All Issue

2022 Vol.38, Issue 11 Preview Page
A Study on the Quality Control Method for Geotechnical Information Using AI

AI를 이용한 지반정보 품질관리 방안에 관한 연구

Ka-Hyun Park1
,
Jongkwan Kim1
,
Seokhyung Lee2
,
Min-Ki Kim3
,
Kyung-Ryoon Lee4
,
Jin-Tae Han5*
박 가현1
,
김 종관1
,
이 석형2
,
김 민기3
,
이 경륜4
,
한 진태5*
1Member, Senior Researcher, Geotechnical Engrg. Research Department, Korea Institute of Civil and Building Technology
2Member, Postdoctoral Researcher, Geotechnical Engrg. Research Department, Korea Institute of Civil and Building Technology
3CTO, Metalogos
4Director, Metalogos
5Member, Research Fellow, Geotechnical Engrg. Research Dept., Korea Institute of Civil and Building Technology
1정회원, 한국건설기술연구원 지반연구본부 수석연구원
2정회원, 한국건설기술연구원 지반연구본부 박사후연구원
3비회원, 메타로고스 주식회사 CTO
4비회원, 메타로고스 주식회사 이사
5정회원, 한국건설기술연구원 지반연구본부 연구위원
*Corresponding Author
30 November 2022. pp. 87-95
PDF XML Citation
Abstract

The geotechnical information constructed in the National Geotechnical Information DB System has been extensively used in design, construction, underground safety management, and disaster assessment. However, it is necessary to refine the geotechnical information because it has nearly 300,000 established cases containing a lot of missing or incorrect information. This research proposes a method for automatic quality control of geotechnical information using a fully connected neural network. Significantly, the anomalies in geotechnical information were detected using a database combining the standard penetration test results and strata information of Seoul. Consequently, the misclassification rate for the verification data is confirmed as 5.4%. Overall, the studied algorithm is expected to detect outliers of geotechnical information effectively.

Keywords
Artificial Intelligence (AI)
Deep learning
Geotechnical information
Neural Network (NN)
Quality Control (QC)
Standard Penetration Test (SPT)

국토지반정보 포털시스템이 구축된 지반정보는 최근 설계, 시공, 지하안전관리, 재해재난 평가 등 다양한 분야에서 활용되고 있다. 그러나 전국적으로 기 구축된 약 30여만공의 지반정보는 누락되거나 잘못된 정보를 다수 포함하고 있어 데이터 활용시 신뢰도를 확보하기가 어렵다. 따라서 분석 데이터의 신뢰도를 확보하기 위해서는 지반정보를 활용하기 전 단계에서 지반정보의 정제(품질관리)가 반드시 필요하다. 본 연구에서는 딥러닝 기법 중 하나인 인공신경망 기법을 활용하여 지반정보를 자동으로 품질관리 하는 방안에 대하여 제안하였다. 특히, 가장 일반적으로 사용되는 정보인 표준관입시험 결과와 지층정보를 이용하여 지반정보의 이상치를 탐지하였다. 서울시 지반정보 데이터를 이용하여 분석하였으며, 검증데이터에 대한 오분류 비율은 5.4%로 확인되었다. 신경망 모델에서 이상치 분류된 데이터만을 추후에 검사함으로써 효율적으로 이상치를 탐지할 수 있을 것으로 기대된다.

