Journal of Korean Society of Environmental Engineers (대한환경공학회지)

Korean Society of Environmental Engineers (대한환경공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Turbidity Estimation Model Using Data Mining Techniques in the Water Supply System

데이터마이닝 기법을 이용한 상수도 시스템 내의 탁도 예측모형 개발에 관한 연구

  • Park, No-Suk (Department of Civil Engineering and Engineering Research Institute, Gyeongsang National University) ;
  • Kim, Soonho (Department of Civil Engineering and Engineering Research Institute, Gyeongsang National University) ;
  • Lee, Young Joo (K-water Institute) ;
  • Yoon, Sukmin (Department of Civil Engineering and Engineering Research Institute, Gyeongsang National University)
  • 박노석 (경상대학교 토목공학과 및 공학연구원) ;
  • 김순호 (경상대학교 토목공학과 및 공학연구원) ;
  • 이영주 (K-water 연구원) ;
  • 윤석민 (경상대학교 토목공학과 및 공학연구원)
  • Received : 2016.01.27
  • Accepted : 2016.02.23
  • Published : 2016.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

Turbidity is a key indicator to the user that the 'Discolored Water' phenomenon known to be caused by corrosion of the pipeline in the water supply system. 'Discolored Water' is defined as a state with a turbidity of the degree to which the user visually be able to recognize water. Therefore, this study used data mining techniques in order to estimate turbidity changes in water supply system. Decision tree analysis was applied in data mining techniques to develop estimation models for turbidity changes in the water supply system. The pH and residual chlorine dataset was used as variables of the turbidity estimation model. As a result, the case of applying both variables(pH and residual chlorine) were shown more reasonable estimation results than models only using each variable. However, the estimation model developed in this study were shown to have underestimated predictions for the peak observed values. To overcome this disadvantage, a high-pass filter method was introduced as a pretreatment of estimation model. Modified model using high-pass filter method showed more exactly predictions for the peak observed values as well as improved prediction performance than the conventional model.

탁도는 송 배수 관로의 부식 등에 의해 발생되는 것으로 알려진 'Discolored Water'현상을 수용가의 물 사용자가 인지할 수 있는 주요 지표로서 활용되고 있다. 즉, 'Discolored Water'는 수돗물 사용자가 육안으로 인지할 수 있는 정도의 탁도를 가진 상태로 정의할 수 있으며, 사용자는 수돗물에 존재하는 불특정의 용존 물질보다는 미세한 입자들에 대한 시각적인 인지인 탁도를 통해서 'Discolored Water'를 인식하게 된다. 이에 본 연구에서는 실제 국내 상수도 시스템 내에서 관측된 다항목의 수질데이터(탁도, pH 및 잔류염소)를 대상으로 하여 탁도 이외의 수질데이터들을 예측모형의 설명변수로 설정한 후 데이터 마이닝 기법(data mining)을 통해 기계학습(machine learning)을 수행하여, 상수도 시스템 내에서의 탁도 변화를 예측하는 모형을 수립하고자 하였다. 수집된 수질 데이터를 대상으로 데이터 마이닝 기법인 Decision Tree를 이용해 탁도 예측모형을 구축한 결과 pH 및 잔류염소를 설명변수로 적용한 모형이 가장 높은 예측결과를 나타내었다. 하지만 예측모형들은 peak 관측치에 대해서는 예측오차가 다소 증가하였는데 이를 보완하기 위해 고주파통과필터를 이용한 전처리 과정을 적용하였다. 그 결과 탁도 데이터의 시계열변화 및 peak 관측치에 대한 예측오차가 감소하는 것으로 나타났다.

