Neural network prediction of fluidized bed bioreactor performance for sulfide oxidation

Sulfide oxidation rate of a fluidized bed bioreactor was predicted using ANN, with upflow velocity, hydraulic retention time, reactor operation time and pH given as input. The reactor was fed with 100mg/L synthetic sulfide wastewater after biofilm formation on nylon support particles. Feedforward neural network model was prepared using 81 data sets, of which 63 were used for training and 18 for testing in a three-way cross validation. Prediction performance of the network was evaluated by calculating the percent error of each data set and mean square error for test data set in three partitions. The mean square error for test data set was 5.55, 4.08 and 2.30 for partition 1, partition 2 and partition 3, respectively. The predicted sulfide oxidation values correlated with the experimental values and a correlation coefficient of 0.96, 0.97 and 0.98 was obtained for partition 1, partition 2 and partition 3, respectively.

[1]  B. Capdeville,et al.  APPLICATION OF AEROBIC BIOFILM GROWTH IN A THREE-PHASE FLUIDIZED- BED REACTOR FOR BIOLOGICAL WASTEWATER TREATMENT , 1988 .

[2]  L. Fan,et al.  Hydrodynamics of a three-phase fluidized bed containing low-density particles , 1989 .

[3]  J. Bandy,et al.  A comparison of media types in acetate fed expanded-bed anaerobic reactors , 1990 .

[4]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[5]  C. Buisman,et al.  Kinetic parameters of a mixed culture oxidizing sulfide and sulfur with oxygen , 1991, Biotechnology and bioengineering.

[6]  T. Sreekrishnan,et al.  Effect of operating variables on biofilm formation and performance of an anaerobic fluidized‐bed bioreactor , 1991, Biotechnology and bioengineering.

[7]  R. Tichý,et al.  Possibilities for using biologically-produced sulphur for cultivation of Thiobacilli with respect to bioleaching processes , 1994 .

[8]  G. L. Sant'anna,et al.  The effect of air superficial velocity on biofilm accumulation in a three-phase fluidized-bed reactor , 1995 .

[9]  Holger R. Maier,et al.  Understanding the behaviour and optimising the performance of back-propagation neural networks: an empirical study , 1998 .

[10]  Schreyer,et al.  Effects of stratification in a fluidized bed bioreactor during treatment of metalworking wastewater , 1999, Biotechnology and bioengineering.

[11]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[12]  Daniel W Smith,et al.  A neural network model to predict the wastewater inflow incorporating rainfall events. , 2002, Water research.

[13]  R. Bautista,et al.  Application of a low density support material as an alternative to prevent clogging in a three-phase fluidized-bed reactor. , 2003, Environmental technology.

[14]  Maged M. Hamed,et al.  Prediction of wastewater treatment plant performance using artificial neural networks , 2004, Environ. Model. Softw..

[15]  J. Kuenen.  Colourless sulfur bacteria and their role in the sulfur cycle , 1975, Plant and Soil.

[16]  Rudolf Braun,et al.  Prediction of trace compounds in biogas from anaerobic digestion using the MATLAB Neural Network Toolbox , 2005, Environ. Model. Softw..

[17]  P. Zheng,et al.  Prediction of anoxic sulfide biooxidation under various HRTs using artificial neural networks. , 2007, Biomedical and environmental sciences : BES.

[18]  D. Mowla,et al.  Theoretical and experimental investigation of biodegradation of hydrocarbon polluted water in a three phase fluidized-bed bioreactor with PVC biofilm support , 2007 .

[19]  M. Rajasimman,et al.  Aerobic digestion of starch wastewater in a fluidized bed bioreactor with low density biomass support. , 2007, Journal of hazardous materials.

[20]  G. Sekaran,et al.  Anaerobic tapered fluidized bed reactor for starch wastewater treatment and modeling using multilayer perceptron neural network. , 2007, Journal of environmental sciences.

[21]  J. Puhakka,et al.  Neural network prediction of thermophilic (65°C) sulfidogenic fluidized‐bed reactor performance for the treatment of metal‐containing wastewater , 2007, Biotechnology and bioengineering.

[22]  K. Arun Kumar,et al.  Simulation of biodegradation process in a fluidized bed bioreactor using genetic algorithm trained feedforward neural network , 2009 .

[23]  Duu-Jong Lee,et al.  Modeling denitrifying sulfide removal process using artificial neural networks. , 2009, Journal of hazardous materials.

[24]  B. Ayati,et al.  Prediction of moving bed biofilm reactor (MBBR) performance for the treatment of aniline using artificial neural networks (ANN). , 2010, Journal of hazardous materials.

[25]  Junfei Qiao,et al.  Neural network predictive optimal control for wastewater treatment , 2010, 2010 International Conference on Intelligent Control and Information Processing.

[26]  A. Dey,et al.  Sulfide oxidation in fluidized bed bioreactor using nylon support material. , 2012, Journal of environmental sciences.