Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score

Diez Oliván, Alberto; Pagán, José A.; Sanz Bravo, Ricardo y Sierra, Basilio (2017). Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score. "Neurocomputing" (n. 241); pp. 97-107. ISSN 0925-2312. https://doi.org/10.1016/j.neucom.2017.02.024.

Descripción

Título: Data-driven prognostics using a combination of constrained K-means clustering, fuzzy modeling and LOF-based score
Autor/es:
  • Diez Oliván, Alberto
  • Pagán, José A.
  • Sanz Bravo, Ricardo
  • Sierra, Basilio
Tipo de Documento: Artículo
Título de Revista/Publicación: Neurocomputing
Fecha: 2 Junio 2017
Materias:
Palabras Clave Informales: Behavior characterization; Condition monitoring; Constrained k-means clustering; Fuzzy modeling; Local outlier factor; Machine learning
Escuela: E.T.S.I. Industriales (UPM)
Departamento: Automática, Ingeniería Eléctrica y Electrónica e Informática Industrial
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img] PDF (Document Portable Format) - Acceso permitido solamente a usuarios en el campus de la UPM hasta 7 Junio 2019 - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (3MB)

Resumen

Today, failure modes characterization and early detection is a key issue in complex assets. This is due to the negative impact of corrective operations and the conservative strategies usually put in practice, focused on preventive maintenance. In this paper anomaly detection issue is addressed in new monitoring sensor data by characterizing and modeling operational behaviors. The learning framework is performed on the basis of a machine learning approach that combines constrained K-means clustering for outlier detection and fuzzy modeling of distances to normality. A final score is also calculated over time, considering the membership degree to resulting fuzzy sets and a local outlier factor. Proposed solution is deployed in a CBM+ platform for online monitoring of the assets. In order to show the validity of the approach, experiments have been conducted on real operational faults in an auxiliary marine diesel engine. Experimental results show a fully comprehensive yet accurate prognostics approach, improving detection capabilities and knowledge management. The performance achieved is quite high (precision, sensitivity and specificity above 93% and ?=0.93?=0.93), even more so given that a very small percentage of real faults are present in data.

Más información

ID de Registro: 46796
Identificador DC: http://oa.upm.es/46796/
Identificador OAI: oai:oa.upm.es:46796
Identificador DOI: 10.1016/j.neucom.2017.02.024
URL Oficial: http://www.sciencedirect.com/science/article/pii/S0925231217302941
Depositado por: Memoria Investigacion
Depositado el: 14 Jun 2017 13:49
Ultima Modificación: 14 Jun 2017 13:49
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM