Optimization of artificial neural network topology for membrane bioreactor filtration using response surface methodology

The optimization of artificial neural networks (ANN) topology for predicting permeate flux of palm oil mill effluent (POME) in membrane bioreactor (MBR) filtration has been investigated using response surface methodology (RSM). A radial basis function neural network (RBFNN) model, trained by gradient descent with momentum (GDM) algorithms was developed to correlate output (permeate flux) to the four exogenous input variables (airflow rate, transmembrane pressure, permeate pump and aeration pump). A second-order polynomial model was developed from training results for natural log mean square error of 50 developed ANNs to generate 3D response surfaces. The optimum ANN topology had minimum ln MSE when the number of hidden neurons, spread, momentum coefficient, learning rate and number of epochs were 16, 1.4, 0.28, 0.3 and 1852, respectively. The MSE and regression coeffcient of the ANN model were determined as 0.0022 and 0.9906 for training, 0.0052 and 0.9839 for testing and 0.0217 and 0.9707 for validation data sets. These results confirmed that combining RSM and ANN was precise for predicting permeates flux of POME on MBR system. This development may have significant potential to improve model accuracy and reduce computational time.

[1]  Mohd Herwan Sulaiman,et al.  Artificial neural network flood prediction for sungai isap residence , 2016, 2016 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS).

[2]  Fatimah Ibrahim,et al.  A novel dengue fever (DF) and dengue haemorrhagic fever (DHF) analysis using artificial neural network (ANN) , 2005, Comput. Methods Programs Biomed..

[3]  Zaini Ujang,et al.  Membrane fouling resistance in a hybrid membrane bioreactor for palm oil mill effluent and resource recovery , 2008 .

[4]  T. Janus.  Modelling and Simulation of Membrane Bioreactors for Wastewater Treatment , 2013 .

[5]  Abdolhamid Salahi,et al.  Experimental investigation, modeling and optimization of membrane separation using artificial neural network and multi-objective optimization using genetic algorithm , 2013 .

[6]  A. Basile,et al.  Membranes for industrial microfiltration and ultrafiltration , 2011 .

[7]  Shafishuhaza Sahlan,et al.  Modeling of submerged membrane bioreactor filtration process using NARX-ANFIS model , 2015, 2015 10th Asian Control Conference (ASCC).

[8]  Javad Khazaei,et al.  Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by using artificial neural networks , 2007 .

[9]  Fangang Meng,et al.  Membrane Bioreactors for Industrial Wastewater Treatment: A Critical Review , 2012 .

[10]  S Judd,et al.  Fouling control in submerged membrane bioreactors. , 2005, Water science and technology : a journal of the International Association on Water Pollution Research.

[11]  Mahmoud Omid,et al.  Prediction of red plum juice permeate flux during membrane processing with ANN optimized using RSM , 2014 .

[12]  Abdullah Al Mamun,et al.  Application of response surface methodology (RSM) for optimization of color removal from POME by granular activated carbon , 2015, International Journal of Environmental Science and Technology.

[13]  Mortaza Aghbashlo,et al.  Optimization of an Artificial Neural Network Topology for Predicting Drying Kinetics of Carrot Cubes Using Combined Response Surface and Genetic Algorithm , 2011 .

[14]  K. Chia,et al.  Neural network and principal component regression in non-destructive soluble solids content assessment: a comparison , 2012, Journal of Zhejiang University SCIENCE B.

[15]  S. Ibrahim,et al.  Amylose content calibration model for the three types of selected rice grains using visible shortwave near infrared spectroscopy , 2015 .

[16]  Mohd Nasir Taib,et al.  Classification of EEG Spectrogram Image with ANN Approach for Brainwave Balancing Application , 2020 .

[17]  N. Abdurahman,et al.  An Integrated Ultrasonic Membrane An aerobic System (IUMAS) for Palm Oil Mill Effluent (POME) Treatment , 2017 .

[18]  Shafishuhaza Sahlan,et al.  Permeate Flux Measurement and Prediction of Submerged Membrane Bioreactor Filtration Process Using Intelligent Techniques , 2015 .

[19]  Wong Pui Wah,et al.  Pre-treatment and membrane ultrafiltration using treated palm oil mill effluent ( POME ) , 2003 .

[20]  R. Padma Sree,et al.  Artificial Neural Network and Response Surface Methodology Approach for Modeling and Optimization of Chromium (VI) Adsorption from Waste Water using Ragi Husk Powder , 2013 .

[21]  Stefano Curcio,et al.  Reduction and control of flux decline in cross-flow membrane processes modeled by artificial neural networks and hybrid systems , 2009 .

[22]  S. Abdullah,et al.  Investigation of three pre-treatment methods prior to nanofiltration membrane for palm oil mill effluent treatment , 2015 .

[23]  N. Azmi,et al.  Wastewater Treatment of Palm Oil Mill Effluent (POME) by Ultrafiltration Membrane Separation Technique Coupled with Adsorption Treatment as Pre-treatment☆ , 2014 .

[24]  Teow Yeit Haan,et al.  Fouling assessment of tertiary palm oil mill effluent (Pome) membrane treatment for water reclamation , 2018 .