Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Study on water quality prediction in water treatment plants using AI techniques

AI 기법을 활용한 정수장 수질예측에 관한 연구

  • Lee, Seungmin (Program in Smart City Engineering, Inha University) ;
  • Kang, Yujin (Program in Smart City Engineering, Inha University) ;
  • Song, Jinwoo (Jemulpo Renaissance Planning Division, Incheon Metropolitan City) ;
  • Kim, Juhwan (Department of Civil Engineering, Inha University) ;
  • Kim, Hung Soo (Department of Civil Engineering, Inha University) ;
  • Kim, Soojun (Department of Civil Engineering, Inha University)
  • 이승민 (인하대학교 스마트시티공학과) ;
  • 강유진 (인하대학교 스마트시티공학과) ;
  • 송진우 (인천광역시 제물포르네상스계획과) ;
  • 김주환 (인하대학교 사회인프라공학과) ;
  • 김형수 (인하대학교 사회인프라공학과) ;
  • 김수전 (인하대학교 사회인프라공학과)
  • Received : 2023.12.27
  • Accepted : 2024.02.19
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

In water treatment plants supplying potable water, the management of chlorine concentration in water treatment processes involving pre-chlorination or intermediate chlorination requires process control. To address this, research has been conducted on water quality prediction techniques utilizing AI technology. This study developed an AI-based predictive model for automating the process control of chlorine disinfection, targeting the prediction of residual chlorine concentration downstream of sedimentation basins in water treatment processes. The AI-based model, which learns from past water quality observation data to predict future water quality, offers a simpler and more efficient approach compared to complex physicochemical and biological water quality models. The model was tested by predicting the residual chlorine concentration downstream of the sedimentation basins at Plant, using multiple regression models and AI-based models like Random Forest and LSTM, and the results were compared. For optimal prediction of residual chlorine concentration, the input-output structure of the AI model included the residual chlorine concentration upstream of the sedimentation basin, turbidity, pH, water temperature, electrical conductivity, inflow of raw water, alkalinity, NH3, etc. as independent variables, and the desired residual chlorine concentration of the effluent from the sedimentation basin as the dependent variable. The independent variables were selected from observable data at the water treatment plant, which are influential on the residual chlorine concentration downstream of the sedimentation basin. The analysis showed that, for Plant, the model based on Random Forest had the lowest error compared to multiple regression models, neural network models, model trees, and other Random Forest models. The optimal predicted residual chlorine concentration downstream of the sedimentation basin presented in this study is expected to enable real-time control of chlorine dosing in previous treatment stages, thereby enhancing water treatment efficiency and reducing chemical costs.

상수도 공급을 위한 정수장에서 전염소 또는 중염소 공정이 도입된 수처리 공정의 염소농도 관리에 필요한 공정제어를 위하여 AI 기술을 활용한 수질예측 기법이 연구되고 있다. 본 연구에서는 정수장 수처리 공정에서 실시간으로 관측, 생산되고 있는 수량·수질자료를 이용하여 염소소독 공정제어 자동화를 목적으로 침전지 후단의 잔류염소 농도를 예측하기 위한 AI 기반 예측모형을 개발하였다. AI 기반 예측모형은 과거 수질 관측자료를 학습하여 이후 시점의 수질에 대한 예측이 가능한 기법으로, 복잡한 물리·화학·생물학적 수질모형과 달리 간단하고 효율적이다. 다중회귀 모형과 AI 기반 모형인 랜덤포레스트와 LSTM을 이용하여 정수장의 침전지 후단 잔류염소 농도를 예측하여 비교하였다. 최적의 잔류염소 농도 예측을 위한 AI 모형의 입출력 구조로는 침전지 전단의 잔류염소 농도, 침전지 탁도, pH, 수온, 전기전도도, 원수의 유입량, 알칼리도, NH3 등을 독립변수로, 예측하고자 하는 침전지 유출수의 잔류염소 농도를 종속변수로 선정하였다. 독립변수는 침전지 후단의 잔류염소에 영향이 있는 정수장에서 확보가 가능한 관측자료중에서 분석을 통해 선별하였으며, 분석 결과 연구대상 정수장인 정수장에서는 중회귀모형, 신경망모형, 모델트리 및 랜덤포레스트 모형을 비교한 결과 랜덤포레스트에 기반한 모형오차가 가장 낮게 도출되는 결과를 얻을 수 있었다. 본 연구에서 제시하는 침전지 후단의 적정 잔류염소 농도 예측값은 이전 처리단계에서 염소주입량의 실시간 제어가 가능토록 할 수 있어 수처리 효율 향상과 약품비 절감에 도움이 될 것으로 기대된다.

Keywords

Acknowledgement

이 논문은 행정안전부 재난피해 복구역량강화 기술개발사업의 지원을 받아 수행된 연구임(2021-MOIS36-002).

References

  1. Amit, Y., and Geman, D. (1997). "Shape quantization and recognition with randomized trees." Neural Computation, Vol. 9, No. 7, pp. 1545-1588.
  2. Bates, S., Hastie, T., and Tibshirani, R. (2023). "Cross-validation: What does it estimate and how well does it do it?." Journal of the American Statistical Association, pp. 1-12.
  3. Breiman, L. (2001). "Random forests." Machine learning, Vol. 45, No. 1, pp. 5-32.
  4. Cohen, I., Huang, Y., Chen, J., and Benesty, J. (2009). "Pearson correlation coefficient." Noise Reduction in Speech Processing, Edited by Benesty, J., and Kellermann, W., Springer, Berlin, Heidelberg, Germany, pp. 1-4.
  5. Diamantopoulos, A., and Siguaw, J.A. (2006). "Formative versus reflective indicators in organizational measure development: A comparison and empirical illustration." British Journal of Management, Vol. 17, No. 4, pp. 263-282.
  6. Gulzar, A., Ihsanullah, I., Mu, N., and Mika, S. (2022). "Applications of artificial intelligence in water treatment for optimization and automation of adsorption processes: Recent advances and prospects." Chemical Engineering Journal, Vol. 427, No. 1, 130011.
  7. Han, H., Choi, C., Jung, J., and Kim, H.S. (2021). "Application of sequence to sequence learning based LSTM model (LSTM-s2s) for forecasting dam inflow." Journal of Korea Water Resources Association, Vol. 54, No. 3, pp. 157-166.
  8. Ho, T.K. (1998). "The random subspace method for constructing decision forests." IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 8, pp. 832-844.
  9. Hochreiter, S., and Schmidhuber, J. (1997). "Long short-term memory." Neural Computation, Vol. 9, No. 8, pp. 1735-1780.
  10. Holland, J.H. (1975). Adaptation in natural artificial systems. The MIT Press, MA, U.S., pp. 1-19.
  11. Jun, H.B., Lee, Y.J., Lee, B.D., and Lee, J.D. (2001). "Effects of prechlorination on diatoms coagulation." Journal of Korean Society on Water Environment, Vol. 17, No. 3, pp. 347-355.
  12. Jung, S.H., Lee, D.O., and Lee, K.S. (2018). "Prediction of river water level using deep learning open library." Journal of Korean Socioty Hazard Mitigation, Vol. 18, No. 1, pp. 1-11.
  13. Kang, G.W., Park, C.Y., and Kim, J.H. (1992). "Nonlinear prediction of river runoff using pattern recognition methods." Journal of Korea Water Resources Association Conference, pp. 196-202.
  14. Kim, B.J., Choi, M.W., Kim, G.H., and Kim, H.S. (2016a). "Evaluation and analysis of characteristics for Hazen-Williams C based on measured data in multi-regional water supply systems." Journal of Korean Society of Water and Wastewater, Vol. 30, No. 2, pp. 197-206.
  15. Kim, B.J., Kim, G.H., and Kim, H.S. (2016b). "Statistical analysis of Hazen-Williams C and influencing factors in multi-regional w ater supply system." Journal of Korea Water Resources Association, Vol. 49, No. 5, pp. 197-206.
  16. Kim, D.H. (2022). Development of flood water level forecasting and flood damage risk assessment method for river basin using AI-based hybrid moded. Ph. D. Dissertation, Inha University, pp. 34-37.
  17. Kim, D.H., Lee, K.S., Hwang-Bo, J.G., Kim, H.S., and Kim, S.J. (2022a). "Development of the method for flood water level forecasting and flood damage warning using an AI-based model." Journal of the Korean Society of Hazard Mitigation, Vol. 22, No. 4, pp. 145-156.
  18. Kim, H.S., Jeong, G.H., Kim, E.S., and Kim, J.H. (2001). "Estimation of mean and variance for NH3-N data of Puyeo Intake." Journal of Korea Water Resources Association, Vol. 34, No. 4, pp. 357-364.
  19. Kim, J.H., Lee, K.H., Kim, S.J., and Kim, K.H. (2022b). "Machine learning model for residual chlorine prediction in sediment basin to control pre-chlorination in water treatment plant." Journal of Korea Water Resources Assocition, Vol. 55, No. S-1, pp. 1283-1293.
  20. Kim, J.S. (2021). Development of prediction and warning technique of heavy rain damage risk based on ensemble machine learning and risk matrix. Ph. D. Dissertation, Inha University, p. 56.
