Comparison of Radial Basis Function Neural Network and Response Surface Methodology for Predicting Performance of Biofilter Treating Toluene
- 1 Environmental Biotechnology Division, National Environmental Engineering and Research Institute, Nagpur, India
- 2 Department of Aerospace Engineering, Indian Institute of Sciences, Bangalore, India
- 3 Environmental Biotechnology Division, National Environmental Engineering and Research Institute, Nagpur, India
- 4 Environmental Biotechnology Division, National Environmental Engineering and Research Institute, Nagpur, India
- 5 Environmental Biotechnology Division, National Environmental Engineering and Research Institute, Nagpur, India
- 6 Solid Waste Management Division, National Environmental Engineering and Research Institute, Nagpur, India
- 7 Department of Aerospace Engineering, Indian Institute of Sciences, Bangalore, India
- 8 Environmental Biotechnology Division, National Environmental Engineering and Research Institute, Nagpur, India
Abstract
Biofiltration is emerging as a promising cost effective technique for the Volatile Organic Compounds (VOCs) removal from industrial waste gases. In the present investigation a comparative modeling study has been carried out using Radial Basis Function Neural Network (RBFN) and Response Surface Methodology (RSM) to predict and optimize the performance of a biofilter system treating toluene (a model VOC). Experimental biofilter system performance data collected over a time period by daily measurement of inlet VOC concentration, retention time, pH, temperature and packing moisture content was used to develop the mathematical model. These independent variables acted as the inputs to the mathematical model developed using RSM and RBFN, while the VOC removal efficiency was the biofilter system performance parameter to be predicted. The data set was divided into two parts: 60% of data was used for training phase and remaining 40% of data was used for the testing phase. The average % error for RSM and RBFN were 7.76% and 3.03%, and R2 value obtained were 0.8826 and 0.9755 respectively. The results indicated the superiority of RBFN in the prediction capability due to its ability to approximate higher degree of nonlinearity between the input and output variables. The optimization of biofilter parameters was also done using RSM to optimize the biofilter performance. RSM being structured in nature enabled the study of interaction effect between the independent variables on biofilter performance.
- E. R. Rene, D. V. S. Murthy and T. Swaminathan, “Performance Evaluation of a Compost Biofilter Treating Toluene Vapours,” Process Biochemistry, Vol. 40, No. 8, 2005, pp. 2771-2779. doi:10.1016/j.procbio.2004.12.010
- J. S. Devinny, M. A. Deshusses and T. S. Webster, “Biofiltration for Air Pollution Control,” CRC Press, New York, 1999.
- S. P. P. Ottengraf and A. H. C. Van den Oever, “Kinetics of Organic Compound Removal from Waste Gases with a Biological Filter,” Biotechnology and Bioengineering, Vol. 25, No. 12, 1983, pp. 3089-3102. doi:10.1002/bit.260251222
- Z. Shareefdeen, B. C. Baltzi, Y. S. Oh and R. Bartha, “Biofiltration of Methanol Vapor,” Biotechnology and Bioengineering, Vol. 41, No. 5, 1993, pp. 512-524. doi:10.1002/bit.260410503
- P. Mathews, “Design of Experiments with MINITAB,” Pearson Education Press, Upper Saddle River, 2005.
- D. C. Montgomery, “Design and Analysis of Experiments,” 5th Edition, Wiley, New York, 2011.
- D. Bas and I. H. Boyaci, “Modeling and Optimization II: Comparison of Estimation Capabilities of Response Surface Methodology with Artificial Neural Network in Biochemical Reaction,” Journal of Food Engineering, Vol. 78, No. 1, 2007, pp. 836-845.
- B. S. Narendra, P. V. Sivapullaiah, S. Suresh, S. N. Omkar, “Prediction of Unconfined Compressive Strength of Soft Grounds Using Computational Intelligence Techniques: A Comparative Study,” Computers and Geotechnics, Vol. 33, No. 3, 2006, pp. 196-208. doi:10.1016/j.compgeo.2006.03.006
- C. Ferreira, “Gene Expression Programming: Mathematical Modeling by an Artificial Intelligence,” 2nd Edition, Springer-Verlag, Berlin, 2006.
- M. B. Kasiri, H. Aleboy and A. Aleboyeh, “Modeling and Optimization of Heterogeneous Photo-Fenton Process with Response Surface Methodology and Artificial Neural Networks,” Environmental Science and Technology, Vol. 42, 2008, pp. 7970-7975. doi:10.1021/es801372q
- S. S. Tambe, B. D. Kulkarni and P. B. Deshpande, “Elements of Artificial Neural Network with Selective Application in Chemical and Biological Sciences,” Simulation and Advance Control Inc., Louisville, 1996.
- K. M. Desai, S. A. Survase, P. S. Saudagar, S. S. Lele and R. S. Singhal, “Comparison of Artificial Neural Network (ANN) and Response Surface Methodology (RSM) in Fermentation Media Optimization: Case Study of Fermentative Production of Scleroglucan,” Biochemical Engineering Journal, Vol. 41, No. 3, 2008, pp. 266-273. doi:10.1016/j.bej.2008.05.009