DONATE

IAHR Document Library


« Back to Library Homepage « Book of Extended Abstracts of the 41st IAHR World Congress, ...

Cross-Plane Predction via Convolutional Neural Network (CNN) Model for Early Biofouling Detection in Swro Desalination Plant

Author(s): Henry J. Tanudjaja; Najat A. Amin; Adnan Qamar And Noreddine Ghaffour

Linked Author(s): Henry J. Tanudjaja, Najat A.Amin

Keywords: Seawater Reverse Osmosis Biofouling Machine Learning Intelligent Framework Neural Network

Abstract: The presence of biofouling in the SWRO desalination plant is inevitable and has a detrimental effect towards the filtration performance and energy consumption. Visualizing biofouling inside a membrane module is a challenging process, however, it could be feasible with the use of machine learning models. Herein, two deep convolutional neural network (CNN) models were developed for detecting biofouling and measuring its thickness. Both models took the membrane surface image as input and the first model (CNN-Class) predicted whether the membrane fouled or not, while the second model (CNN-Reg) predicted the thickness. CNN-Class model showed 80% accuracy and CNN-Reg reached a moderate difference in predicting the classification and thickness, respectively. These results showed the potential of these intelligent frameworks in visualizing the membrane biofouling and could be beneficial if implemented in the full-scale desalination plant for early decision making and preventive actions.

DOI:

Year: 2025

Copyright © 2025 International Association for Hydro-Environment Engineering and Research. All rights reserved. | Terms and Conditions