Journal of Korean Society on Water Environment (한국물환경학회지)

Korean Society on Water Environment (한국물환경학회)
권호 표지

Prediction of Influent Flow Rate and Influent Components using Artificial Neural Network (ANN)

인공 신경망(ANN)에 의한 하수처리장의 유입 유량 및 유입 성분 농도의 예측

  • Moon, Taesup (Department of Civil and Environmental Engineering, Pusan National University) ;
  • Choi, Jaehoon (Department of Civil and Environmental Engineering, Pusan National University) ;
  • Kim, Sunghui (Department of Civil and Environmental Engineering, Pusan National University) ;
  • Cha, Jaehwan (Department of Civil and Environmental Engineering, Pusan National University) ;
  • Yoom, Hoonsik (Department of Civil and Environmental Engineering, Pusan National University) ;
  • Kim, Changwon (Department of Civil and Environmental Engineering, Pusan National University)
  • 문태섭 (부산대학교 사회환경시스템공학부) ;
  • 최재훈 (부산대학교 사회환경시스템공학부) ;
  • 김성희 (부산대학교 사회환경시스템공학부) ;
  • 차재환 (부산대학교 사회환경시스템공학부) ;
  • 염훈식 (부산대학교 사회환경시스템공학부) ;
  • 김창원 (부산대학교 사회환경시스템공학부)
  • Received : 2007.11.19
  • Accepted : 2007.12.27
  • Published : 2008.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

This work was performed to develop a model possible to predict the influent flow and influent components, which are one of main disturbances causing process problems at the operation of municipal wastewater treatment plant. In this study, artificial neural network (ANN) was used in order to develop a model that was able to predict the influent flow, $COD_{Mn}$, SS, TN 1 day-ahead, 2day-ahead and 3 day ahead. Multi-layer feed-forward back-propagation network was chosen as neural network type, and tanh-sigmoid function was used as activation function to transport signal at the neural network. And Levenberg-Marquart (LM) algorithm was used as learning algorithm to train neural network. Among 420 data sets except missing data, which were collected between 2005 and 2006 at field plant, 210 data sets were used for training, and other 210 data sets were used for validation. As result of it, ANN model for predicting the influent flow and components 1-3day ahead could be developed successfully. It is expected that this developed model can be practically used as follows: Detecting the fault related to effluent concentration that can be happened in the future by combining with other models to predict process performance in advance, and minimization of the process fault through the establishment of various control strategies based on the detection result.

Keywords

Acknowledgement

Grant : 데이터마이닝 기법에 의한 하수처리장 운전의 예측진단

Supported by : 환경부

References

  1. Cartensen, J., Nielsen, M. K. and Strandbaek, H. (1998). Prediction of hydraulic load for urban storm control of municipal WWT plant. Water Science & Technology, 37(12), pp. 363-370
  2. Choi, D. J. and Park, H. K. (2001). A hybrid artificial neural network as a software sensor for optimal control of a wastewater treatment process. Water Research, 35(16), pp. 3959-3967 https://doi.org/10.1016/S0043-1354(01)00134-8
  3. El-Din, A. G. and Smith, D. W. (2002). A neural network model to predict the wastewater inflow incorporating rainfall events. Water Research, 36, pp. 1115-1126 https://doi.org/10.1016/S0043-1354(01)00287-1
  4. Gernaey, K. V., van Loosdrecht, M. C. M., Henze, M., Lind, M. and Sten B. Jorgensen (2004). Activated sludge wastewater treatment plant modelling and simulation: state of the art. Environmental Modeling & Software, 19, pp. 763-783 https://doi.org/10.1016/j.envsoft.2003.03.005
  5. Grieu, S., Traore, A., Polit, M. and Colprim, J. (2005). Prediction of parameters characterizing the state of a pollution removal biologic process. Engineering Application of Artificial Intelligence, 18, pp. 559-573 https://doi.org/10.1016/j.engappai.2004.11.008
  6. Hagan, M. T., Demuth, H. B. and Beale, M. H. (1996). Neural network design, PWS Publishing, Boston, MA
  7. Jang, J. S. R., Sun, C. T. and Mizutani, E. (1997). Nuero-fuzzy and soft computing, Prentice-Hall, Inc., New Jersey
  8. Kim, J. R., Ko, J. H., Im, J. H., Lee, S. H., Kim, S. H., Kim, C. W. and Park, T. J. (2006). Forecasting influent flowrate and composition with occasional data for supervisory management system by time-series model. Water Science & Technology, 53(4-5), pp. 185-192
  9. Kim, Y. J. (2006). Development of inference models and diagnosis algorithms using intelligent methods for sequencing batch reactor operation. Ph. D. thesis, Pusan National University, Korea
  10. Mjalli, F. S., Al-Asheh, S. and Alfadala, H. E. (2007). Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance. Journal of Environmental Management, 83(3), pp. 329-338 https://doi.org/10.1016/j.jenvman.2006.03.004
  11. Shioya, S., Shimizu, K. and Yoshida, T. (1999). Knowledgebased design and operation of bioprocess system. Journal of Bioscience and Bioengineering, 87(3), pp. 261-266 https://doi.org/10.1016/S1389-1723(99)80029-2
  12. The MathWorks, Inc. (2000). Neural network toolbox user's guide, 3 Apple hill drive, Natick
  13. Yoo, C. K., Vanrolleghem, P. A. and Lee, I. B. (2003). Nonlinear modeling and adaptive monitoring with fuzzy and multivariate statistical methods in biological wastewater treatment plants. Journal of Biotechnology, 105, pp. 135-163 https://doi.org/10.1016/S0168-1656(03)00168-8