Keywords

References

  1. Hong, J., Mun, H., Yun, H., Yu, C. and Kang, B., "Sensitivity Analysis of Real-time Water Quality Index added Turbidity" Proceedings of the 2015 spring conference of KSWW and KSWQ, pp. 521-522(2015).
  2. Shin, J., Jeong, S. and Hwang, S., "Long-term variation of water turbidity in a Korean river ecosystem (Youngsan River)" Proceedings of the 2005 spring conference of KSWW and KSWQ, pp. 711-714(2005).
  3. Wetzel, R. G., Limnology: Lake and River Ecosystems, 3rd ed., Academic Press, California(2001).
  4. Vreeburg, J. H. G., Discolouration in drinking water systems : the role of particles clarified, IWA Publishing(2010).
  5. REWAB, "Registration system yearly analysis results of Dutch water companies, available through ministry of VROM (Netherlands Ministry of Housing, Spatial Planning and the Environment,"(Eds), Den Haag, The Netherlands
  6. Ellison, D., Investigation of Pipe Cleaning Methods, AWWARF, Denver(2003).
  7. Prince, R., Goulter, I. and Ryan, G., "Relationship Between Velocity Profiles And Turbidity Problems In Distribution Systems," World Water and Environmental Resources Congress, pp. 1-9(2001).
  8. Slaats, N., Rosenthal, L. P. M., Siegers, W. G., Boomen, M. V. d., Beuken, R. H. S. and Vreeburg, J. H. G. Processes involved in the generation of discolored water, American Water Works Association Research Foundation / Kiwa, The Netherlands(2002).
  9. Boxall, J. B., Skipworth, P. J. and Saul, A. J., "Aggressive flushing for discolouration event mitigation in water distribution networks," Water Sci. Technol. Water Supply, 3(1-2), 179-186(2003). https://doi.org/10.2166/ws.2003.0101
  10. Clement, J. A., Hayes, M., Kriven, W. M., Sarin, P., Bebee, J., Jim, K., Beckett, M., Snoeyink, V. L., Kirmeyer, G. J. and Pierson, G., Development of red water control strategies, American Water Works Association Research Foundation, Denver(2002).
  11. Kirmeyer, G. J., Friedman, M., Clement, J., Sandvig, A., Noran, P. F., Martel, K. D., Smith, D., LeChevallier, M., Volk, C., Antoun, E., Hiltebrand, D., Dyksen, J. and Cushing, R., Guidance manual for maintaining distribution system water quality, AWWA Research Foundation and American Water Works Association, Denver(2000).
  12. Lee, D., Kwan, B. and Ryu, S., "Filtration Performance Evaluation by Monitoring the Filtered Water Turbidity in Water Treatment Plant," Proceedings of the 2000 autumn conference of KSWW and KSWQ, pp. 115-118(2000).
  13. U.S. EPA, Water Sentinel System Architecture Draft, Version 1.0(2005).
  14. Janke, R., Murray, R. Uber, J. and Taxon, T., "Comparison of Physical Sampling and Real-Time Monitoring Strategies for Designing a Contamination Warning System in a Drinking Water Distribution System," J. Water Resour. Plann. and Manage., 132(4), 310-313(2006). https://doi.org/10.1061/(ASCE)0733-9496(2006)132:4(310)
  15. U.S. EPAa, Water Security Initiative: System Evaluation of the Cincinnati Contamination Warning System Pilot, U.S EPA Water Security Division(2014).
  16. U.S. EPAb, Water Security Initiative: Evaluation of the Water Quality Monitoring Component of the Cincinnati Contamination Warning System Pilot, U.S EPA Water Security Division(2014).
  17. Park, N. S., Lee, Y., Chae, S. and Yoon, S., "A Study on the Statistical Predictability of Drinking Water Qualities for Contamination Warning System," J. Korean Soc. Water and Wastewater, 29(4), 469-479(2015). https://doi.org/10.11001/jksww.2015.29.4.469
  18. Park, N. S., Park, S., Kim, S. and Jeong, N., "Establishment of the Refined Model for Prediction of Flocculation/Sedimentation Efficiency Using Model Tree Technique," J. Korean Soc. Water and Wastewater., 20(6), 1-436(2006).

Cited by

  1. Application of the LPCF Model for Real-Time Contamination Warning in the Water Supply System vol.40, pp.10, 2018, https://doi.org/10.4491/KSEE.2018.40.10.403