Journal of Korean Society of Water and Wastewater (상하수도학회지)

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

DOI QR Code

An early fouling alarm method for a ceramic microfiltration pilot plant using machine learning

머신러닝을 활용한 세라믹 정밀여과 파일럿 플랜트의 파울링 조기 경보 방법

  • Dohyun Tak (Major of Civil Engineering, Division of Sustainable Engineering, Pukyong National University) ;
  • Dongkeon Kim (Major of Civil Engineering, Division of Sustainable Engineering, Pukyong National University) ;
  • Jongmin Jeon (Major of Civil Engineering, Division of Sustainable Engineering, Pukyong National University) ;
  • Suhan Kim (Major of Civil Engineering, Division of Sustainable Engineering, Pukyong National University)
  • 탁도현 (부경대학교 지속가능공학부 토목공학전공) ;
  • 김동건 (부경대학교 지속가능공학부 토목공학전공) ;
  • 전종민 (부경대학교 지속가능공학부 토목공학전공) ;
  • 김수한 (부경대학교 지속가능공학부 토목공학전공)
  • Received : 2023.08.31
  • Accepted : 2023.10.11
  • Published : 2023.10.15
Download PDF
⟨ Previous Next ⟩

Abstract

Fouling is an inevitable problem in membrane water treatment plant. It can be measured by trans-membrane pressure (TMP) in the constant flux operation, and chemical cleaning is carried out when TMP reaches a critical value. An early fouilng alarm is defined as warning the critical TMP value appearance in advance. The alarming method was developed using one of machine learning algorithms, decision tree, and applied to a ceramic microfiltration (MF) pilot plant. First, the decision tree model that classifies the normal/abnormal state of the filtration cycle of the ceramic MF pilot plant was developed and it was then used to make the early fouling alarm method. The accuracy of the classification model was up to 96.2% and the time for the early warning was when abnormal cycles occurred three times in a row. The early fouling alram can expect reaching a limit TMP in advance (e.g., 15-174 hours). By adopting TMP increasing rate and backwash efficiency as machine learning variables, the model accuracy and the reliability of the early fouling alarm method were increased, respectively.

Keywords

Acknowledgement

이 논문은 부경대학교 자율창의학술연구비(2023년)에 의하여 연구되었음

References

  1. Blum, A.L., and Langley, P. (1997). Selection of relevant features and examples in machine learning, Artif. Intell., 97, 245-271.  https://doi.org/10.1016/S0004-3702(97)00063-5
  2. Choi, B. (2007). Influence of conditions for pre-treatment, aeration intensity and methods of backwash on micro-filter fouling in water treatment, Master's Thesis, Yonsei University. 
  3. Dalmau, M., Rodriguez-Roda, I., Ayesa, E., Odriozola, J., Sancho, L., and Comas, J. (2013). Development of a decision tree for the integrated operation of nutrient removal MBRs based on simulation studies and expert knowledge, J. Chem. Eng., 217, 174-184.  https://doi.org/10.1016/j.cej.2012.11.060
  4. Dong-Ah Geological Engineering (2012). Assessment of applicability by ceramic membrane filtration process at Beomeosa water treatment plant, Research report.
  5. Hall, M.A., and Smith, L.A. (1998). Practical feature subset selection for machine learning, Comput. Sci., 98, 181-191. 
  6. Han, S.W., Lee, C.W., and Kang, L.S. (2003). Improvement of the effectiveness of drinking water treatment using a mixture of polyamine and PACl, Korean Chem. Eng. Res., 41(3), 319-325. 
  7. Jang, D. and Park, M. (2021). Art price prediction using decision tree-based machine learning methods, Korean Manag. Rev., 50(2), 357-381.  https://doi.org/10.17287/kmr.2021.50.2.357
  8. Kim, D., Kim, N., Jeon, J., Kim, J., Lim, J., and Kim S. (2022). Reconsidering clean-in-place criterion for low pressure membrane filtration systems using a model verified by long-term pilot plant operation data, J. Water Process. Eng., 46, 102506. 
  9. Kim, J.Y., Jeon, J., Kim, N., and Kim, S. (2021). Predicting flux of forward osmosis membrane module using deep learning, J. Korean Soc. Water Wastewater, 35(1), 93-100.  https://doi.org/10.11001/jksww.2021.35.1.093
  10. Kim, M., Kim, N., Jeon, J., and Kim, S. (2020), Vibration signals at the early stage of fouling in reverse osmosis system, Desalination Water Treat., 183, 81-87.  https://doi.org/10.5004/dwt.2020.25257
  11. Kim, S. (2013). A process diagnosis method for membrane water treatment plant using a constant flux membrane fouling model, J. Korean Soc. Water Wastewater, 27(1), 139-146.  https://doi.org/10.11001/jksww.2013.27.1.139
  12. Kim, S., Lim, J., Park, J.Y., and Kim, J.O. (2014). Effect of flux fluctuation on the fouling in membrane water treatment system for smart water grid, Desalination Water Treat., 52, 1028-1034.  https://doi.org/10.1080/19443994.2013.826775
  13. Ko, Y.S. (2011). The Construction methodology of a rule-based expert system using CART-based decision tree method, J. Korea Inst. Electron. Commun. Sci., 6(6), 849-854. 
  14. Park, S.H., Park, Y.G., Lim, J., and Kim, S. (2015). Evaluation of ceramic membrane applications for water treatment plants with a life cycle cost analysis, Desalination Water Treat., 54, 973-979.  https://doi.org/10.1080/19443994.2014.912162
  15. Pi, M.G., Shin, I.H., and Min, O.G. (2019). Visual analytics system to help feature selection of machine learning, Korea Software Congress 2019, Pyeongchang, South korea. 
  16. Schmitt, F., Banu, R., Yeom, I.T., and Do, K.U. (2018). Development of artificial neural networks to predict membrane fouling in an anoxic-aerobic membrane bioreactor treating domestic wastewater, Biochem. Eng. J., 133, 47-58.  https://doi.org/10.1016/j.bej.2018.02.001
  17. Shetty, G.R., and Chellam, S. (2003). Predicting membrane fouling during municipal drinking water nanofiltration using artificial neural networks, J. Membr. Sci., 217(1), 69-86.  https://doi.org/10.1016/S0376-7388(03)00075-9
  18. Song, Y.Y. and Lu, Y. (2015). Decision tree methods: applications for classification and prediction, Shanghai Arch. Psychiatry, 27(2), 130-135. 
  19. Yoon, N., Kim, J., Lim, J.L., Abbas, A., Jeong, K., and Cho, K.H. (2021). Dual-stage attention-based LSTM for simulating performance of brackish water treatment plant, Desalination, 512, 115107. 
  20. You, S.J., Ahan, H.W., Park, S.H., Lim, J., Hong, S.C., and Lee, B.I. (2014). The study on optimum operation conditions of ceramic MF membrane process in Y water treatment plant, Membr., 24, 201-212.  https://doi.org/10.14579/MEMBRANE_JOURNAL.2014.24.3.201