IJSER Home >> Journal >> IJSER
International Journal of Scientific and Engineering Research
ISSN Online 2229-5518
ISSN Print: 2229-5518 2    
Website: http://www.ijser.org
scirp IJSER >> Volume 3,Issue 2,February 2012
Artificial Neural Network Based Model for the Prediction of Effluent from Lab-Scale Upward Flow Hybrid Anaerobic Sludge Blanket (UHASB) Reactor
Full Text(PDF, )  PP.250-255  
Author(s)
Sindhu. J. Nair, Hota H.S., Ghosh P.K. and Agrawal M.L
KEYWORDS
— Error back propagation Network (EBPN), Radial basis Function Netw ork (RBFN), upw ard flow hybrid anaerobic sludge blanket (UHASB).
ABSTRACT
Anaerobic processes have gained popularity over the past decade, and have already been applied successfully for the treatment of a number of waste streams. One of the most attractive options available for such a treatment is the up flow anaerobic sludge blanket (UASB) reactor, which acts as a compact system for removal and digestion of organic matter present in sewage. The hybrid reactor UHASB is an improved version of the UASB system and combines the merits of the up flow sludge blanket and the fixed film reactors. The hybrid reactor is an economical solution for the treatment of municipal sewage. This paper presents the predictions of the effluent from a UHSAB reactor using artificial neural network. Two different neural network Error back propagation network (EBPN) and Radial basis function network (RBF) are used here for prediction, the prediction results are compared. When a UHSAB reactor is put into operation, variations of the waste water quantity and quality must be predicted using mathematical models to assist in UHSAB reactor such that the treated effluent will be controlled and meet discharge standards. In this study ANN is used to predict the effluent biochemical oxygen demand (BOD), chemical oxygen demand (COD), suspended solids (SS) and total dissolved solids (TDS) from the lab-scale upward flow hybrid anaerobic sludge blanket reactor (UHASB).The simulation results indicated that the mean absolute percentage error (MAPE) of 11.86, 15.53, 26.67 and 22.26 for BOD, COD, SS and TDS respectively could be achieved in case of testing. Prediction result suggests that EBPA tuned neural network (EBPN) is performing well and could predict the removal efficiencies effectively and accurately.
References
[1] APHA (1998) Standard Methods for the Examination of water and wastewater, Washington D.C.

[2] CPCB (1997). Status of water supply and wastewater generation, collection, treatment, and disposal in metro cities. Central Pollution Control Board, series CUPS/42/1997-98, India.

[3] Goncalves, R.F., Charlier, A.C. and Sammut, F. (1994). Primary fermentation of soluble and particulate organic matter for wastewater treatment. Water Science and Technology. 30(6): 53-62.

[4] H.H chen & S.L.L.O. “ Prediction of the effluent from a domestic waste water treatment plant of CASP using gray model and neural network” Environ Monit Assess springer science no 162, pp 2645-275,2010.

[5] T.T. chow, Z. Lin and C.L. Song “Applying neural network and genetic algorithm in chiller optimization” 7th international IBPSA cont, Rio de Janeiro, Brazil, PP 1059-1065, Aug. 13-15, 2001.

[6] M. DJENNAS and M. BENBOUZIANE “A neural Network & Genetic algorithm hybrid model for modeling exchange rates. The case of the US Dollar /Kuwait Dinar” survey paper, www.fxtop.com, 2009.

[7] S.N Shivanandam and S.N. Deepa, Principals of soft computing, second edition Wiley India publication 2011.

[8] S. Rajshekhran and Pai, Neural Network, Fuzzy logic and Genetic algorithm: Synthesis and Applications, PHI learning private limited 2010.

[9] Seghezzo,L., 2004. Anaerobic treatment of domestic wastewater in subtropical regions. Phd thesis, Wageningen University

Untitled Page