Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks.

Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m2h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R2 - 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery efficiency.

Parametric analysis of lignocellulosic ultrafiltration in lab scale cross flow module using pore blocking and artificial neural network model.

In this study, fouling mechanism and modelling analysis of synthetic lignocellulose biomass and agricultural palm oil effluent was studied using polyethersulfone (PES) ultrafiltration (UF) 10 kDa membrane. The impact of process variables (transmembrane pressure (TMP), pH and concentration of feed solution) on lignocellulosic flux was analysed using pore blocking model. The feasible approaches on utilising deep learning artificial neural network (ANN) to predict smaller flux datasets are studied. Among the input variables, pH of lignin feed solution has significant control towards flux and lignin rejection coefficient for both lignin and lignocellulosic solution. Alteration in the structure of lignin at different pH conditions contributed in the improvement of lignin rejection coefficient to 0.98 at the feed pH of 9. A maximum steady state flux of 52.03 L/m2h was observed at the lower lignin concentration (0.25 g/L), TMP of 200 kPa and feed pH of 3. At high TMP and concentration, lignin rejection decreased due to enhancement of feed concentration on membrane surface. The mechanistic model exhibited that cake layer phenomena was dominant in both lignin and lignocellulosic solution. The proposed ANN model showed good correlation (R2-1.00) with experimental non-linear flux dynamic data of both lignin and synthetic lignocellulosic solution. In ANN analysis, activation function, algorithm and neuron effect have significant effect in design of accurate model for prediction of small flux datasets. Aerobically-treated palm oil mill filtration analysis also showed that cake layer phenomenon was dominant. A water recovery of 82 % was achieved even at low TMP under short durations.