Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Intelligent Controller for Optimal Coagulant Dosage Rate in Water Treatment Process

정수장 약품 최적 주입률 결정을 위한 지능형 제어기 개발

  • Received : 2015.03.22
  • Accepted : 2015.06.12
  • Published : 2015.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

Chemicals are injected in order to remove a variety of organic substances contained in the water purification plant influent. It can be determined with measuring sedimentation turbidity 4~7 hours later, whether the chemical dosage rate is proper or not, which make the real-time feedback control impossible. In addition, manual operation in accordance with the Jar-Test carried out in the laboratory and the operator's experience may cause the experimental and human error by the changes of organic characteristics and water quality. Especially at night ad weekend, the rate have been determined only by the operator judgment owing to environment engineer's absence. Therefore, the decision of optimal chemical dosage rate using proposed intelligent control algorithm is expected to result in real-time injection and cost reduction.

정수장 유입수에 포함된 다양한 유기물을 제거하기 위하여 약품을 주입하고 있으나 적정 주입률 결정은 4~7시간 후에나 탁도를 통하여 확인 가능함에 따라 실시간 피드백 제어가 불가하다. 또한 실험실에서 실시하는 Jar-Test 및 운영자의 경험에 따른 수동운전은 유기물 특성 및 수질 변화로 인하여 실험 및 휴먼에러가 발생할 수 있다. 특히 야간/주말 등에는 실험을 실시할 수 없어 운영자 판단에 의한 간헐적 변경만이 이루어지고 있다. 따라서 지능제어 알고리즘을 이용한 적정 약품 주입률을 학습하여 실시간 약품 주입과 주입량 감소로 원가절감을 달성코자 하였다.

Keywords

References

  1. Paul F. Gooda, C.W. Olanowb, Daniel P. Perl, "Neuromelanin-containing neurons of the substantia nigra accumulate iron and aluminum in Parkinson's disease", Elsevier Brain Research, vol. 593, issue 2, pp. 343-346, 1992. https://doi.org/10.1016/0006-8993(92)91334-B
  2. H Bae, S.S Kim, D.W Choi, S.T Lee, Y.J Kim, "Application of data mining method to determine coagulant type and dosage rate in accordance with raw water conditions", Journal of the korean institute of intelligent systems, vol. 15, No 1, pp. 53-58, 2005. https://doi.org/10.5391/JKIIS.2005.15.1.053
  3. K-water research institute, "Study of system development for automatic coagulant dosage rate," , Technical report by K-water, pp. 14-17, 1977.
  4. A. P. Black and S. A. Hamnah, "Electrophoretic Studies of Turbidity removal Coagulant with Aluminum Sulfate," J. AWWA, vol. 53, no. 4, pp. 438-452, 1961.
  5. O. Yagishita, O. Itoh, and M. Sugeno, "Application of fuzzy reasoning to the water purification process," Industrial Application of Fuzzy Control, pp. 19-39, 1985.
  6. K. Baba, I. Enbutu, H. Matuzki, and S. Nogita, "Intelligent support system for water and sewage treatment plants which includes a past history learning function-coagulant injection guidance system using neural net algorithm," IAWPRC, pp. 227-234, 1990.
  7. I. Enbutsu, K. Baba, N. Hara, K. Waseda, and S. Nogita, "Integration of multi AI paradigms for intelligent operation support systems-fuzzy rule extraction from a neural network," IAW Water Science & Technology, vol. 28, no. 11, pp. 333-340, 1993.
  8. B.J Lee, "Study of modelling to determine the optimal coagulant dosage rate using neural network," M.D paper of Jeon-nam Univ., pp. 34-41, 1992.
  9. Guan-De Wu, Shang-Lien Lo, "Predicting real-time coagulant dosage in water treatment by artificial neural networks and adaptive network-based fuzzy inference system", Elsevier Engineering Applications of Artificial Intelligence, vol. 21, issue 8, pp. 1189-1195, Dec. 2008. https://doi.org/10.1016/j.engappai.2008.03.015
  10. Claude Gagnon, Bernard P.A. Grandjean, Jules Thibault Lienert, "Modelling of coagulant dosage in a water treatment plant", Elsevier Artificial Intelligence in Engineering, vol. 11, issue 4, pp. 401-404, Oct. 1997. https://doi.org/10.1016/S0954-1810(97)00010-1
  11. Jacob Cohen, Patricia Cohen, Stephen G. West, Leona S. Aiken, "Applied multiple regression/ correlation analysis for the behavioral sciences," Routledge, pp. 19-31, 2013.
  12. Richard O. Duda, Peter E. Hart, David G. Stoke. "Pattern Classification," Wiley, pp. 114-125, 2012.
  13. J.H Seol, Y.D Lim, "Study of position control for DC servo motor using neuro fuzzy system," Korea institute of intelligent system, vol. 7, no. 5, pp. 51-59, 1997.
  14. H.H Lee, S.B Jang, S.T Hong, M.G Jeon, "Intelligent Controller for Constant control of residual chlorine in WTP", Journal of korean institute of intelligent systems, vol. 24, no. 2, pp. 147-154, 2014. https://doi.org/10.5391/JKIIS.2014.24.2.147
  15. Jyh-Shing Roger Jang, Chuen-Tsai Sun and Eiji Mizutani. "A Computational Approach to Learning and Machine Intelligence," IEEE Transactions on automatic control, vol. 42, no. 10, pp. 1482-1484, 1997. https://doi.org/10.1109/TAC.1997.633847
  16. B.H Wang, Short-term electrical load forecasting using neuro-Fuzzy model with error compensation, Journal of korean institute of intelligent systems, vol. 9 no.4, pp. 327-332, 2009.