Knowledge extraction from a nitrification denitrification wastewater treatment plant using SOM-NG algorithm

ABSTRACT SOM-NG is a hybrid algorithm that is able to carry out visualization of process data, nonlinear function approximation, classification and clustering. The supervised version of SOM-NG produces a new type of 2D lattices called gradient planes which are useful to determine the dynamics of a target variable according to the remaining training variables. In this way, it is an interesting tool for data mining in order to extract knowledge from databases for nonlinear systems. The main objective of this work is to analyze data from an industrial wastewater treatment plant using SOM-NG algorithm in order to investigate relationships between the process variables. The data used proceeds from a biological wastewater treatment plant. This plant is based on an activated sludge treatment including nitrification and denitrification processes. A direct relation between the nitrification efficiency and the operating temperature was found, and also between the ammonia loading rate and the nitrification denitrification efficiency.

[1]  Jeanny Hérault,et al.  Curvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets , 1997, IEEE Trans. Neural Networks.

[2]  Pablo A. Estévez,et al.  Online data visualization using the neural gas network , 2006, Neural Networks.

[3]  Christopher M. Bishop,et al.  Mixtures of Probabilistic Principal Component Analyzers , 1999, Neural Computation.

[4]  Esko Juuso,et al.  Real-time optical monitoring of the wastewater treatment process , 2016, Environmental technology.

[5]  J. Rodríguez,et al.  Treatment of coke wastewater in a sequential batch reactor (SBR) at pilot plant scale. , 2008, Bioresource technology.

[6]  José Luís Calvo-Rolle,et al.  Detection of locally relevant variables using SOM-NG algorithm , 2013, Eng. Appl. Artif. Intell..

[7]  Thomas Villmann,et al.  Batch and median neural gas , 2006, Neural Networks.

[8]  José Luís Calvo-Rolle,et al.  A hybrid batch SOM-NG algorithm , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[9]  I Vázquez,et al.  Simultaneous removal of phenol, ammonium and thiocyanate from coke wastewater by aerobic biodegradation. , 2006, Journal of hazardous materials.

[10]  Michael C. Hout,et al.  Multidimensional Scaling , 2003, Encyclopedic Dictionary of Archaeology.

[11]  Mario J. Crespo-Ramos,et al.  Supervised Hybrid SOM-NG Algorithm , 2011 .

[12]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[13]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[14]  Iván Machón-González,et al.  Comparing feed-forward versus neural gas as estimators: application to coke wastewater treatment , 2013, Environmental technology.

[15]  Iván Machón González,et al.  Self-organizing map and clustering for wastewater treatment monitoring , 2004, Eng. Appl. Artif. Intell..

[16]  J. Rodríguez,et al.  Study of the aerobic biodegradation of coke wastewater in a two and three-step activated sludge process. , 2006, Journal of hazardous materials.