Artificial neural network modeling of a multiphase photodegradation system

Abstract Photodegradation of spent Bayer liquor was carried out in an 18 l pilot scale photoreactor. The experimental data indicated that the average reaction rate was a complex nonlinear function of various process variables, such as lamp power, catalyst loading, initial solution pH, liquid batch time, and total organic carbon (TOC) concentration. The experimental data were modeled using feed forward artificial neural networks (ANN). The networks were trained with 350 sets of input–output patterns using backpropagation algorithm. Out of several configurations, a three-layered network with eight-neurons in its hidden layer yielded optimal results with respect to data validation. The optimal model gave excellent predictions with a correlation coefficient of 0.9955.

[1]  Y. Inel,et al.  Photocatalytic degradation of malonic acid in aqueous suspensions of titanium dioxide: an initial kinetic investigation of CO2 photogeneration , 1996 .

[2]  N. Serpone,et al.  Photocatalysis: Fundamentals and Applications , 1989 .

[3]  J. Michalopoulos,et al.  Modelling of an Industrial Fluid Catalytic Cracking Unit Using Neural Networks , 2001 .

[4]  D. Himmelblau.  Applications of artificial neural networks in chemical engineering , 2000 .

[5]  Nick Serpone,et al.  Photocatalyzed destruction of water contaminants , 1991 .

[6]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[7]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[8]  Alberto E. Cassano,et al.  Photoreactor Analysis and Design: Fundamentals and Applications , 1995 .

[9]  Vishnu Pareek,et al.  Continuous Process for Photodegradation of Industrial Bayer Liquor , 2001 .

[10]  P. Reilly,et al.  Non-linear parameter estimation for a dynamic model in photocatalytic reaction engineering , 2000 .

[11]  X. Doménech,et al.  Redox photodegradation of 2,4-dichlorophenoxyacetic acid over TiO2 , 1995 .

[12]  A. Adesina,et al.  Continuous flow bubble column reactor for the photocatalytic causticisation of sodium oxalate , 1999 .

[13]  Ali Elkamel,et al.  Measurement and prediction of ozone levels around a heavily industrialized area: a neural network approach , 2001 .

[14]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[15]  Andrew Mills,et al.  An overview of semiconductor photocatalysis , 1997 .

[16]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.