Process monitoring using residuals and fuzzy classification with learning capabilities

Joseph Aguilar-Martin*, Claudia Isaza, Eduard Diez-Lledo, Marie Veronique Lelann, Julio Waissman Vilanova

*Autor correspondiente de este trabajo

Resultado de la investigación: Capítulo del libro/informe/acta de congresoCapítulorevisión exhaustiva

3 Citas (Scopus)

Resumen

This paper presents a monitoring methodology to identify complex systems faults. This methodology combines the production of meaningful error signals (residuals) obtained by comparison between the model outputs and the system outputs, with a posterior fuzzy classification. In a first off-line phase (learning) the classification method characterises each fault. In the recognition phase, the classification method identifies the faults. The chose classification method permits to characterize faults non included in the learning data. This monitoring process avoids the problem of defining thresholds for faults isolation. The residuals analysis and not the system variables themselves, permit us to separate fault recognition from system operation point influence. The paper describes the proposed methodology using a benchmark of a two interconnected tanks system.

Idioma originalInglés
Título de la publicación alojadaTheoretical Advances and Applications of Fuzzy Logic and Soft Computing
EditoresOscar Castillo, Patricia Melin, Oscar Montiel Ross, Roberto Sepulveda Cruz, Witold Pedrycz, Janusz Kacprzyk
Páginas275-284
Número de páginas10
DOI
EstadoPublicada - 1 dic 2007

Serie de la publicación

NombreAdvances in Soft Computing
Volumen42
ISSN (versión impresa)1615-3871
ISSN (versión digital)1860-0794

Huella

Profundice en los temas de investigación de 'Process monitoring using residuals and fuzzy classification with learning capabilities'. En conjunto forman una huella única.

Citar esto