Modeling of forward osmosis process using artificial neural networks (ANN) to predict the permeate flux

Jawad, Jasir; Hawari, Alaa H.; Zaidi, Syed Javaid

doi:10.1016/j.desal.2020.114427

Cited by 86 publications

(20 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…R 2 values for FFA, MC, and a w model were 0.9241, 0.9058, and 0.9311, respectively. This represents the variability of the parameters by the models, which indicated that the predicted values obtained by the quadratic polynomial equations had a strong correlation with the actual experimental values of Pearson's correlation coefficients (Jawad, et al, 2020). These models were well adapted to the response and were effective to predict the FFA, MC, and a w of the SRB samples.…”

Section: Resultsmentioning

confidence: 95%

“…The prediction model was validated and presented in Table 5. The criterion for fitting the efficiency data of FFA, MC, and a w model is calculated as the % E difference between the experimental and predicted data by Equation (2) (Jawad, et al, 2020). The FFA, MC, and a w values predicted by the RSM model are shown in Table 5 and % E of each variable was 12.62, 7.37, and 8.90, respectively.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of rice bran stabilization by infrared‐vacuum process and storage stability

Kreungngern

Kongbangkerd

Ruttarattanamongkol

2021

J Food Process Engineering

View full text Add to dashboard Cite

Hydrolytic rancidity seriously reduces the quality and limits the utilization of rice bran (RB) in foods. Thus, stabilization of RB has become of great interest to producers. This study proposes a new stabilization technique using infrared heat in combination with a vacuum (IR‐VC) to inhibit free fatty acids (FFA) and microbial growth as well as to preserve the phytochemical compounds in the RB. Optimization of the IR‐VC process was performed by Response Surface Methodology (RSM) and Central Composite Design (CCD) and found to be 999 W of infrared power, 650 mmHg of vacuum strength, and 562 s of treatment time. This level of IR‐VC treatment successfully reduced FA hydrolysis while still preserving the bran's beneficial components such as tocols, and essential fatty acids. The improved shelf life of thus stabilized rice bran (SRB) was 130 days (30°C), compared to only 35 days for the fresh rice bran. Slow rate increase in FFA was found in SRB over 8 weeks of storage at 35°C in a range from 1.50% to 3.24% with effective microbial growth control (<1 × 104 CFU/g TPC). Nutritional values, tocols and oryzanol in the SRB were well preserved with approximately four times longer shelf life than fresh rice bran. Practical applications The rice bran stabilization process by IR‐VC was optimized by RSM. IR‐VC process effectively inhibited lipase activity in the fresh rice bran by lowering the FFA to <5% suitable for oil extraction and consumption. IR‐VC process enabled the deactivation of undesired chemical changes in the rice bran while still maintaining nutrients and biochemicals such as tocols and oryzanol. The shelf life of stabilized rice bran was extended to ~4 months with acceptable qualities. Further development of a pilot‐scale, continuous stabilization process of rice bran using IR‐VC is carried out to meet the demand of rice bran and RBO manufacturers.

show abstract

Section: Resultsmentioning

confidence: 95%

Section: Resultsmentioning

confidence: 99%

Optimization of rice bran stabilization by infrared‐vacuum process and storage stability

Kreungngern

Kongbangkerd

Ruttarattanamongkol

2021

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…In our previous study, an ANN model was developed with nine input variables to predict the membrane flux, but the weights associated with the network were not analyzed for their contribution towards the output [ 20 ]. In this paper, the relative importance of each input variable was assessed on the ANN model output (membrane flux) using a sensitivity analysis approach that employs the partitioning of the weights.…”

Section: Resultsmentioning

confidence: 99%

“…The study also evaluated the importance of the parameters using analysis of variance (ANOVA) that could affect the quality characteristics of FO. In our previous study, an ANN model for a generalized prediction of membrane flux for lab-scale FO desalination [ 20 ]. The model was compared to multiple linear regression and published mathematical models, which showed satisfactory performance.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Sensitivity Analysis of the Forward Osmosis Process to Predict Membrane Flux Using a Novel Combination of Neural Network and Response Surface Methodology Techniques

2021

Self Cite

View full text Add to dashboard Cite

The forward osmosis (FO) process is an emerging technology that has been considered as an alternative to desalination due to its low energy consumption and less severe reversible fouling. Artificial neural networks (ANNs) and response surface methodology (RSM) have become popular for the modeling and optimization of membrane processes. RSM requires the data on a specific experimental design whereas ANN does not. In this work, a combined ANN-RSM approach is presented to predict and optimize the membrane flux for the FO process. The ANN model, developed based on an experimental study, is used to predict the membrane flux for the experimental design in order to create the RSM model for optimization. A Box–Behnken design (BBD) is used to develop a response surface design where the ANN model evaluates the responses. The input variables were osmotic pressure difference, feed solution (FS) velocity, draw solution (DS) velocity, FS temperature, and DS temperature. The R2 obtained for the developed ANN and RSM model are 0.98036 and 0.9408, respectively. The weights of the ANN model and the response surface plots were used to optimize and study the influence of the operating conditions on the membrane flux.

show abstract

“…A literature review found that research on predicting membrane fouling in forward osmosis membrane filtration process by the ANN is rarely exercised. Jawada et al [ 54 ] constructed a multilayer neural network model to predict the permeation flux of forward osmosis. The model studied the influence of the number of neurons and hidden layers on the performance of the neural network, which is helpful in optimizing the development of the network structure.…”

Section: Methods Based On Artificial Neural Network To Predict Membrane Foulingmentioning

confidence: 99%

Recent Advances in the Prediction of Fouling in Membrane Bioreactors

Shi

Wang

et al. 2021

Membranes

View full text Add to dashboard Cite

Compared to the traditional activated sludge process, the membrane bioreactor (MBR) has several advantages such as the production of high-quality effluent, generation of low excess sludge, smaller footprint requirements, and ease of automatic control of processes. The MBR has a broader prospect of its applications in wastewater treatment and reuse. However, membrane fouling is the biggest obstacle for its wider application. This paper reviews the techniques available to predict fouling in MBR, discusses the problems associated with predicting fouling status using artificial neural networks and mathematical models, summarizes the current state of fouling prediction techniques, and looks into the trends in their development.

show abstract

Modeling of forward osmosis process using artificial neural networks (ANN) to predict the permeate flux

Cited by 86 publications

References 40 publications

Optimization of rice bran stabilization by infrared‐vacuum process and storage stability

Optimization of rice bran stabilization by infrared‐vacuum process and storage stability

Modeling and Sensitivity Analysis of the Forward Osmosis Process to Predict Membrane Flux Using a Novel Combination of Neural Network and Response Surface Methodology Techniques

Recent Advances in the Prediction of Fouling in Membrane Bioreactors

Contact Info

Product

Resources

About