Membrane Journal (멤브레인)

The Membrane Society of Korea (한국막학회)
권호 표지
DOI QR코드

DOI QR Code

Modeling of a Dynamic Membrane Filtration Process Using ANN and SVM to Predict the Permeate Flux

ANN 및 SVM을 사용하여 투과 유량을 예측하는 동적 막 여과 공정 모델링

  • Soufyane Ladeg (Materials and Environmental Laboratory, University of Medea) ;
  • Mohamed Moussaoui (Department of Mechanical Engineering, University of Bouira) ;
  • Maamar Laidi (Laboratory of Biomaterials and Transport Phenomena, University of Medea) ;
  • Nadji Moulai-Mostefa (Materials and Environmental Laboratory, University of Medea)
  • Received : 2022.11.20
  • Accepted : 2023.02.13
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Two computational intelligence techniques namely artificial neural networks (ANN) and support vector machine (SVM) are employed to model the permeate flux based on seven input variables including time, transmembrane pressure, rotating velocity, the pore diameter of the membrane, dynamic viscosity, concentration and density of the feed fluid. The best-fit model was selected through the trial-error method and the two statistical parameters including the coefficient of determination (R2) and the average absolute relative deviation (AARD) between the experimental and predicted data. The obtained results reveal that the optimized ANN model can predict the permeate flux with R2 = 0.999 and AARD% = 2.245 versus the SVM model with R2 = 0.996 and AARD% = 4.09. Thus, the ANN model is found to predict the permeate flux with high accuracy in comparison to the SVM approach.

본 연구에서는 투과 유량 모델을 개발하기 위하여, 시간, 막 전후의 압력 차, 회전 속도, 막의 기공 크기, 동점도, 농도 및 공급 유체의 밀도 등 7개의 입력 변수에 기반한 두 종류(ANN 및 SVM) 인공지능 기법을 이용하였다. 시행착오법과 실험데이터와 예측 데이터 간의 결정 계수(R2) 와 평균절대상대편차(AARD)를 포함한 두 가지 통계 변수를 통해 최적의 모델을 선정하였다. 최종적으로 얻어진 결과에서 최적화된 ANN 모델이 R2 = 0.999 및 AARD% = 2.245인 투과 플럭스 예측 정확도를 보여서, R2 = 0.996 및 AARD% = 4.09의 정확도를 보인 SVM 모델에 비해 더 정확함을 알 수 있었다. 또한, ANN 모델은 SVM 방식에 비해 투과 유속을 예측하는 능력도 더 높은 것으로 나타났다.

Keywords

Acknowledgement

This work was supported by the Laboratory of Materials and Environment (LME, University of Medea, Algeria).

