All Issue

2024 Vol.57, Issue 11 Preview Page

Research Article

Establishment of dam sensor management criteria for abnormal pattern detection

이상패턴 감지를 위한 댐 계측기 관리기준 수립

Seungyub Leea
,
Young Hwan Choib
,
Doosun Kangc
,
Seong-Bae Jod
,
Jeong Yeul Lime
,
Do Guen Yoof*
이 승엽a
,
최 영환b
,
강 두선c
,
조 성배d
,
임 정열e
,
유 도근f*
aAssistant Professor, Department of Civil and Environmental Engineering, Hannam University, Daejeon, Korea
bAssociate Professor, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
cProfessor, Department of Civil Engineering, Kyung Hee University, Yongin, Korea
dPrincipal Researcher, Water Infrastructure Research Center, Kwater Research Institute, Daejeon, Korea
eGeneral Director, Water Infrastructure Research Center, Kwater Research Institute, Daejeon, Korea
fAssociate Professor, Department of Civil Engineering, The University of Suwon, Suwon, Korea
a한남대학교 토목환경공학과 조교수
b경상국립대학교 건설시스템공학과 부교수
c경희대학교 사회기반시스템공학과 교수
dKwater연구원 물인프라안전연구소 책임연구원
eKwater연구원 물인프라안전연구소 연구소장
f수원대학교 건설환경에너지공학부 부교수
*Corresponding Author
30 November 2024. pp. 921-933
PDF XML Citation
Abstract

Dams are essential infrastructure for supplying various types of water demands, and their maintenance is of paramount importance. However, as many dams continue to age, strengthening technical support and ensuring stability through research and development have become critical. Ensuring stability relies on monitoring the current state of dams; thus, various sensors are installed or embedded, and extensive research on predicting dam anomalies using these sensors is actively underway. However, most studies analyze data under the assumption that all sensors are functioning normally, without considering potential sensor malfunctions. Additionally, the absence of clear management criteria and definitions of normal patterns for each sensors makes it challenging to differentiate between abnormal dam behavior and sensor malfunctions. In this study, we propose new definitions of abnormal patterns for sensors and establish management criteria for each type of sensor. We identified abnormal patterns based on previous studies and defined general management criteria through statistical analysis of historical dam sensor data. The proposed criteria were applied to five dams in South Korea to assess sensor functionality. The abnormal pattern detection criteria presented in this study can be used as inspection standards for dam sensors and are expected to provide a foundation for more reliable dam management through continuous refinement and calibration with each inspection.

Keywords
Abnormal pattern
Displacement
Leakge, Turbidity
Dam management

댐은 각종 용수를 공급하는 주요 기반시설로 그 유지관리는 매우 중요한 일이다. 하지만, 대부분 댐들은 노후로 인해 이를 극복하기 위한 강화된 기술적 지원과 지속적인 연구 개발을 통한 안정성 확보가 중요해지고 있다. 안정성 확보는 결국 댐의 현재 상태에 대한 모니터링이 필수로 해당 목적에 따라 다양한 계측기가 매설 혹은 설치되어 있으며, 이를 활용한 댐의 이상거동 예측 연구도 활발히 진행되고 있다. 다만, 대부분의 연구에서는 계측기 이상 유무를 고려하지 않고 모든 데이터가 계측기가 정상적으로 가동되고 있다는 가정 하에 데이터를 활용한 분석이 수행되고 있다. 또한, 계측기에 대한 관리기준이 명확하지 않고 일부 계측 항목의 경우 정상 범위에 대한 정의가 없어, 데이터 분석 결과 댐의 이상 거동과 계측기의 불량 여부를 판단하기 어렵다. 이에 본 연구에서는 계측기 이상패턴을 새로이 정의하고 이에 대한 관리기준을 계측기 별로 제시하였다. 이상패턴 규명은 기존 연구 사례를 토대로 제시하였으며, 실제 댐 계측기 데이터를 활용한 통계분석을 통해 일반적인 관리기준을 정의하였다. 제시한 관리기준은 국내 5개 댐에 적용하여 계측기 이상 유무를 판단하는 예시를 제공하였다. 본 연구에서 제시한 이상패턴 감지 기준은 향후 댐 계측기에 대한 점검 기준으로 활용할 수 있으며, 점검마다 지속적인 보정을 통해 고도화하여 안정적인 댐 관리에 기반을 마련할 수 있을 것으로 기대된다.

