Comparison of a deterministic and a data driven model to describe MBR fouling

Dalmau, Montserrat; Atanasova, Nataša; Gabarrón, S.; Rodríguez-Roda, Ignasi; Comas, Joaquím

doi:10.1016/j.cej.2014.09.003

Cited by 51 publications

(20 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Same as 5 shows the structure of tree model to predict the relative feed pressure. The input parameter at the top of the tree structure was the most particular [24]. In this study, temperature was the most influential parameter affecting the output in the M5P tree mode.…”

Section: Tm Model Set-up Calibration and Validationmentioning

confidence: 68%

See 1 more Smart Citation

Analysis of long-term performance of full-scale reverse osmosis desalination plant using artificial neural network and tree model

Choi

Lee

Shin

et al. 2019

Environmental Engineering Research

View full text Add to dashboard Cite

The reverse osmosis (RO) technology is currently the leading desalination method. However, until recently, application of RO technology on a large scale has been primarily limited by membrane fouling. The mechanism of fouling is complex, which is not well understood in full-scale plants. Although many studies about modeling and prediction of fouling have been done, in most cases, the experimental data set of lab or pilot scale systems, which may not show fouling characteristics well in full-scale systems were used. In this study, both artificial neural network (ANN) model and tree model (TM) was evaluated to analyze long-term performance of full scale reverse osmosis desalination plant. The results of application of the ANN and TM indicated high correlation coefficients between the measured and simulated output variables. However, it is not easy to use ANN for the full scale plant operation because the final model is not expressed as a form of mathematical functions. TM has advantages over ANN because the model can be obtained as forms of simple function and it showed reasonably high <i>R</i><sup>2</sup>. Therefore, TM is shown to be more adequate than ANN for developing models in which the full-scale RO plant data is considered as an input.

show abstract

Section: Tm Model Set-up Calibration and Validationmentioning

confidence: 68%

“…For example, LM 1 for prediction of relative feed pressure is valid when the relative temperature is below 1.9 and the relative feed flowrate is under 0.98. The LM equations of tree model can notify the most influential parameters because each parameter is multiplied by a weighting factor [24].…”

Section: Tm Model Set-up Calibration and Validationmentioning

confidence: 99%

Analysis of long-term performance of full-scale reverse osmosis desalination plant using artificial neural network and tree model

Choi

Lee

Shin

et al. 2019

Environmental Engineering Research

View full text Add to dashboard Cite

show abstract

“…Such a mechanistic approach could hardly be applied in a straightforward and simple manner, when there is a lack of fundamental knowledge of the system behavior (e.g. fouling development) [13].…”

Section: Introductionmentioning

confidence: 99%

Prediction of reverse electrodialysis performance by inclusion of 2D fluorescence spectroscopy data into multivariate statistical models

Pawlowski

Galinha

Crespo

et al. 2015

Separation and Purification Technology

View full text Add to dashboard Cite

“…However, the complexity of the fouling phenomenon, the lack of agreement on a specific fouling indicator, and the impact of biological processes increase the difficulty of modeling the filtration process. Thus, integrated (hybrid) models have been proposed for a comprehensive description of the MBR process, which combine biomass kinetic models with membrane fouling models [16][17][18][19][20][21][22][23]. The latter enable better modeling of the involved processes as they take into account not only the physical, but the biological phenomena, and the interactions between them [17].…”

Section: Introductionmentioning

confidence: 99%

Modeling of Wastewater Treatment Processes in Membrane Bioreactors Compared to Conventional Activated Sludge Systems

et al. 2019

View full text Add to dashboard Cite

Membrane techniques constitute an interesting alternative to conventional activated sludge systems (CAS). In membrane bioreactors (MBR), the biomass separated on membranes is retained independently of sludge sedimentation properties. As a consequence, a high biomass concentration as well as low food to microorganisms ratio can be obtained. Moreover, the development of a characteristic activated sludge population is stimulated by the specific conditions prevailing in MBRs. In the study, the operation and treatment efficiency of the MBR and CAS processes were examined and compared. Simulation was performed with the use of GPS-X software. The effluent quality obtained for the MBR system was either better or comparable to that of CAS. The most significant difference concerned the elimination of total suspended solids, which amounted to 99.8% in the MBR. Regarding nutrients, a low concentration of total phosphorus in the effluent from CAS and MBR was obtained (0.67 gP m−3 and 0.50 gP m−3, respectively). Greater differences were achieved in the case of total nitrogen. Although almost complete nitrification took place in both systems, a lower concentration of nitrate in the effluent from MBR in comparison to CAS, i.e., 11.2 gN m−3 and 14.1 gN m−3, respectively, allowed us to obtain a higher removal of total nitrogen (80.8% and 76.1%, respectively).

show abstract

Comparison of a deterministic and a data driven model to describe MBR fouling

Cited by 51 publications

References 35 publications

Analysis of long-term performance of full-scale reverse osmosis desalination plant using artificial neural network and tree model

Analysis of long-term performance of full-scale reverse osmosis desalination plant using artificial neural network and tree model

Prediction of reverse electrodialysis performance by inclusion of 2D fluorescence spectroscopy data into multivariate statistical models

Modeling of Wastewater Treatment Processes in Membrane Bioreactors Compared to Conventional Activated Sludge Systems

Contact Info

Product

Resources

About