References
1
Biswas, S., Faysal, T. I., Promiti, A. Siddiqui, Hossain, M. S., Bazlul, L., Sarwar, A. M., Shaiban, S. Md., and Rahman, R. M. (2020), "Analysis of Soil and Various Geo-Technical Properties Using Data Mining Techniques", 2020 IEEE 10th International Conference on Intelligent Systems, pp.288-293. 10.1109/IS48319.2020.9199941
2
Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M.A., Senior, A., Tucker, P., Yang, K., and Ng., A. (2012), "Large Scale Distributed Deep Networks", Advances in neural information processing systems, 25.
3
Glorot, X. and Yoshua, B. (2010), "Understanding the Difficulty of Training Deep Feedforward Neural Networks", Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp.249-256.
4
Gülçehre, Ç. and Bengio, Y. (2016), "Knowledge Matters: Importance of Prior Information for Optimization", The Journal of Machine Learning Research, Vol.17, No.1, pp.226-257.
5
Jou, I. C., You, S. S., and Chang, L. W. (1994), "Analysis of Hidden Nodes for Multi-layer Perceptron Neural Networks", Pattern Recognition, Vol.27, No.6, pp.859-864. 10.1016/0031-3203(94)90170-8
6
Kim, H. S., Kim, H. K., Shin, S. Y., and Chung, C. K. (2011), "Application of Statistical Geo-Spatial Information Technology to Soil Stratification", Journal of Journal of the Korean Geotechnical Society, Vol.27, No.7, pp.59-68. 10.7843/kgs.2011.27.7.059
7
Kim, H. S., Kim, H. K., Shin, S. Y., and Chung, C. K. (2012), "Application of Statistical Geo-Spatial Information Technology to Soil Stratification in the Seoul Metropolitan Area", Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, Vol.6, No.4, pp.221-228. 10.1080/17499518.2012.744248
8
Kim, H. S., Chung, C. K., and Kim, H. K. (2016), "Geo-spatial Data Integration for Subsurface Stratification of Dam Site with Outlier Analyses", Environmental Earth Sciences, Vol.75, No.2, pp.1-10. 10.1007/s12665-015-4931-4
9
Kim, J. J., Kim, H. S., and Chung, C. K. (2014), "Determination of Optimum Outlier for Borehole Data in Offshore Dredging Area using Cross Validation", KSCE 2014 CONVENTION 2014 CIVIL EXPO & CONFERENCE, pp.569-570.
10
Kim, J., Park, N. S., Yun, S., Chae, S. H., and Yoon, S. (2018), "Application of Isolation Forest Technique for Outlier Detection in Water Quality Data", Journal of Korean Society of Environmental Engineers, Vol.40, No.12, pp.473-480. 10.4491/KSEE.2018.40.12.473
11
Knorr, E. M. and Ng, R. T. (1999), "Finding Intensional Knowledge of Distance-based Outliers", Proceedings of the 25th International Conference on Very Large Data Bases, 99, pp.211-222.
12
Lee, B. Y., Hwang, B. S., and Cho, W. J. (2017a), "Reliability Evaluation Methodology of Boring Investigation DB for the 3D Integrated Underground Space Map", Journal of the Korean Geotechnical Society, Vol.33, No.9, pp.35-47. 8.
13
Lee, B. Y., Hwang, B. S., and Cho, W. J. (2017b), "Precision Analysis of Geotechnical Information for the 3D Integrated Underground Space Map", Journal of the Korean Geo-Environmental Society, Vol.18, No.4, pp.5-8.
14
Lee, B. Y., Hwang, B. S., Kim, H.S., and Cho, W. J. (2018), "Precision Improvement Methodology of Geotechnical Information through Outlier Analysis", Journal of the Korean Geo-Environmental Society, Vol.19, No.2, pp.23-35.
15
Liu, J. and Zou, T. (2022), "Identifying the Outlier in Tunnel Monitoring Data: An Integration Model", Computer Communications, 188, pp.145-155. 10.1016/j.comcom.2022.03.002
16
Murino, V. (1998), "Structured Neural Networks for Pattern Recognition", IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), Vol.28, No.4, pp.553-561. 10.1109/3477.70429418255974
17
National Disaster Management Research Institute (2021), "Development of Quality Control System of Geo-information and Construction of Liquefaction Hazard Map".
18
Park, K.H., Han, J.T., and Yoon, Y.N. (2021a), "A Study on the Automatic Digital DB of Boring Log Using AI", Journal of the Korean Geotechnical Society, Vol.37, No.11, pp.119-129.
19
Park, K.H., Han, J.T., and Kim, J.K. (2021b), "Automated Quality Control Method for Geotechnical Information using Autoencoder", Proceedings of 2021 Fall Korean Geotechnical Society Conference, pp.261-262.
20
Park, S. and Ha, J.H. (2021), "Development of Computational Algorithms for Daily Water Leak Detection in District Metered Areas Based on the Principal Component Analysis", Desalination and Water Treatment 227, pp.93-103. 10.5004/dwt.2021.27354
21
Raiko, T., Valpola, H., and LeCun, Y. (2012), "Deep Learning Made Easier by Linear Transformations in Perceptrons", Artificial intelligence and statistics, pp.924-932
22
Shao, C., Zheng, S., Gu, C., Hu, Y., and Qin, X. (2022), "A Novel Outlier Detection Method for Monitoring Data in Dam Engineering", Expert Systems with Applications, 193, 116476. 10.1016/j.eswa.2021.116476
Information
  • Publisher :The Korean Geotechnical Society
  • Publisher(Ko) :한국지반공학회
  • Journal Title :Journal of the Korean Geotechnical Society
  • Journal Title(Ko) :한국지반공학회 논문집
  • Volume : 38
  • No :11
  • Pages :87-95
  • Received Date : 2022-10-24
  • Revised Date : 2022-11-07
  • Accepted Date : 2022-11-07
  • DOI :https://doi.org/10.7843/kgs.2022.38.11.87
Journal Informaiton Journal of the Korean Geotechnical Society Journal of the Korean Geotechnical Society
Archives
: Vol.23~28 (2007~2012)
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close