All Issue

2023 Vol.56, Issue 5 Preview Page

Research Article

Evaluation of leakage detection performance according to leakage scenarios of water distribution systems based on deep neural networks

DNN기반 상수도시스템 누수시나리오에 따른 누수탐지성능 평가

Ryul Kima
,
Young Hwan Choib*
김 률a
,
최 영환b*
aMaster Student, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
bAssistant Professor, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
a경상국립대학교 건설시스템공학과 석사과정
b경상국립대학교 건설시스템공학과 조교수
*Corresponding Author
31 May 2023. pp. 347-356
PDF XML Citation
Abstract

In Water Distribution Systems (WDSs), can abnormal hydraulic and water quality conditions such as red-water phenomenon and leakage occur. To restore them, data is generated through various meters data to predict and detect. However, in the case of leakage if difficult to detect unless direct exploration is performed. Among them, unreported leakage, are not seen visually and account for the most considerable volumes of leakage, which leads to economic loss. Bur direct exploration is limited through on site conditions such as securing professional manpower. In this paper, leakage volumes and location were randomly generated for the WDS, which was assumed to be calibrated, and it was detected through a deep learning model. For abnormal data generation, the leakage was simulated using the emitter coefficient, and leakage detection was successfully performed through the generated abnormal data and normal data.

Keywords
Water distribution system (WDS)
Leakage scenarios
Leakage detection performance
Deep neural network
Hydraulic analysis model

상수도시스템에서는 적수 및 누수와 같은 다양한 수리 및 수질적 비정상상황이 발생한다. 이를 방지하거나 빠르게 복구하기 위하여 다양한 계측기에서 얻어지는 데이터를 통해 사고를 예상하고 탐지한다. 하지만 대표적인 수리학적 비정상상황인 누수의 경우 직접적인 탐사를 수행하지 않는다면 발견되기 어렵다. 그 중 미신고 파열누수의 경우 육안식별이 어렵기 때문에 가장 많은 누수를 차지하게 되며 이는 곧 큰 경제적 손실로 이어진다. 직접적인 탐사의 경우 전문인력 확보 등 현장의 여건 등 여러 한계점이 존재한다. 이를 해결하기 위해 본 연구에서는 검보정이 완료된 상수도관망 수리모형(EPANET)의 수리해석결과 데이터를 학습데이터로 사용하고 Deep neural network 알고리즘을 활용하여 누수규모 및 누수위치에 대한 누수탐사를 수행하였다. 누수탐사 수행을 위해 모의 누수 사고데이터를 생성하였으며 누수규모, 위치 등 다양한 시나리오를 고려하였다. 또한, 최적의 누수 탐지 성능을 위해 관망의 크기, 계측기의 종류, 개수, 위치에 따른 탐지성능을 분석하였다.

