Signal analysis and feature generation for pattern identification of partial discharges in high-voltage equipment

Perpiñan Lamigueiro, Oscar; Sánchez-Urán González, Miguel Ángel; Álvarez, Fernando; Ortego, Javier y Garnacho, Fernando (2013). Signal analysis and feature generation for pattern identification of partial discharges in high-voltage equipment. "Electric Power Systems Research", v. 95 ; pp. 56-65. ISSN 0378-7796. https://doi.org/10.1016/j.epsr.2012.08.016.

Descripción

Título: Signal analysis and feature generation for pattern identification of partial discharges in high-voltage equipment
Autor/es:
  • Perpiñan Lamigueiro, Oscar
  • Sánchez-Urán González, Miguel Ángel
  • Álvarez, Fernando
  • Ortego, Javier
  • Garnacho, Fernando
Tipo de Documento: Artículo
Título de Revista/Publicación: Electric Power Systems Research
Fecha: Febrero 2013
Volumen: 95
Materias:
Palabras Clave Informales: Partial discharge; Wavelet variance; Prony method; Feature generation; Clustering; Visualization tools
Escuela: E.U.I.T. Industrial (UPM) [antigua denominación]
Departamento: Ingeniería Eléctrica [hasta 2014]
Licencias Creative Commons: Reconocimiento - No comercial - Compartir igual

Versiones

Aviso

Hay una versión más reciente de este eprint. Pulse aquí para verla.

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (7MB) | Vista Previa

Resumen

This paper proposes a method for the identification of different partial discharges (PDs) sources through the analysis of a collection of PD signals acquired with a PD measurement system. This method, robust and sensitive enough to cope with noisy data and external interferences, combines the characterization of each signal from the collection, with a clustering procedure, the CLARA algorithm. Several features are proposed for the characterization of the signals, being the wavelet variances, the frequency estimated with the Prony method, and the energy, the most relevant for the performance of the clustering procedure. The result of the unsupervised classification is a set of clusters each containing those signals which are more similar to each other than to those in other clusters. The analysis of the classification results permits both the identification of different PD sources and the discrimination between original PD signals, reflections, noise and external interferences. The methods and graphical tools detailed in this paper have been coded and published as a contributed package of the R environment under a GNU/GPL license.

Más información

ID de Registro: 13521
Identificador DC: http://oa.upm.es/13521/
Identificador OAI: oai:oa.upm.es:13521
Identificador DOI: 10.1016/j.epsr.2012.08.016
URL Oficial: http://www.sciencedirect.com/science/article/pii/S0378779612002696
Depositado por: Oscar Perpiñán Lamigueiro
Depositado el: 04 Oct 2012 10:27
Ultima Modificación: 01 Oct 2014 12:03
  • 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