키워드
이상패턴
변위계
누수량계
침투수탁도계
댐 관리
References
1

Amarbayasgalan, T., Pham, V.H., Theera-Umpon, N., and Ryu, K.H. (2020). "Unsupervised anomaly detection approach for time-series in multi-domains using deep reconstruction error." Symmetry, Vol. 12, No. 8, 1251.

10.3390/sym12081251
2

Boquet, G., Morell, A., and Serrano, J. (2020). "A variational autoencoder solution for road traffic forecasting systems: missing data imputation, dimension reduction, model selection and anomaly detection." Transportation Research Part C: Emerging Technologies, Vol. 115, 115.

10.1016/j.trc.2020.102622
3

Ergen, T., and Kozat, S.S. (2019). "Unsupervised anomaly detection with LSTM neural networks." IEEE Transactions on Neural Networks and Learning Systems,Vol. 31, No. 8, pp. 3127-3141.

10.1109/TNNLS.2019.293597531536024
4

Fisher, W.D., Camp, T.K., and Krzhizhanovskaya, V.V. (2017). "Anomaly detection in earth dam and levee passive seismic data using support vector machines and automatic feature selection." Journal of Computational Science, Vol. 20, pp. 143-153.

10.1016/j.jocs.2016.11.016
5

Hellgren, R., Malm, R., and Ansell, A. (2021). "Performance of data-based models for early detection of damage in concrete dams." Structure and Infrastructure Engineering, Vol. 17, No. 2, pp. 275-289.

10.1080/15732479.2020.1737146
6

Kang, G., Kim, D., Yoon, S., Jang, B.S., and Kim, J. (2020). "Assessing the stability of fill dams by relationship between water level and porewater pressure." Journal of the Korean Geotechnical Society, Vol. 36, No. 6, pp. 5-15.

7

Korean Geotechnical Society (KGS) (2010). Design, construction and safety management for the dam and embankment. Goomi Book.

8

Kwater (2019). A study on the combined analysis method of measurement data for dam safety and maintenance (II).

9

Kwater (2020). Research of advanced warning level of water infrastructure for early warning system improvement (Interim Report), 2021-WR-RR-23-89.

10

Kwater (2021). Research of advanced warning level of water infrastructure for early warning system improvement (Final Report), 2022-WR-RR-26-122.

11

Lee, J., Yoon, S., Im, E.S., and Kang, G. (2020). "A study on management criteria of seepage for fill dams considering rainfall effect." Journal of the Korean Geotechnical Society, Vol. 36, No. 5, pp. 5-16.

12

Lee, J.W. (2014). "Application of statistical method for establishment of alert level for dam instrumentation." KSCE 2014 Conference, pp. 283-284.

13

Li, L., Yan, J., Wang, H., and Jin, Y. (2020). "Anomaly detection of time series with smoothness-inducing sequential variational auto-encoder." IEEE Transactions on Neural Networks and Learning Systems, Vol. 99, pp. 1-15.

14

Park, H., Nah, B., and Lim, H. (2016). "Shear wave velocity profile considering uncertainty caused by spatial variation of material property in core zone of fill dam." Journal of Korean Geotechnical Society, Vol. 31, No. 11, pp. 51-60.

10.7843/kgs.2016.32.11.51
15

Park, H.C., Hwang, H.J., and Lee, J.W. (2012). "Development of new data analysis method to evaluate reliability of the sensor or measured data." Journal of the Korea Institute for Structural Maintenance and Inspection, Vol. 16, No. 6, pp. 34-44.

10.11112/jksmi.2012.16.6.034
16

Salazar, F., Conde, A., Irazabal, J., and Vicente, D.J. (2021). "Anomaly detection in dam behaviour with machine learning classification models." Water, Vol. 13, No. 17, 2387.

10.3390/w13172387
17

Shu, X., Bao, T., Xu, R., Li, Y., and Zhang, K. (2021). "Dam anomaly assessment based on sequential variational autoencoder and evidence theory." Applied Mathematical Modelling, Vol. 98, pp. 576-594.

10.1016/j.apm.2021.05.021
18

Wei, B., Yuan, D., Li, H., and Xu, Z. (2019). "Combination forecast model for concrete dam displacement considering residual correction." Structural Health Monitoring, Vol. 18, No. 1, pp. 232-244.

10.1177/1475921717748608
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 57
  • No :11
  • Pages :921-933
  • Received Date : 2024-10-11
  • Revised Date : 2024-11-01
  • Accepted Date : 2024-11-04
  • DOI :https://doi.org/10.3741/JKWRA.2024.57.11.921
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close