Artificial neural network based model for evaluating performance of immobilized cell biofilter

Artificial neural networks (ANNs) are powerful data driven modelling tools which has the potential to approximate and interpret complex input/output relationships based on the given sets of data matrix. In this paper, a predictive computerised approach has been proposed to predict the performance of an immobilized cell biofilter treating NH3 vapours in terms of its removal efficiency (RE) and elimination capacity (EC). The input parameters to the ANN model were inlet concentration, loading rate, flow rate and pressure drop, while the output parameters were RE and EC respectively. The data set was divided into two parts, training matrix consisting of 51 data points, while the test matrix had 16 data points representing each parameter considered in this study. Earlier, experiments from continuous operation in the biofilter showed removal efficiencies from 60 to 100% at inlet loading rates varying between 0.5 to 5.5 g NH3/m3.h. The internal network parameters of the ANN model during simulation was selected using the 2k factorial design and the best network topology for the model was thus estimated. The predictions were evaluated based on their determination coefficient values (R2). The results showed that a multilayer network (4-4-2) with a back propagation algorithm was able to predict biofilter performance effectively with R2 values of 0.9825 and 0.9982. The proposed ANN model for biofilter operation could be used as a potential alternative for knowledge based models through proper training and testing of the state variables.

[1]  Yaomin Jin,et al.  Performance optimization of the fungal biodegradation of α-pinene in gas-phase biofilter , 2006 .

[2]  Holger R. Maier,et al.  The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study , 1998 .

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

[4]  B. C. Baltzis,et al.  Biofiltration of methanol vapor , 1993, Biotechnology and bioengineering.

[5]  G. Ibarra-Berastegi,et al.  Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide , 2006, Bioprocess and biosystems engineering.

[6]  C. Tseng,et al.  Operation optimization of Thiobacillus thioparus CH11 biofilter for hydrogen sulfide removal , 1996 .

[7]  I. Dunn,et al.  Behavior of biofilters for waste air biotreatment. 1. Dynamic model development. , 1995, Environmental science & technology.

[8]  Hung‐Suck Park,et al.  Performance of an immobilized cell biofilter for ammonia removal from contaminated air stream. , 2007, Chemosphere.

[9]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[10]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[11]  S. Ottengraf,et al.  Kinetics of organic compound removal from waste gases with a biological filter , 1983, Biotechnology and bioengineering.

[12]  T. Swaminathan,et al.  Back-propagation neural network for performance prediction in trickling bed air biofilter , 2006 .