Use this link to cite:
http://hdl.handle.net/2183/23791 Detección de fallos en redes de presión pertenecientes a redes de suministro de agua mediante filtros estáticos lineales basados en PCA
Loading...
Identifiers
Publication date
Authors
Pereira Martín, Mario
Blesa, Joaquim
Puig, Vicenç
Muñoz de la Peña, David
Advisors
Other responsabilities
Journal Title
Bibliographic citation
Pereira Martín, M., Blesa, J.,Puig, V., Muñoz De la Peña Sequedo, D. (2019). Detección de fallos en redes de presión pertenecientes a redes de suministro de agua mediante filtros estáticos lineales basados en PCA. En XL Jornadas de Automática: libro de actas, Ferrol, 4-6 de septiembre de 2019 (pp. 568-573). DOI capítulo: https://doi.org/10.17979/spudc.9788497497169.568. DOI libro: https://doi.org/10.17979/spudc.9788497497169
Type of academic work
Academic degree
Abstract
[Resumen] Este artículo se centra en la elaboración de una serie
de modelos estáticos lineales que relacionan los datos
de un conjunto de sensores de presión con un subconjunto
de ellos que denominaremos base. Gracias
a estos modelos se pueden detectar comportamientos
anómalos en el funcionamiento de dichos sensores mediante
la comparación de los datos reales con los estimados.
Para la detección de anomalías en la base
se empleará otro subconjunto secundario para su chequeo
que denominaremos base secundaria. Como caso
de estudio se han utilizado datos almacenados de los
sensores de presión de una sección de la red de suministro
de aguas de la ciudad de Madrid.
[Abstract] This paper is focused on the design of a set of static and linear models which relate the data of a subset of pressure sensors in a drinking water network with the rest of them. This subset of sensors is called principal base. Thanks to these models wrong behaviours in these devices can be detected comparing real data from sensors with estimated data obtained from these models. In case of fault in a sensor beloning to the principal base, we propose the use of another base, different from the previous one, called secondary base. This second set is needed to detect anomalies in the first one. The proposed methodology was applied to a section of the water drinking network of the city of Madrid
[Abstract] This paper is focused on the design of a set of static and linear models which relate the data of a subset of pressure sensors in a drinking water network with the rest of them. This subset of sensors is called principal base. Thanks to these models wrong behaviours in these devices can be detected comparing real data from sensors with estimated data obtained from these models. In case of fault in a sensor beloning to the principal base, we propose the use of another base, different from the previous one, called secondary base. This second set is needed to detect anomalies in the first one. The proposed methodology was applied to a section of the water drinking network of the city of Madrid
Description
Editor version
Rights
Atribución-NoComercial-CompartirIgual 4.0


