자 지정분할방법이 적합하지 않은 경우도 있었으나 일정 조건하에서 데이터 학습 및 출력에 가장 우수한 성능을 나타냈다. 데이터 스케일링은 앵커의 인장력, 수압을 표준화하였을 때 오차 1 이내, R- Squared 값이 0.77로 우수한 성능을 나타냈으며 스케일링을 적용하지 않은 모델 대비 음의 변위를 예측하는 결과를 보였다.

키워드
SVR
변위 예측
머신러닝
흙막이 벽체
데이터 스케일링
데이터 분할
References
1
An, J.S., Kang, K.N., Kim, S.H., Song, K.I., 2019, Analysis for applicability of differential evolution algorithm to geotechnical engineering field, Journal of the Korean Geotechnical Society, 35(4), 27-35 (in Korean with English abstract). 10.7843/kgs.2019.35.4.27
2
Ann, S.Y., Jung, G.S., Choi, H.S., Choi, E.J., 2014, A study on the development for the programmable numerical formular using the horizontal displacements by the inclinometer, Proceedings of the 2014 Fall Geosynthetics Conference, Jeonju, 29-32 (in Korean with English abstract).
3
Chung, J.S., Shin, Y.W., Kim, M.H., Kook, Y.M., Jeong, K.Y., Kim, P.S., Lee, S.H., 2018, A study on the displacement behavior according to the analysis model of ground excavation, Journal of the Korean Geo-Environmental Society, 19(4), 27-32 (in Korean with English abstract). 10.14481/jkges.2018.19.4.27
4
Goh, A.T.C., Zhang, F., Zhang, W., Zhang, Y., Liu, H., 2017, A simple estimation model for 3D braced excavation wall deflection, Computers and Geotechnics, 83(2017), 106-113. 10.1016/j.compgeo.2016.10.022
5
Goldberg, D.T., Jaworski, W.E., Gordon, M.D., 1976, Lateral support systems and underpinning, Report No. FHWA-RD-75-128 (PB-257210), Federal Highway Administration, Washington DC, 51-87.
6
Ji, Z., Wang, B., Deng, S., You, Z., 2014, Predicting dynamic deformation of retaining structure by LSSVR-based time series method, Neurocomputing, 137, 165-172. 10.1016/j.neucom.2013.03.073
7
Kim, H.T., Park, S.W., Kwon, Y.H., Kim, J.H., 2000, Development of a system predicting maximum displacements of earth retaining walls at various excavation stages using artificial neural network, Journal of the Korean Geotechnical Society, 16(1), 83-97 (in Korean with English abstract).
8
Kim, T.S., Jung, Y.H., 2020, Evaluation of soil stiffness and excavation support wall deformation at deep excavation site using inverse analysis, Journal of the Korean Geo-Environmental Society, 12(12), 5-10 (in Korean with English abstract). 10.14481/jkges.2020.21.12.5
9
Lambe, T.W., Wolfskill, L.A., Wong, I.H., 1970, Measured performance of braced excavation, Journal of the Soil Mechanics and Foundations Division, 96(3), 817-836. 10.1061/JSFEAQ.0001421
10
Lee, D.G., Kang, K.N., Song, K.I., 2022, Multi-layered ground back analysis of retaining wall using differential evolution algorithm : Basic research of digital twin, Journal of the Korean Geo-Environmental Society, 23(1), 25-30 (in Korean with English abstract). 10.14481/jkges.2022.23.1.25
11
Lee, D.G., Yu, J.Y., Choi, J.Y., Song, K.I., 2023, Development of stability evaluation algorithm for C.I.P. retaining walls during excavation, Journal of the Korean Geotechnical Society, 39(9), 13-24 (in Korean with English abstract). 10.7843/kgs.2023.39.9.13
12
Liu, D., Lin, P., Zhao, C., Qiu, J., 2021, Mapping horizontal displacement of soil nail walls using machine learning approaches, Acta Geotechnical, 16(12), 4027-4044. 10.1007/s11440-021-01345-z
13
Moormann, C., 2004, Analysis of wall and ground movements due to deep excavations in soft soil based on a new worldwide database, Soil and Foundations, 44(1), 87-98. 10.3208/sandf.44.87
14
O'Rourke, T.D., 1976, The ground movements related to braced excavation and their influence on adjacent buildings, Report No. DOT-TST 76T-23, US Department of Transportation, 7-46.
15
O'Rourke, T.D., 1981, Ground movements caused by braced excavations, Journal of the Geotechnical Engineering Division, 107(9), 1159-1178. 10.1061/AJGEB6.0001183
16
Park, C.S., Joung, S.M., 2020, An analytical study on the horizontal displacement and excavation width of H-pile earth retaining wall, Proceedings of the KSCE 2020 Convention, Seogwipo, 1177-1178 (in Korean with English abstract).
17
Park, C.S., Park, D.W., Lee, Y.K., 2009, A study on the displacement analysis of earth retaining wall, Proceedings of the Civil Expo 2009, Hoengseong, 2059-2062 (in Korean with English abstract).
18
Park, D.H., Song, S.M., Park, K.C., Ahn, C.Y., 2016, Numerical simulation of braced excavation using nonlinear constitutive model, Proceedings of the KSCE 2016 Convention, Seogwipo, 270-271 (in Korean with English abstract).
19
Peck, B.B., 1969, Deep excavations and tunneling in soft ground, State of the Art Report, Proceedings of the 7th International Conference on Soil Mechanics and Foundation Engineering, Mexico, 4, 225-290.
20
Seo, S.H., Chung, M.K., 2022, Engineering application of artificial intelligence to predict displacement of retaining walls in excavation sites, Proceedings of the KSCE 2022 Convention, Busan, 7-8 (in Korean with English abstract).
21
Seo, S.H., Chung, M.K., 2023, Development of an ensemble prediction model for lateral deformation of retaining wall under construction, Journal of the Korean Geotechnical Society, 39(4), 5-17 (in Korean with English abstract). 10.7843/kgs.2023.39.4.5
22
Song, J.H., 2023, Prediction of anchored retention wall horizontal displacement using SVM, MSc Thesis, Kumoh National Institute of Technology, 19-27 (in Korean with English abstract).
23
Yoo, C.S., Yang, J.W., 2020, A study on development of artificial neural network (ANN) for preliminary design of urban deep Excavation and tunnelling, Journal of the Korean Geosynthetics Society, 19(1), 11-23 (in Korean with English abstract). 10.12814/jkgss.2020.19.1.011
24
Yun, Y.M., 2019, Development of site management system for temporary facility construction using back analysis, Journal of the Society of Disaster Information, 15(4), 570-577 (in Korean with English abstract). 10.15683/kosdi.2019.12.31.570
Information
  • Publisher :Korean Society of Engineering Geology
  • Publisher(Ko) :대한지질공학회
  • Journal Title :The Journal of Engineering Geology
  • Journal Title(Ko) :지질공학
  • Volume : 33
  • No :4
  • Pages :639-655
  • Received Date : 2023-11-08
  • Revised Date : 2023-12-19
  • Accepted Date : 2023-12-19
  • DOI :https://doi.org/10.9720/kseg.2023.4.639
Journal Informaiton The Journal of Engineering Geology The Journal of Engineering Geology
Online Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close