Open Access Open Access  Restricted Access Subscription or Fee Access

Conjugate Gradient Method for Evaluating the Anaerobic Wastewater Treatment System in the Prediction of COD

R.  Vijayabhanu

Abstract


An anaerobic reactor predicts the level of COD by applying a feed forward Neural Network. The organic effluent COD is the most common ecological and process performance indicator for all types of Wastewater Treatment Systems. In this experiment, the prediction is carried out by training the three layered feed forward ANN using Conjugate gradient algorithm. The trial sets are subjected to recognizeand reduce the missing values and outliers using K-Means clustering method and are used for training the input and output data. Thus the assessment results for the prediction of COD using Conjugate gradient function were found satisfactory.

Keywords


Anaerobic Filter, Conjugate Gradient (CG) Method, Chemical Oxygen Demand (COD), K- Means Clustering, Wastewater Treatment.

Full Text:

PDF

References


Rakesh Singh Asiwal, Dr. Santosh Kumar Sar, Shweta Singh, Megha Sahu, (2016), Wastewater Treatment by Effluent Treatment Plants, SSRG International Journal of Civil Engineering (SSRG - IJCE) – volume 3 Issue 12,ISSN: 2348 – 8352.

I. Plazl, G. Pipus, M. Grolka, T. Koloini., 1999, Parametric sensitivity and evaluation of a dynamic.model for single-. Stage wastewater treatment plant. ActaChimica Slovenica42, 289-300.

PeimanKianmehr, WathiqMansoor, and Fadi A. Kfoury (2014) Prediction of Biogas Generation Profiles in Wastewater Treatment Plants Using Neural Networks Journal of Clean Energy Technologies, Vol. 2, No. 3.

Dixon. M, Gallop J.R., Lambert S.C. and Healy J.V. 2005. Experience with data mining for the anaerobic wastewater treatment process. Environmental Modelling and Software. pp. 315-322..

Barnett.V and Lewis.T (1994). Outliers in statistical data, 3rd Ed., Wiley, Chichester, U.K.

J. B. MacQueen (1967): "Some Methods for classification and Analysis of Multivariate Observations, Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability", Berkeley, University of California Press, 1:281-297.

R.Vijayabhanu and V.Radha(2010). Recognition and Elimination of Missing Values and Outliers from An Anaerobic Wastewater Treatment System Using K-Means Cluster. 3rd International Conference on Advanced Computer Theory and Engineering - ICACTE 2010, Chengdu, China. IEEE catlog No: CFD1052F-PRT, ISBN: 978 -1-4244 -6540 -8.

Hamed M.M., Khalafallah M.G. and Hassanien E.A. 2004.Prediction of wastewater treatment plant performance using artificial neural networks, Environmental Modeling Software. 19: 919-928

Sima J. (1998). Introduction to Neural Networks, Technical Report No. V 755, Institute of Computer Science, Academy of Sciences of the Czech Republic

D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations by error propagation.Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pages 318-362, Cambridge, Massachusetts, 1986.

SaeedPakrou, NaserMehrdadi and AkbarBaghvand, (2015), ANN Modeling to Predict the COD and Efficiency of Waste Pollutant Removal from Municipal Wastewater Treatment Plants, pages 873-881, Vol. 10(Special Issue 1), 873-881.

RunarHeggelianRefsnaes, fall (2009), A Berif introduction to the Conjugate gradient Method.

Ningsheng Gong, Wei Shao, HongweiXu, (2010), The Conjugate Gradient Method with Neural Network Control, IEEE, School of Electronics and Information Engineering Nanjing University of Technology, Nanjing, Jiangsu, China.

Shi, Z. J., & Guo, J. H. (2008). A new algorithm of nonlinear conjugate gradient method with strong convergence. Computational & Applied Mathematics, 27, 93-106.

I.E. Livieris, P. Pintelas, A survey on algorithms for training artificial neural networks, University of Patras, Department of Mathematics, Educational Software Development Laboratory, University of Patras,GR-265 04, Patras, Hellas.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.