Obtaining key parameters and working conditions of wastewater biological nutrient removal by means of artificial intelligence tools

DSpace/Manakin Repository

español português english

Obtaining key parameters and working conditions of wastewater biological nutrient removal by means of artificial intelligence tools

Show full item record

Title: Obtaining key parameters and working conditions of wastewater biological nutrient removal by means of artificial intelligence tools
Author: Martín de la Vega, Pedro Tomás; Jaramillo Morán, Miguel Ángel
Abstract: El potencial de oxidación-reducción (ORP) y el oxígeno disuelto (DO) han sido monitoreados en una planta municipal de tratamiento de aguas residuales (EDAR). Se registraron tres mil doscientos ciclos de aireación-no aireación. Se analizaron definiendo 16 parámetros para caracterizar cada uno de ellos. Los vectores así obtenidos fueron tratados con la herramienta de diagrama de caja para rechazar aquellos con valores atípicos (valores anormalmente altos o bajos). Los datos restantes fueron procesados por una red neuronal (mapa auto organizado: SOM) para clasificarlos en clases y obtener relaciones entre parámetros para identificar aquellos más representativos de la dinámica del sistema. Eran: la tasa de absorción de oxígeno (OUR), la pendiente promedio de aumento de oxígeno (ORAS) y la "flecha" potencial de oxidación-reducción (ORParrow, la distancia máxima entre la curva ORP y su alineación). Finalmente, las clases obtenidas de SOM se agruparon en cuatro macro clases mediante el algoritmo K-Medias para definir cuatro estados de operación relacionados con las características estacionales y de carga, que pueden tenerse en cuenta, junto con los parámetros clave, en La gestión de la EDAR con el objetivo de mejorar el rendimiento de eliminación de nutrientes mediante la adaptación de sus controladores a las variaciones estacionales y de carga.The oxidation-reduction potential (ORP) and the dissolved oxygen (DO) have been monitored in a municipal wastewater treatment plant (WWTP). Three thousand two hundred aeration–non-aeration cycles were recorded. They were analyzed by defining 16 parameters to characterize each one of them. The vectors so obtained were treated with the box-plot tool to reject those with outliers (abnormally high or low values). The remaining data were processed by a neural network (self-organizing map: SOM) in order to classify them into classes and to obtain relations between parameters to identify those more representative of the system dynamics. They were: the oxygen uptake rate (OUR), the oxygen rise average slope (ORAS), and the oxidation-reduction potential “arrow” (ORParrow, the maximum distance between the ORP curve and its linearization). Finally, the classes obtained from SOM were grouped into four macro-classes by means of the K-means algorithm in order to define four operation states related to seasonal and load characteristics, which may be taken into account, along with the key parameters, in the WWTP management with the aim of improving the nutrient removal performance by adapting their controllers to seasonal and load variations.
URI: http://hdl.handle.net/10662/9869
Date: 2018


Files in this item

Files Size Format View
w10060685.pdf 2.175Mb PDF Thumbnail

The following license files are associated with this item:

This item appears in the following Collection(s)

Show full item record

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International

Search DSpace


Browse

My Account

Statistics

Help

Redes sociales