Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Determination of a priority for leakage restoration considering the scale of damage in for water distribution systems

피해규모를 고려한 용수공급시스템 누수복구 우선순위 선정

  • Kim, Ryul (Department of Civil and Infrastructure Engineering, Gyeongsang National University) ;
  • Kwon, Hui Geun (Department of Civil and Infrastructure Engineering, Gyeongsang National University) ;
  • Choi, Young Hwan (Department of Civil and Infrastructure Engineering, Gyeongsang National University)
  • 김률 (경상국립대학교 건설시스템공학과) ;
  • 권희근 (경상국립대학교 건설시스템공학과) ;
  • 최영환 (경상국립대학교 건설시스템공학과)
  • Received : 2023.09.13
  • Accepted : 2023.10.10
  • Published : 2023.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Leakage is one of the representative abnormal conditions in Water distribution systems (WDSs). Leakage can potentially occur and cause immediate economic and hydraulic damage upon occurrence. Therefore, leakage detection is essential, but WDSs are located underground, it is difficult. Moreover, when multiple leakage occurs, it is required to prioritize restoration according to the scale and location of the leakage, applying for an optimal restoration framework can be advantageous in terms of system resilience. In this study, various leakage scenarios were generated based on the WDSs hydraulic model, and leakage detection was carried out containing location and scale using a Deep learning-based model. Finally, the leakage location and scale obtained from the detection results were used as a factor for the priority of leakage restoration, and the results of the priority of leakage restoration were derived. The priority of leakage restoration considered not only hydraulic factors but also socio-economic factors (e.g., leakage scale, important facilities).

누수는 용수공급시스템 내에서 발생할 수 있는 대표적인 비정상상황 중 하나이다. 누수는 관로가 매설된 이후부터 잠재적으로 발생할 수 있으며 발생 직후부터 즉시 경제적 및 수리학적 피해를 입을 수 있기 때문에 이를 적시에 감지하고 탐지하는 것이 중요하다. 하지만 시스템이 지하에 매설되어 있어 이를 빠르게 인지하는 것은 쉽지 않으며 인지한다 하여도 복구하기 위해서는 상대적으로 많은 가용자산이 요구된다. 따라서 다중 누수가 발생할 시 누수규모 및 위치에 따라 복구 우선순위에 대한 우선순위를 선정해야 할 필요성이 있으며 최적의 복구전략이 도출되어 이를 수행할 시 시스템의 탄력성 측면에 있어 유리함을 가질 수 있다. 본 연구에서는 프로그램 기반 모의 누수를 발생시켜 비정상상황 시나리오를 구축하였으며 이에 따라 딥러닝 기반 모델로 누수탐사를 수행하였다. 탐사 결과로 얻어지는 누수위치와 누수량은 이 후 누수복구 우선순위를 위한 요소로써 활용되며 타 요소와 함께 최적의 누수복구 시나리오를 도출하였다.

Keywords

Acknowledgement

본 결과물은 환경부의 재원으로 한국환경산업기술원의 가뭄대응 물관리 혁신기술개발사업의 지원을 받아 연구되었습니다(RS-2023-0023194).