References

  1. L. Ding and M. Y. Jaffrin, "Benefits of high shear rate dynamic nanofiltration and reverse osmosis: A review", Sep. Sci. Technol., 49, 1953 (2014).
  2. L. Ding, O. Al-Akoum, A. Abraham, and M. Y. Jaffrin, "Milk protein concentration by ultrafiltration with rotating disk modules", Desalination., 144, 307-311 (2002). https://doi.org/10.1016/S0011-9164(02)00334-X
  3. S. Mondal and S. De, "A fouling model for steady state crossflow membrane filtration considering sequential intermediate pore blocking and cake formation", Sep. Purif. Technol., 75, 222 (2010).
  4. G. Belfort, H. R. Davis, and L. A. Zydney, "The behavior of suspensions and macromolecular solutions in crossflow microfiltration", J. Membr. Sci., 96, 1 (1994).
  5. M. Y. Jaffrin, "Dynamic shear-enhanced membrane filtration: A review of rotating disks, rotating membranes and vibrating systems", J. Membr. Sci., 324, 7 (2008).
  6. L. Ding, M. Y. Jaffrin, and J. Luo, "Dynamic filtration with rotating disks, and rotating or vibrating membranes", Progress in Filtration and Separation, pp. 27, Academic Press (2015).
  7. A. Brou, L. Ding, P. Boulnois, and M. Y. Jaffrin, "Dynamic microfiltration of yeast suspensions using rotating disks equipped with vanes", J. Membr. Sci., 197, 269 (2002).
  8. R. Bouzerar, L. Ding, and M. Y. Jaffrin, "Local permeate flux-shear-pressure relationships in a rotating disk microfiltration module: Implications for global performance", J. Membr. Sci., 170, 127 (2000).
  9. R. Bouzerar, M. Y. Jaffrin, A. Lefevre, and P. Paullier, "Concentration of ferric hydroxide suspensions in saline medium by dynamic cross-flow filtration", J. Membr. Sci., 165, 111 (2000).
  10. Z. Zhu, J. Luo, L. Ding, O. Bals, M. Y. Jaffrin, and E. Vorobiev, "Chicory juice clarification by membrane filtration using rotating disk module", Food Eng., 115, 264 (2013).
  11. J. Luo, Z. Zhu, L. Ding, O. Bals, Y. Yinhua, M. J. Jaffrin, and E. Vorobiev, "Flux behavior in clarification of chicory juice by high-shear membrane filtration: evidence for threshold flux", J. Membr. Sci., 435, 120 (2013).
  12. S. Park, S. S Baek, J. Pyo, Y. Pachepsky, J. Park, and K. Cho, "Deep neural networks for modeling fouling growth and flux decline during NF/RO membrane filtration", J. Membr. Sci., 587, 117 (2019).
  13. S. Ladeg, N. Moulai-Mostefa, A. Ould-Dris, and L. Ding, "Modeling of surface fouling on the surface of a rotating disk membrane using CFD and numerical study", Desalin. Water Treat., 190, 52 (2020).
  14. Z. Zhu, S. Ladeg, L. Ding, O. Bals, N. MoulaiMostefa, M. Y. Jaffrin, and E. Vorobiev, "Study of rotating disk assisted dead-end filtration of chicory juice and its performance optimization", Ind. Crops Prod., 53, 154 (2014).
  15. Z. Yusuf, N. A. Wahab, and S. Sudin, "Soft computing techniques in modelling of membrane filtration system: A review", Desalin. Water Treat., 161, 144 (2019).
  16. R. Soleimani, N. Alavi, B. Mirza, and A. Salahi, "Experimental investigation, modeling and optimization of membrane separation using artificial neural network and multi-objective optimization using genetic algorithm", Chem. Eng. Res. Des., 91, 883 (2013).
  17. J. Jawad, A. H. Hawari, and S. Zaidi, "Modeling of forward osmosis process using artificial neural networks (ANN) to predict the permeate flux", Desalination., 484, 114427 (2020).
  18. G. B. Sahoo and C. Ray, "Predicting flux decline in crossflow membranes using artificial neural networks and genetic algorithms", J. Membr. Sci., 283, 147 (2006).
  19. M. Bagheri, A. Akbari, and S. A. Mirbagheri, "Advanced control of membrane fouling in filtration systems using artificial intelligence and machine learning techniques: A critical review", Process Saf. Environ. Prot., 123, 229 (2019).
  20. Q. F. Liu, S. H. Kim, and S. Lee, "Prediction of microfiltration membrane fouling using artificial neural network models", Sep. Purif. Technol., 70, 96 (2009).
  21. L. Auria and R. A. Moro, "Support vector machines (SVM) as a technique for solvency analysis", SSRN, DIW Berlin., 811 (2008).
  22. C. Li, and Y. Tao, "Application of support vector machine with simulated annealing algorithm in MBR membrane pollution prediction", IEEE 15th International Conference on Software Engineering Research, Management and Applications (SERA), pp. 211, London, UK (2017).
  23. H. Adib, F. Sharifi, N. Mehranbod, N. M. Kazerooni, and M. Koolivand, "Support Vector Machine based modeling of an industrial natural gas sweetening plant", J. Nat. Gas Sci. Eng., 14, 121 (2013).
  24. K. Gao, X. Xi, Z. Wang, Y. Ma, S. Chen, X. Ye, and Y. Li, "Use of support vector machine model to predict membrane permeate flux", Desalin. Water Treat., 57, 16810 (2016).
  25. N. S. A. Yasmin, N. A. Wahab, A. N. Anuar, and M. Bob, "Performance comparison of SVM and ANN for aerobic granular sludge", Bull. Electr. Eng. Informatics., 8, 1392 (2019).
  26. A. Brou, M. Y. Jaffrin, and L. Ding, "Microfiltration and ultrafiltration of polysaccharides produced by fermentation using a rotating disk dynamic filtration system", J. Courtois, Biotechnol. Bioeng., 82, 429 (2003).
  27. W. Zhang, L. Ding, M. Y. Jaffrin, and B. Tang, "Membrane cleaning assisted by high shear stress for restoring ultrafiltration membranes fouled by dairy wastewater", Chem. Eng. J., 325, 457 (2017).
  28. R. Bouzerar, M. Y. Jaffrin, L. Ding, and P. Paullier, "Influence of geometry and angular velocity on performance of a rotating disk filter", AIChE J., 46, 257 (2000).
  29. A. H. Mohammadi, F. Gharagheizi, A. Eslamimanesh, and D. Richon, "Evaluation of experimental data for wax and diamondoids solubility in gaseous systems", Chem. Eng. Sci., 81, 1 (2012).
  30. A. Baghban, A. Jalali, M. Shafiee, M. H. Ahmadi, and K. Chau, "Developing an ANFIS-based swarm concept model for estimating the relative viscosity of nanofluids", Eng. Appl. Comput. Fluid Mech., 13, 26 (2019).