키워드
상수도시스템
누수시나리오 생성
누수탐사성능 평가
Deep neural network
수리해석모형
References
1
Glorot, X., and Bengio, Y. (2010). "Understanding the difficulty of training deep feedforward neural networks." In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Whistler, Canada, pp. 249-256.
2
Gupta, R. and Bhave, P.R. (1996). "Comparison of methods for predicting deficient-network performance." Journal of Water Resources Planning and Management, ASCE, Vol. 122, No. 3, pp. 214-217. 10.1061/(ASCE)0733-9496(1996)122:3(214)
3
Ha, J.H., Park, S.W., Mun, C.J., and An, J.H. (2019). "Development of principal component analysis outlier detection algorithm for detecting leak in water pipe networks." Journal of Civil Engineering Conference, pp. 226-227.
4
Hagos, M., Jung, D., and Lansey, K.E. (2016). "Optimal meter placement for pipe burst detection in water distribution systems." Journal of Hydroinformatics, No. 18, Vol. 4, pp. 741-756. 10.2166/hydro.2016.170
5
Jun, S.H., and Choi, Y.H. (2022). "Data generation approaches to detect abnormal conditions in water distribution systems." Journal of The Korean Society of Hazard Mitigation, Vol. 22, No. 2, pp.69-79. 10.9798/KOSHAM.2022.22.2.69
6
Jung, D., and Lansey, K. (2015). "Water distribution system burst detection using a Nonlinear Kalman filter." Journal of Water Resources Planning and Management, Vol. 141, No. 5, 04014070. 10.1061/(ASCE)WR.1943-5452.0000464
7
Kingma, D.P., and Ba, J. (2015). "Adam: A method for stochastic optimization." Proceedings 3rd International Conference on Learning Representations. ICLR 2015, San Diego, CA, U.S.
8
K-water (2009). Water facilities construction cost estimation report.
9
LeCun, Y., Bottou, L., Orr, G.B., and Müller, K.R. (2002). Efficient backprop. In Neural networks: Tricks of the trade. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 9-50. 10.1007/3-540-49430-8_2
10
Lee, C.W., and Yoo, D.G. (2021). "Development of leakage detection model in water distribution networks applying LSTM-based deep learning algorithm." Journal of Korea Water Resources Association, Vol .54, No. 8, pp. 599-606. 10.3741/JKWRA.2021.54.8.599
11
Lee, Y.S., and Yoon, D.J. (2004). "Pinpointing of leakage location using pipe-fluid coupled vibration." Transactions of the Korean Society for Noise and Vibration Engineering, Vol. 14, No. 2, pp. 95-104. 10.5050/KSNVN.2004.14.2.095
12
Min, K.W., Kim, T., Lee, S., Choi, Y.H., and Kim, J.H. (2022). "Detecting and localizing leakages in water distribution systems using a two-phase model." Journal of Water Resources Planning and Management, Vol. 148, No. 10, 04022051. 10.1061/(ASCE)WR.1943-5452.0001599
13
Park, S.B., Kim, K., Seo, J., Kim, J., and Koo, J. (2018). "The leak signal characteristics and estimation of the leak location on water pipeline." Journal of Korean Society of Water and Wastewater, Vol. 32, No. 5, pp. 461-470. 10.11001/jksww.2018.32.5.461
14
Rossman, L.A. (2000). EPANET 2 users manual. United States Environmental Protection Agency, Cincinnati, OH, U.S.
15
Santos-Ruiz, I., Blesa, J., Puig, V., and López-Estrada, F.R. (2020). "Leak localization in water distribution networks using classifiers with cosenoidal features." IFAC-PapersOnLine, Vol. 53, No. 2, pp. 16697-16702. 10.1016/j.ifacol.2020.12.1113
16
Schmidhuber, J. (2015). "Deep learning in neural networks: An overview." Neural Networks, Vol. 61, pp. 85-117. 10.1016/j.neunet.2014.09.00325462637
17
Steffelbauer, D.B., Deuerlein, J., Gilbert, D., Abraham, E., and Piller, O. (2022). "Pressure-leak duality for leak detection and localization in water distribution systems." Journal of Water Resources Planning and Management, Vol. 148, No. 3, 04021106. 10.1061/(ASCE)WR.1943-5452.0001515
18
Tanyimboh, T.T., and Tabesh, M. (1997). "Discussion comparison of methods for predicting deficient-network performance." Journal of Water Resources Planning and Management, ASCE, Vol. 123, No. 6, pp. 369-370. 10.1061/(ASCE)0733-9496(1997)123:6(369)
19
Wagner, J.M., Shamir, U., and Marks, D.H. (1988). "Water distribution reliability: Simulation methods." Journal of Water Resources Planning and Management, Vol. 114, No. 3, pp. 276-294. 10.1061/(ASCE)0733-9496(1988)114:3(276)
20
Yoo, D.G., Yoon, J.S., Lee, H.M., Kang, D., and Kim, J.H. (2014). "Development and application of leakage detection model for water distribution networks considering uncertainty analysis." Journal of the Korean Society of Hazard Mitigation, Vol. 14, No. 3, pp. 177-186. 10.9798/KOSHAM.2014.14.3.177
21
Yoon, J.S., Yoo, D.G., Lee, H.M., and Kim, J.H. (2012). "Optimal leakage detection model of water distribution systems using semi-pressure driven analysis and harmony search." Journal of The Korean Society of Hazard Mitigation, Vol. 12, No. 3, pp. 23-32.
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 56
  • No :5
  • Pages :347-356
  • Received Date : 2023-02-20
  • Revised Date : 2023-04-27
  • Accepted Date : 2023-04-29
  • DOI :https://doi.org/10.3741/JKWRA.2023.56.5.347
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