References

  1. American Water Works Association (AWWA ) (2008). Water audits and loss control programs. Washington, DC.
  2. Balut, A., Brodziak, R., Bylka, J., and Zakrzewski, P. (2018). "Battle of post-disaster response and restauration (BPDRR)." 1st International WDSA/CCWI 2018 Joint Conference, Kingston, Ontario, Canada.
  3. Basnet, L., Brill, D., Ranjithan, R., and Mahinthakumar, K. (2023). "Supervised machine learning approaches for leak localization in water distribution systems: Impact of complexities of leak characteristics." Journal of Water Resources Planning and Management, Vol. 149, No. 8, 04023032.
  4. Choi, J., Jeong, G., and Kang, D. (2021). "Multiple leak detection in water distribution networks following seismic damage." Sustainability, Vol. 13, No. 15, 8306.
  5. Choi, Y.H., Jung, D., Jun, H., and Kim, J.H. (2018). "Improving water distribution systems robustness through optimal valve installation." Water, Vol. 10, No. 9, 1223.
  6. Daniel, I., Pesantez, J., Letzgus, S., Khaksar Fasaee, M.A., Alghamdi, F., Berglund, E., Mahinthakumar, G., and Cominola, A. (2022). "A sequential pressure-based algorithm for data-driven leakage identification and model-based localization in water distribution networks." Journal of Water Resources Planning and Management, Vol. 148, No.6, 04022025.
  7. Deb, K., Agrawal, S., Pratap, A., and Meyarivan, T. (2000). "A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA II." Proceedings of the International Conference on Parallel Problem Solving From Nature, Springer, Paris, France, pp. 849-858.
  8. Jun, S., and Lansey, K.E. (2023). "Convolutional neural network for burst detection in smart water distribution systems." Water Resources Management, Vol. 1, No. 15, pp. 3729-3743. https://doi.org/10.1007/s11269-023-03524-x
  9. 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.
  10. Lambert, A. (1994). "Accounting for losses: The Bursa and background concept (BABE)." Water and Environment Journal, Vol. 8, No. 2, pp. 205-214. https://doi.org/10.1111/j.1747-6593.1994.tb00913.x
  11. LeCun, Y., Bottou, L., Orr, G.B., and Muller, K.R. (2002). Efficient backprop. In Neural networks: Tricks of the trade. Springer Berlin Heidelberg, Berlin, Heidelberg, Germany, pp. 9-50.
  12. Marvin, G., Grbcic, L., Druzeta, S., and Kranjcevic, L. (2023). "Water distribution network leak localization with histogram-based gradient boosting." Journal of Hydroinformatics, Vol. 25, No. 3, pp. 663-684. https://doi.org/10.2166/hydro.2023.102
  13. Romero-Ben, L., Alves, D., Blesa, J., Cembrano, G., Puig, V., and Duviella, E. (2023). "Leak detection and localization in water distribution networks: review and perspective." Annual Reviews in Control, Vol. 55, pp. 392-419. https://doi.org/10.1016/j.arcontrol.2023.03.012
  14. Rossman, L., Woo, H., Tryby, M., Shang, F., Janke, R., and Haxton, T. (2020). EPANET 2.2 user manual. U.S. Environmental Protection Agency, Cincinnati, OH, U.S.
  15. Sophocleous, S., and Nikoloudi, E. (2018). "Simulation-based framework for the restoration of earthquake-damaged water distribution networks using a genetic algorithm: (118)." 1st International WDSA/CCWI 2018 Joint Conference, Kingston, Ontario, Canada.
  16. Tornyeviadzi, H.M., and Seidu, R. (2023). "Leakage detection in water distribution networks via 1D CNN deep autoencoder for multivariate SCADA data." Engineering Applications of Artificial Intelligence, Vol. 122, 106062.
  17. Tyagi, V., Pandey, P., Jain, S., and Ramachandran, P. (2023). "A two-stage model for data-driven leakage detection and localization in water distribution networks." Water, Vol. 15, No. 15, 2710.
  18. Walski, T.M., Brill Jr, E.D., Gessler, J., Goulter, I.C., Jeppson, R.M., Lansey, K., Lee, H.L., Liebman, J.C., Mays, L., Morgan, D.R., and Ormsbee, L. (1987). "Battle of the network models: Epilogue." Journal of water resources Planning and Management, Vol. 113, No. 2, pp. 191-203. https://doi.org/10.1061/(ASCE)0733-9496(1987)113:2(191)
  19. Wan, X., Farmani, R., and Keedwell, E. (2023). "Real-time gradual leakage detection system for water distribution networks based on MIMO-ANN." EGU General Assembly 2023, Vienna, Austria & Online.
  20. Yoo, D.G., Kang, D., Jun, H., and Kim, J.H. (2014). "Rehabilitation priority determination of water pipes based on hydraulic importance." Water, Vol. 6, No. 12, pp. 3864-3887. https://doi.org/10.3390/w6123864
  21. Zanfei, A., Menapace, A., Brentan, B.M., Righetti, M., and Herrera, M. (2022). "Novel approach for burst detection in water distribution systems based on graph neural networks." Sustainable Cities and Society, Vol. 86, 104090.