Application of Artificial Intelligence in Evaluating the Crossflow Microfiltration Process for Treating Effluent Generated in a Sewage Treatment System

https://doi.org/10.55977/etsjournal.v01i01.e026001

Authors

  • Érica Regina Filletti Department of Physics and Mathematics, Institute of Chemistry; São Paulo State University – UNESP; Araraquara, Brasil
  • Giovana Herrera Ribeiro Pereira Department of Engineering of Bioprocesses and Biotechnology, School of Pharmaceutical Sciences; São Paulo State University – UNESP; Araraquara, Brasil

Keywords:

Artificial neural networks, Crossflow Microfiltration, Wastewater treatment, Sustainability

Abstract

This study explores the application of artificial neural networks (ANNs) to optimize the crossflow microfiltration process in wastewater treatment. This membrane filtration method is efficient in removing suspended particles, turbidity, and microorganisms, but faces challenges such as membrane clogging, which reduces efficiency and increases operating costs. The research aims to develop an artificial intelligence-based model capable of optimizing filtration conditions and improving overall system performance. The experimental data used include variables such as time, volume, flow rate and temperature to predict permeate flux. The ANN model was trained in MATLAB software using the Levenberg-Marquardt method, with data percentages distributed between training, validation, and testing. The analyses were performed using error histograms, linear regression plots, percentage errors, and mean squared error (MSE) metrics. Two models were developed: one for mixed liquor and one for water, demonstrating high accuracy in both cases. The results indicated that the models were able to predict data patterns with coefficients of determination (R²) equal to 1, indicating a perfect linear relationship between actual and predicted values. The MSE graph showed a consistent reduction over the epochs, evidencing the efficiency of the training. Furthermore, low relative mean errors (0.064 for liquor and 0.0031 for water) reinforce the effectiveness of the model. The research validated the use of ANNs in optimizing effluent treatment processes, promoting operational efficiency and sustainability.

Keywords: Artificial neural networks; Crossflow microfiltration; Wastewater treatment; Sustainability

References

CAVALCANTI, A. S.; FILHO, H. J. I.; GUIMARÃES, O. L. C.; SIQUEIRA, A. F. Modelagem neural e análise estatística do processo de degradação de chorume por foto-Fenton solar. Revista Ambiente & Água, v. 10, p. 89–106, 2015. DOI: 10.4136/ambi-agua.1341. DOI: https://doi.org/10.4136/ambi-agua.1341

DE ARAUJO, L. F.; CAMARGO, F. P.; NETTO, A. T.; VERNIN, N. S.; DE ANDRADE, R. C. Analysis of the coverage of supply and of the water quality distributed in different regions of Brazil in 2019. Ciência & Saúde Coletiva, v. 27, p. 2935–2947, 2022. DOI: 10.1590/1413-81232022277.16472021. DOI: https://doi.org/10.1590/1413-81232022277.16472021

DEVLIN, J.; CHANG, M. W.; LEE, K.; TOUTANOVA, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019). Minneapolis, MN, USA, 2019. p. 4171–4186. DOI: https://doi.org/10.18653/v1/N19-1423

FIORIN, D. V.; MARTINS, F. R.; SCHUCH, N. J.; PEREIRA, E. B. Aplicações de redes neurais e previsões de disponibilidade de recursos energéticos solares. Revista Brasileira de Ensino de Física, v. 33, n. 1, 2011. DOI: 10.1590/S1806-11172011000100009. DOI: https://doi.org/10.1590/S1806-11172011000100009

HAGAN, M. T.; MENHAJ, M. B. Training Feedforward Networks with the Marquardt Algorithm. IEEE Transactions on Neural Networks, v. 5, n. 6, p. 989–993, 1994. DOI: 10.1109/72.329697. DOI: https://doi.org/10.1109/72.329697

KINGMA, D. P.; BA, J. Adam: A Method for Stochastic Optimization. In: 3rd International Conference on Learning Representations (ICLR). San Diego, USA, 2015.

