Improving the efficiency of the prediction system for anaerobic wastewater treatment process using Genetic Algorithm

Wastewater treatment methods are dynamic and have high non-linear behaviour. The significance of the influent disturbances and the bioreactor performances are generally predicted off- line in a laboratory, since there is no consistent on-line sensor available for the prediction. This work suggests the development of a neural network model for prediction of the values of the influent disturbances using Z-score as a normalization technique followed by Genetic Algorithm (GA) as a feature selection process to improve the speed and quality of the prediction accuracy. A Back Propagation Network (BPN) trained using Modified Levenberg-Marquardt (MLM) algorithm was efficiently utilized to develop a BPN for an Up-flow Anaerobic filter (UAF) for predicting the chemical oxygen demand (COD) level in the effluent. In this paper, MLM algorithm has been applied to train the BPN based on the normalized influent parameters of the cheese-dairy wastewater treatment using UAF. COD is an essential test for evaluating the quality of wastewater in terms of organic pollution load prior to discharge. The predicted COD level of BPN based on all influent parameters is compared with the predicted COD level of BPN based on selected influent features by genetic algorithm. Experimental results shows that the MSE , regression and the MAE obtained in BPN-MLM when using z-score normalization and genetic algorithm for feature selection are found satisfactory as it predicted the effluent COD level more accurately.

[1]  A. Santhakumaran,et al.  Statistical Normalization and Back Propagationfor Classification , 2011 .

[2]  S. Mohamed,et al.  Statistical Normalization and Back Propagation for Classification , 2022 .

[3]  Grietje Zeeman,et al.  The effects of operational and environmental variations on anaerobic wastewater treatment systems: a review. , 2006, Bioresource technology.

[4]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

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

[6]  Marc M. Van Hulle,et al.  Genetic Algorithm for Feature Subset Selection with Exploitation of Feature Correlations from Continuous Wavelet Transform: a real-case Application , 2004, International Conference on Computational Intelligence.

[7]  Ida Scheel,et al.  The influence of missing value imputation on detection of differentially expressed genes from microarray data , 2005, Bioinform..

[8]  Huiping Zhang,et al.  A hybrid genetic--neural algorithm for modeling the biodegradation process of DnBP in AAO system. , 2011, Bioresource technology.

[9]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[10]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[11]  Joseph V. Thanikal,et al.  Sustainable Agro-Food Industrial Wastewater Treatment Using High Rate Anaerobic Process , 2013 .

[12]  L. Neves,et al.  Anaerobic co-digestion of organic wastes , 2009 .

[13]  L. Ladha,et al.  FEATURE SELECTION METHODS AND ALGORITHMS , 2011 .

[14]  Sri Ramakrishna,et al.  FEATURE SELECTION METHODS AND ALGORITHMS , 2011 .

[15]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[16]  Pradeep Kumar,et al.  High rate anaerobic filter with floating supports for the treatment of effluents from small-scale agro-food industries , 2009 .

[17]  L. Parthiban,et al.  Back propagation Neural network modeling approach in the anaerobic digestion of wastewater treatment , 2012 .