Artificial neural network simulation of combined humic substance coagulation and membrane filtration

被引:47
作者
Al-Abri, Mohammed [1 ]
Hilal, Nidal [1 ]
机构
[1] Univ Nottingham, Sch Chem & Environm Engn, Ctr Clean Water Technol, Nottingham NG7 2RD, England
关键词
membrane separation; artificial neural network; prediction;
D O I
10.1016/j.cej.2007.10.005
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Backpropagation artificial neural network (BPNN) was utilized to predict membrane performance. The network was used to predict and compare humic substance (HS) retention and membrane fouling with previously obtained experimental data. BPNN simulation results show high network reliability, if the network is implemented correctly. The difference between the predicted and experimental data was lower than 5%. Low number of training data input has been shown to hinder the learning process. A high number of training data input has lead to over-fitting or memorization of the training data set, reducing the networks predictability. The number of neurons in the hidden layers needs to be chosen carefully to obtain a reliable network. This paper shows that a lower number of neurons result in low reliability, while a higher number of neuron leads to data over-fitting. The best performance was obtained with 2-10 neurons for HS and heavy metals agglomeration and 5-15 neurons for HS coagulation with and without heavy metals. (C) 2007 Elsevier B.V. All rights reserved.
引用
收藏
页码:27 / 34
页数:8
相关论文
共 33 条
[1]   A Widrow-Hoff learning rule for a generalization of the linear auto-associator [J].
Abdi, H ;
Valentin, D ;
Edelman, B ;
OToole, AJ .
JOURNAL OF MATHEMATICAL PSYCHOLOGY, 1996, 40 (02) :175-182
[2]  
Assaad M, 2005, LECT NOTES COMPUT SC, V3697, P169
[3]   Site characterization by neuronets: An application to the landfill siting problem [J].
Basheer, IA ;
Reddi, LN ;
Najjar, YM .
GROUND WATER, 1996, 34 (04) :610-617
[4]  
Bowen WR, 1998, CHEM ENG SCI, V53, P3793
[5]  
Bowen WR, 2000, DESALINATION, V129, P147
[6]   Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network [J].
Ceylan, Rahime ;
Ozbay, Yuksel .
EXPERT SYSTEMS WITH APPLICATIONS, 2007, 33 (02) :286-295
[7]   Prediction of permeate flux decline in crossflow membrane filtration of colloidal suspension: a radial basis function neural network approach [J].
Chen, Huaiqun ;
Kim, Albert S. .
DESALINATION, 2006, 192 (1-3) :415-428
[8]   Generalized regression neural network in modelling river sediment yield [J].
Cigizoglu, HK ;
Alp, M .
ADVANCES IN ENGINEERING SOFTWARE, 2006, 37 (02) :63-68
[9]   Reduction and control of flux decline in cross-flow membrane processes modeled by artificial neural networks [J].
Curcio, Stefano ;
Calabro, Vincenza ;
Iorio, Gabriele .
JOURNAL OF MEMBRANE SCIENCE, 2006, 286 (1-2) :125-132
[10]   Neural networks simulation of the filtration of sodium chloride and magnesium chloride solutions using nanofiltration membranes [J].
Darwish, N. A. ;
Hilal, N. ;
Al-Zoubi, H. ;
Mohammad, A. W. .
CHEMICAL ENGINEERING RESEARCH & DESIGN, 2007, 85 (A4) :417-430