KROGH, A. What are artificial neural networks? Nature Biotechnology, v. 26, n. 2, p. 195–197, 2008. DOI: 10.1038/nbt1386. DOI: https://doi.org/10.1038/nbt1386

VIDAL, C. M. S.; CAMPOS, J. R. Coagulação associada à microfiltração para o tratamento avançado de esgoto sanitário. Ambiência, v. 5, n. 1, p. 101–114, 2009.

MANNING, C. D. Computational linguistics and deep learning. Computational Linguistics, v. 41, n. 4, p. 701–707, 2015. DOI: 10.1162/COLI_a_00239. DOI: https://doi.org/10.1162/COLI_a_00239

MCCULLOCH, W. S.; PITTS, W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biology, v. 52, p. 99–115, 1990. DOI: 10.1007/BF02459570. DOI: https://doi.org/10.1016/S0092-8240(05)80006-0

MORÉ, J. J. The Levenberg-Marquardt Algorithm: Implementation and Theory. In: WATSON, G. A. (Ed.). Numerical Analysis. Lecture Notes in Mathematics, v. 630. Berlin: Springer, 1978. p. 105–116. DOI: 10.1007/BFb0067700. DOI: https://doi.org/10.1007/BFb0067700

PEIXOTO, L. O. M.; DE LIMA, B. A.; ALMEIDA, C. C.; FERNANDES, C. V. S.; CENTENO, J. A. S.; DE AZEVEDO, J. C. R. Data imputation of water quality parameters through feed-forward neural networks. Revista Brasileira de Recursos Hídricos, v. 28, 2023. DOI: 10.1590/2318-0331.282320220118. DOI: https://doi.org/10.1590/2318-0331.282320220118

SICHMAN, J. S. Inteligência Artificial e sociedade: avanços e riscos. Estudos Avançados, v. 35, n. 101, p. 37–49, 2021. DOI: 10.1590/S0103-4014.2021.35101.004. DOI: https://doi.org/10.1590/s0103-4014.2021.35101.004

SILVA, I. S. Inteligência artificial para avaliação da qualidade da água. 2019. 104 f. Dissertação (Mestrado em Recursos Hídricos) – Universidade Federal de Sergipe, São Cristóvão, SE, 2019.

VIDAL, C. M. S. Avaliação da microfiltração tangencial como alternativa de tratamento avançado de efluente gerado em sistema de tratamento de esgoto sanitário constituído de reator UASB (Upflow Anaerobic Sludge Blanket) seguido de tanque de aeração. 2006. Tese (Doutorado em Engenharia Hidráulica e Sanitária) – Escola de Engenharia de São Carlos, Universidade de São Paulo, São Carlos, SP, 2006. DOI: 10.11606/T.18.2006.tde-06112006-233334. DOI: https://doi.org/10.11606/T.18.2006.tde-06112006-233334

Published

2026-06-11

How to Cite

Filletti, Érica R., & Herrera Ribeiro Pereira, G. . (2026). Application of Artificial Intelligence in Evaluating the Crossflow Microfiltration Process for Treating Effluent Generated in a Sewage Treatment System. Engineering & Technology Scientific Journal, 1(1). https://doi.org/10.55977/etsjournal.v01i01.e026001

Issue

Vol. 1 No. 1 (2026): Engineering & Technology Scientific Journal

Section

Research Article
Copyright & Licensing

Copyright (c) 2026 Érica Regina Filletti, Giovana Herrera Ribeiro Pereira

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Creative Commons License

Engineering & Technology Scientific Journal is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Disclaimer: Articles published by Engineering & Technology Scientific Journal have been pre-viewed and authenticated by the Authors before publication. The Journal, Editor and the editorial board are not entitled or liable to either justify or responsible for inaccurate and misleading data if any. It is the sole responsibility of the Author concerned. Read our Plagiarism Policy and use of this site signifies your agreement to the Terms of Use.