DOI QR코드

DOI QR Code

Development of Sludge Concentration Estimation Method using Neuro-Fuzzy Algorithm

뉴로-퍼지 알고리즘을 이용한 슬러지 농도 추정 기법 개발

  • Jang, Sang-Bok (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Lee, Ho-Hyun (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Lee, Dae-Jong (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Kweon, Jin-Hee (LETECH Co.Ltd.) ;
  • Chun, Myung-Geun (Department of Control and Robotics Engineering, Chungbuk University)
  • Received : 2014.08.01
  • Accepted : 2015.02.17
  • Published : 2015.04.25

Abstract

A concentration meter is widely used at purification plants, sewage treatment plants and waste water treatment plants to sort and transfer high concentration sludge and to control the amount of chemical dosage. When the strange substance is contained in the sludge, however, the attenuation of ultrasonic wave could be increased or not be transmitted to the receiver. At that case, the value of concentration meter is higher than the actual density value or vibrated up and down. It has also been difficult to automate the residuals treatment process according to the problems as sludge attachment or damage of a sensor. Multi-beam ultrasonic concentration meter has been developed to solve these problems, but the failure of the ultrasonic beam of a specific concentration measurement value degrade the performance of the entire system. This paper proposes the method to improve the accuracy of sludge concentration rate by choosing reliable sensor values and learning them by proposed algorithm. The prediction algorithm is chosen as neuro-fuzzy model, which is tested by the various experiments.

정수장, 하수처리장, 폐수처리장의 배출수 처리공정에서 고 농도의 슬러지 선별, 이송 및 약품 투입량 조절을 위한 기준으로 슬러지 농도계가 사용되고 있다. 그러나 슬러지에 함유된 이물질이 혼입될 경우 감쇄량이 증가하거나 초음파가 수신부에 전달되지 않아 실제 농도값 보다 높은 값을 출력하거나 헌팅현상이 발생한다. 또한 단일 센서에 슬러지 포착 또는 고장 등의 문제로 배출수 공정 자동화에 어려움이 많았다. 이러한 문제점을 개선하기 위해 초음파 다중빔 농도계를 개발하여 사용하고 있으나 특정 초음파 빔의 농도 측정값에 오류가 발생할 경우 전체 농도시스템의 성능이 떨어지는 단점이 있다. 따라서 본 논문에서는 초음파 다중빔 농도계 간의 신뢰성을 판단하고, 신뢰성이 높은 다중빔 농도계만을 사용하여 슬러지 농도 예측값의 성능 향상방안을 제시하였다. 예측 알고리즘으로는 뉴로-퍼지모델을 적용하였으며 다양한 실험을 통하여 제안된 방법의 타당성을 검증하였다.

Keywords

References

  1. Dr. Kawamura, Integrated Design and Operation of Water Treatment Facilities, 2nd edition, 2003.
  2. K. panter, "Comparison of Centrifuge and Belt Press for Compressible Digested After Thermal Hydrolysis", WEFTEC2009, pp. 6220-6229, 2009.
  3. Korea water and wastewater works association, Standard for drinking water facility, 2010.
  4. Seiji Yamaguchi, "New type of sludge density meter using microwaves for application in sewage treatment plants", Water Science and Technology, Vol33, issue1, pp. 53-60, 1996. https://doi.org/10.1016/0273-1223(96)00158-8
  5. S. S. Baek, Y. O. Park, J. H. Ban, "Study on optimal operation of residual treatment process automation", Journal of Korea society for fluid machinery, vol 20, issue 6, pp. 77-81, 2008.
  6. S. B Jang, J. H Kwen, Development of Ultrasonic Multi-beam Sludge density meter, K-water, 2009.
  7. J. Bougadis, K. Adamowski, and R. Diduch, "Short-term municipal water demand forecasting," Hydrological Processes, vol. 19, no. 1, pp. 137-148, 2005. https://doi.org/10.1002/hyp.5763
  8. S. L. Zhou, T. A. McMahon, A. Walton, and J. Lewis, "Forecasting daily urban water demand: a case study of melbourne," Journal of Hydrology, vol. 236, no. 3, pp. 153-164, 2000. https://doi.org/10.1016/S0022-1694(00)00287-0
  9. P. N. Tan, Introduction to data mining, Addison- Wesley, 2006.
  10. J. S. R. Jang, "ANFIS: Adaptive-network-based fuzzy inference system," IEEE Trans. on Systems, Man and Cybernetics, Vol. 23, No. 3, pp. 665-685, 1993. https://doi.org/10.1109/21.256541
  11. H.H Lee, S.B Jang, S.T Hong, M.G Chun, "Intelligent Controller for Constant Control of Residual Chlorine in Water Treatment Process", International journal of fuzzy and intelligent systems, Vol.24 No.2, pp. 147-154, 2014.
  12. Bo-Hyeun Wang, Short-term Electrical Load Forecasting Using Neuro-Fuzzy Model with Error Compensation, International journal of fuzzy and intelligent systems, Vol.9 No.4, pp. 327-332, 2009. https://doi.org/10.5391/IJFIS.2009.9.4.327
  13. S.C Shin, "A Study on Prediction of Wake Distribution by Neuro-Fuzzy System", International journal of fuzzy and intelligent systems, Vol.17 No.2, pp. 154-159, 2007. https://doi.org/10.5391/JKIIS.2007.17.2.154
  14. S.P Chun, S.S Kim, C.B Lee, "Modified Transformation and Evaluation for High Concentration Ozone Predictions", International journal of fuzzy and intelligent systems, Vol.17 No.4, pp. 435-442, 2007. https://doi.org/10.5391/JKIIS.2007.17.4.435