  21. Kim, J.W., Kim, Y.S., Kang, N.R., Jung, J.W., and Kim, S.J. (2014). "Risk assessment for water quality of a river using QUAL2E model." Journal of Wetlands Researh, Vol. 16, No. 3, pp. 441-450.
  22. Kim, S.W., and Kim, H.S. (2007a). "Neural network-genetic algorithm model for modeling of nonlinear evaporation and evapotranspiration time series 1. Theory and application of the model." Journal of Korea Water Resources Association, Vol. 40. No. 1, pp. 73-88. https://doi.org/10.3741/JKWRA.2007.40.1.073
  23. Kim, S.W., and Kim, H.S. (2007b). "Neural network-genetic algorithm model for modeling of nonlinear evaporation and evapotranspiration time series 2. Optimal model construction by uncertainty analysis." Journal of Korea Water Resources Association, Vol. 22. No. 2, pp. 149-169.
  24. Kwon, S.D. (2015). "Exploring a way to overcome multicollinearity problems by using hierarchical construct model in structural equation model." Journal of Information Technology Applications & Management, Vol. 40. No. 1, pp. 89-99.
  25. Kwon, S.H., Lee, J.W., and Chung, G,H. (2017). "Snow damages estimation using artificial neural network and multiple regression analysis." Korean Society of Disaster & Security, Vol. 17, No. 2, pp. 315-325.
  26. Kyoung, M.S., Kim, S.D., Kim, H.S., and Park, S.K. (2006). "Statistical water quality monitoring network design of Kyung-An Stream." Journal of Civil Engineering, Vol. 26, No. 3B, pp. 291-300.
  27. Le, X.H., Ho, H.V., Lee, G., and Jung, S. (2019). "Application of long short-term memory (LSTM) neural network for flood forecasting." Water, Vol. 11, No. 7, 1387.
  28. Lee, H.H., Jang, S.B., Hong, S.T., and Chun, M.G. (2014). "Intelligent controller for constant control of residual chlorine in water treatment process." Journal of Korean Institute of Intelligent Systems, Vol. 23, No. 1, pp. 147-154.
  29. Lee, K.H., Kim, J.H., Lim, J.L., and Chae, S.H. (2007). "Prediction models of residual chlorine in sediment basin to control pre-chlorination in water treatment plant." Journal of Korean Society of Water and Wastewater, Vol. 21, No. 5, pp. 601-607.
  30. Lee, S.M., Baek, S.W., Lee, J.H., Kim, K.T., Kim, S.J., and Kim, H.S. (2023a). "Development of disaster severity classification model using machine learning technique." Journal of Korea Water Resources Assocition, Vol. 56, No. 4, pp. 261-272.
  31. Lee, S.M., Wang, W.J., Kim, D.H., Han, H.C., Kim, S.J., Kim, H.S. (2023b) "Establishing meteorological drought severity considering the level of emergency water supply." Journal of Korea Water Resources Assocition, Vol. 56, No. 10, pp. 619-629.
  32. Liaw, A., and Wiener, M. (2002). "Classification and regression by randomforest." R News, Vol. 12, No. 3, pp. 18-22.
  33. Lim, J.O. (2019). Estimation of flood damage based on multi-dimensional flood damage assessment and multiple regression analysis: A case study for the PyeongChang River Basin. Master's Thesis, Inha University, pp. 20-22.
  34. Lowe, M., Qin, R., and Mao, X. (2022). "A review on machine learning, artificial intelligence, and smart technology in water treatment and monitoring." Water, Vol. 14, No. 9, 1384.
  35. Ministry of Environment (ME) and Korea Environmental Industry & Technology Institute (KEITI) (2021). 2020 water & wastewater R&D technology trends report.
  36. Ngo, T.H.D., and La Puente, C.A. (2012). "The steps to follow in a multiple regression analysis." Proceedings of the SAS Global Forum, Florida, FL, U.S., pp. 22-25.
  37. Petter, S., Straub, D., and Rai, A. (2007). "Specifying formative constructs in information systems research." MIS Quarterly, Vol. 31, No. 4, pp. 623-656.
  38. Waterworks Headquarters Incheon Metropolitan City (WHIM) (2023). 2023 Incheon sky water quality report, pp. 16-22.
  39. Yoon, J.Y., Byun, S.J., and Choi, Y.S. (2001) "Importance of Prechlorination practices and structures of clearwell in estimating disinfection capabilities in water treatment plants." Journal of Korean Society on Water Environment, Vol. 17, No. 3, pp. 327-337.
  40. Zhang, Q., and Stanley, S.J. (1999). "Real time water treatment process control with artificial neyral networks." Journal of Environmental Engineering, Vol. 125, No. 2, pp. 153-160.