Membrane permeate flux and rejection factor prediction using intelligent systems

Sargolzaei, Javad; Asl, M. Haghighi; Moghaddam, Amin Hedayati

doi:10.1016/j.desal.2011.08.041

Cited by 28 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fuzzy logic system is used as a powerful tool to predict future values of the membrane permeation flux based on precise data collection of the experiments in the module [14].…”

Section: Resultsmentioning

confidence: 99%

“…The mathematical models are complex, expensive and require a detailed knowledge of the process, while the modeling techniques based on direct analysis of the experimental data, such as artificial neural networks [11][12][13][14] and fuzzy modeling [14][15][16][17], appear to be a good alternative to the model based on phenomenological hypotheses [16]. Fuzzy logic inference systems and artificial neural networks are capable of modeling highly complex and non-linear processes, but the main limitation of these types of modeling is that they can only be utilized for a specific experiment [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fuzzy Modeling of the Permeate Flux Decline during Microfiltration of Starch Suspensions

et al. 2014

View full text Add to dashboard Cite

Flux declines versus time during cross-flow microfiltration of wheat starch suspensions were modeled using fuzzy logic systems under different conditions of transmembrane pressure, flow rate, and suspension concentration. Fuzzy modeling is one of the most efficient methods for empirical modeling, especially for non-linear systems, and does not require any prior knowledge about the process. The influence of the process parameters on the dynamic behavior of the permeate flux was determined by comparing the permeate flux decline versus the volume curves, considering a constant value of the volumetric concentration factor during batch cross-flow filtration. At the transient stages of the filtration process, the permeate flux was shown to be strongly dependent on all process parameters, within the examined range.

show abstract

“…The fuzzy logic system is used as a powerful tool to predict future values of the membrane permeation flux based on precise data collection of the experiments in the module [14].…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fuzzy Modeling of the Permeate Flux Decline during Microfiltration of Starch Suspensions

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Testing data set is used to test the trained network for unseen patterns (The results of which are known to the researcher but not used in the training procedure). The network generalizes well when it sensibly interpolates these new patterns [9].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Sargolzaei et al [9] showed the capability of ANN model to predict the starch removal performance using a hydrophilic polyethersulfone. Aydiner et al [10] compared performance of ANN and Koltuniewicz's method in modeling of flux decline rate of crossflow microfiltration of a mixture in presence of phosphate and fly ash.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence vs. classical approaches: a new look at the prediction of flux decline in wastewater treatment

Meighani

Dehghani

Rekabdar

et al. 2013

Desalination and Water Treatment

View full text Add to dashboard Cite

A B S T R A C TThis study compares the performance of three different approaches to modeling namely the classical pore-blocking models, artificial neural networks (ANN) and the novel genetic programming (GP) approach. Among the available models proposed by Hermia, standard poreblocking and cake filtration models were opted because of their better fitness with experimental measurements. A feedforward backpropagation network using Bayesian Regulation as well as Levenberg-Marquardt training methods was developed based on the experimental results. Network inputs include the controlling parameters of permeate flux namely: temperature, transmembrane pressure, crossflow velocity, pH, and filtration time. The architecture and internal parameters of the network have substantial effect on the prediction performance of the ANN. Hidden layers and neuron numbers were regulated using trial-and-error approach. The individual program proposed by GP, which has satisfied the required fitness value after 500 generations, had a depth of 10 among a population of 700 individuals. Relative error with respect to experimental results was used to compare the aforementioned models. It was found that ANN outperformed pore-blocking and GP models. The GP-based model had an acceptable coincidence with the experimental data and its ability to correlate the input and target variables by a mathematical relation showed the high potentiality of GP as a modeling tool.

show abstract

“…The number of experiments and in turn the related parameters like costs, designs, manufacturing etc. can be reduced [19] .…”

Section: Introductionmentioning

confidence: 97%

Effect of Different Parameters on WEPS Production and Thermal Behavior Prediction Using Artificial Neural Network (ANN)

Moghaddam

Sargolzaei

Asl

et al. 2012

Polymer-Plastics Technology and Engineering

Self Cite

View full text Add to dashboard Cite

The objective of this study is to investigate Differential Thermal Analysis (DTA) and thermal behavior prediction of Water Expandable Polystyrene (WEPS) using Artificial Neural Network (ANN). In this procedure spherical PS beads containing small water droplets are applied. These droplets are capable to expand the PS matrix while heating above the Tg. Also, the effect of Sodium Chloride (NaCl) on water distribution into Water Expandable Polystyrene (WEPS) beads would be investigated. The ANN model was developed to predict DTA data in different temperatures. The results reveal that there is a good agreement between predicted thermal behavior and the actual values.

show abstract

Membrane permeate flux and rejection factor prediction using intelligent systems

Cited by 28 publications

References 24 publications

Fuzzy Modeling of the Permeate Flux Decline during Microfiltration of Starch Suspensions

Fuzzy Modeling of the Permeate Flux Decline during Microfiltration of Starch Suspensions

Artificial intelligence vs. classical approaches: a new look at the prediction of flux decline in wastewater treatment

Effect of Different Parameters on WEPS Production and Thermal Behavior Prediction Using Artificial Neural Network (ANN)

Contact Info

Product

Resources

About