A hybrid modelling approach for reverse osmosis processes including fouling
- Author
- Dorien Gaublomme (UGent) , Ward Quaghebeur (UGent) , Anse Van Droogenbroeck, Marjolein Vanoppen (UGent) , Bart De Gusseme (UGent) , Arne Verliefde (UGent) , Ingmar Nopens (UGent) and Elena Torfs (UGent)
- Organization
- Project
- Abstract
- A novel hybrid modelling approach, combining the strengths of a mechanistic reverse osmosis (RO) model and a data-driven fouling model, is developed on a unique long-term dataset from a full-scale RO installation to predict its performance. The mechanistic solution-diffusion model describes well understood phenomena in RO such as concentration polarisation, osmotic pressure and solutes transport throughout the membrane. This solution -diffusion model is combined with a data-driven model to cover the gaps in knowledge related to fouling phe-nomena. Several fouling models are tested to predict the membrane resistance over time and a thorough analysis of important input features was performed. A non-linear recurrent neural network with long short-term memory
- Keywords
- Water treatment, Recurrent neural networks, ARIMAX, Solution -diffusion model, Full-scale, WATER-TREATMENT, ARTIFICIAL-INTELLIGENCE, NEURAL NETWORKS, MEMBRANE, ULTRAFILTRATION, NANOFILTRATION, PREDICTION, EFFICIENCY, REJECTION, TOOL
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 7.73 MB
-
Preprint a hybrid modeling approach.pdf
- full text
- |
- open access
- |
- |
- 9.39 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01H8BH8GMBJQ4W31AWX75490QX
- MLA
- Gaublomme, Dorien, et al. “A Hybrid Modelling Approach for Reverse Osmosis Processes Including Fouling.” DESALINATION, vol. 564, 2023, doi:10.1016/j.desal.2023.116756.
- APA
- Gaublomme, D., Quaghebeur, W., Van Droogenbroeck, A., Vanoppen, M., De Gusseme, B., Verliefde, A., … Torfs, E. (2023). A hybrid modelling approach for reverse osmosis processes including fouling. DESALINATION, 564. https://doi.org/10.1016/j.desal.2023.116756
- Chicago author-date
- Gaublomme, Dorien, Ward Quaghebeur, Anse Van Droogenbroeck, Marjolein Vanoppen, Bart De Gusseme, Arne Verliefde, Ingmar Nopens, and Elena Torfs. 2023. “A Hybrid Modelling Approach for Reverse Osmosis Processes Including Fouling.” DESALINATION 564. https://doi.org/10.1016/j.desal.2023.116756.
- Chicago author-date (all authors)
- Gaublomme, Dorien, Ward Quaghebeur, Anse Van Droogenbroeck, Marjolein Vanoppen, Bart De Gusseme, Arne Verliefde, Ingmar Nopens, and Elena Torfs. 2023. “A Hybrid Modelling Approach for Reverse Osmosis Processes Including Fouling.” DESALINATION 564. doi:10.1016/j.desal.2023.116756.
- Vancouver
- 1.Gaublomme D, Quaghebeur W, Van Droogenbroeck A, Vanoppen M, De Gusseme B, Verliefde A, et al. A hybrid modelling approach for reverse osmosis processes including fouling. DESALINATION. 2023;564.
- IEEE
- [1]D. Gaublomme et al., “A hybrid modelling approach for reverse osmosis processes including fouling,” DESALINATION, vol. 564, 2023.
@article{01H8BH8GMBJQ4W31AWX75490QX,
abstract = {{A novel hybrid modelling approach, combining the strengths of a mechanistic reverse osmosis (RO) model and a data-driven fouling model, is developed on a unique long-term dataset from a full-scale RO installation to predict its performance. The mechanistic solution-diffusion model describes well understood phenomena in RO such as concentration polarisation, osmotic pressure and solutes transport throughout the membrane. This solution -diffusion model is combined with a data-driven model to cover the gaps in knowledge related to fouling phe-nomena. Several fouling models are tested to predict the membrane resistance over time and a thorough analysis of important input features was performed. A non-linear recurrent neural network with long short-term memory}},
articleno = {{116756}},
author = {{Gaublomme, Dorien and Quaghebeur, Ward and Van Droogenbroeck, Anse and Vanoppen, Marjolein and De Gusseme, Bart and Verliefde, Arne and Nopens, Ingmar and Torfs, Elena}},
issn = {{0011-9164}},
journal = {{DESALINATION}},
keywords = {{Water treatment,Recurrent neural networks,ARIMAX,Solution -diffusion model,Full-scale,WATER-TREATMENT,ARTIFICIAL-INTELLIGENCE,NEURAL NETWORKS,MEMBRANE,ULTRAFILTRATION,NANOFILTRATION,PREDICTION,EFFICIENCY,REJECTION,TOOL}},
language = {{eng}},
pages = {{16}},
title = {{A hybrid modelling approach for reverse osmosis processes including fouling}},
url = {{http://doi.org/10.1016/j.desal.2023.116756}},
volume = {{564}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: