Journal of Korean Society of Water and Wastewater (상하수도학회지)

The Korean Society of Water and Wastewater (대한상하수도학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Wastewater Treatment Process Simulators Based on Artificial Neural Network and Mass Balance Models

인공신경망 및 물질수지 모델을 활용한 하수처리 프로세스 시뮬레이터 구축

  • Kim, Jungruyl (Department of Civil and Environmental Engineering, Urban Design and studies, Chung-Ang University) ;
  • Lee, Jaehyun (Department of Civil and Environmental Engineering, Urban Design and studies, Chung-Ang University) ;
  • Oh, Jeill (Department of Civil and Environmental Engineering, Urban Design and studies, Chung-Ang University)
  • 김정률 (중앙대학교 사회기반시스템공학부) ;
  • 이재현 (중앙대학교 사회기반시스템공학부) ;
  • 오재일 (중앙대학교 사회기반시스템공학부)
  • Received : 2014.10.01
  • Accepted : 2015.05.08
  • Published : 2015.06.15
Download PDF
⟨ Previous Next ⟩

Abstract

Developing two process models to simulate wastewater treatment process is needed to draw a comparison between measured BOD data and estimated process model data: a mathematical model based on the process mass-balance and an ANN (artificial neural network) model. Those two types of simulator can fit well in terms of effluent BOD data, which models are formulated based on the distinctive five parameters: influent flow rate, effluent flow rate, influent BOD concentration, biomass concentration, and returned sludge percentage. The structuralized mass-balance model and ANN modeI with seasonal periods can estimate data set more precisely, and changing optimization algorithm for the penalty could be a useful option to tune up the process behavior estimations. An complex model such as ANN model coupled with mass-balance equation will be required to simulate process dynamics more accurately.

Keywords

References

  1. Choi, D. J., Park, H. K. (2001) Estimation of a wastewater component using a hybrid artificial neural network in a wastewater treatment process, J. of Korean Society on Water Quality, 17(1), pp.87-98.
  2. Chung, S. H., Oh, K. J. (2014) Using genetic algorithm to optimize rough set strategy in KOSPI200 futures market, J. of the Korean Data & Information Science Society, 25(2), pp.28-292. https://doi.org/10.7465/jkdi.2014.25.2.281
  3. Gu, H. S., Kim, K. H. (2007) Distribution Characteristics and Changing Trends of Natural Seasons in Korea, Univ. Konkuk J. of Climate Research, 2(2), pp.105-117.
  4. Jacob Carstensen, Poul Harremoes and Rune Strube (1996) Software sensors based on the grey-box modeling approach. Wat. Sci. Tech., 33(1), pp.117-1263. https://doi.org/10.1016/0273-1223(96)00164-3
  5. Jurgen Schmidhuber (1989) A local learning algorithm for dynamic feedforward and recurrent networks, Connection Science, 1(4), pp.403-412. https://doi.org/10.1080/09540098908915650
  6. Kang, K. H., Jang, J. K., Lee, J. Y., Moon, H. S., Chang, I. S., Kim, J. M., Kim, B. H. (2004) A Low BOD Sensor Using a Microbial Fuel Cell, J. of Korean Society of Environmental Engineers, 26(1), pp.58-63.
  7. Kim, M. H., Yoo, C. K. (2009) Artificial Neural Network Modeling and Prediction Based on Hydraulic Characteristics in a Full-scale Wastewater Treatment Plant, J. of Institute of Control, Robotics and Systems, 15(5), pp.555-561. https://doi.org/10.5302/J.ICROS.2009.15.5.555
  8. Mathworks (2007), Nueral Network Toolbox 5-User's Guide.
  9. Mackenzie L. Davis and Susan J. Masten (2009) Principles of Environmental Engineering and Science. 2nd Ed. pp.481-488, McGraw-Hill, New York.
  10. Michael Hack and Manfred Kohne (1996) Estimation of wastewater process parameters using neural networks, Wat. Sci. Tech, 33(1), pp.101-155. https://doi.org/10.1016/0273-1223(96)00163-1
  11. Paul J. Werbos (1990) Backpropagtion Through Time: What It Does and How to Do It, Proceedings of the IEEE, 78(10), pp.1550-1560. https://doi.org/10.1109/5.58337
  12. Steven C. Chapra (2008) Surface Water-Quality Modeling, pp.590-601, Waveland Press, Long Grove.