covid
Buscar en
Revista Iberoamericana de Automática e Informática Industrial RIAI
Toda la web
Inicio Revista Iberoamericana de Automática e Informática Industrial RIAI Atributos Relevantes para el Diagnóstico Automático de Eventos de Tensión en ...
Información de la revista
Vol. 10. Núm. 1.
Páginas 73-84 (enero - marzo 2013)
Compartir
Compartir
Descargar PDF
Más opciones de artículo
Visitas
4386
Vol. 10. Núm. 1.
Páginas 73-84 (enero - marzo 2013)
Artículo
Open Access
Atributos Relevantes para el Diagnóstico Automático de Eventos de Tensión en Redes de Distribución de Energía Eléctrica
Relevant Attributes for Voltage Event Diagnosis in Power Distribution Networks
Visitas
4386
Victor Barrera Núñeza,
Autor para correspondencia
vbarrera@eia.udg.edu

Autor para correspondencia.
, Ronald Velandiab, Fredy Hernándezb, Joaquim Meléndeza, Hermann Vargasb
a Instituto de Informática y Aplicaciones, Universitat de Girona, Campus Montilivi, 17003, Girona, España
b Escuela de Ingeniería Eléctrica, Electrónica y Telecomunicaciones, Universidad Industrial de Santander, Carrera 27 Calle 9, Bucaramanga, Colombia
Este artículo ha recibido

Under a Creative Commons license
Información del artículo
Resumen
Texto completo
Bibliografía
Descargar PDF
Estadísticas
Resumen

En este trabajo se aborda el diagnóstico de eventos o perturbaciones de tensión registradas en subestaciones de distribución. La aparición de dichos eventos se debe a causas diversas que van desde faltas en la red, el arranque de motores de inducción, energización de transformadores y conmutación de bancos de capacitores. Se propone la caracterización de estos eventos de tensión a partir de atributos extraídos directamente de la forma de onda, y que se relacionan con los fenómenos físicos asociados tanto con las causas de los eventos, como con su localización relativa respecto del punto de medida. Se ha estudiado la relevancia de dichos atributos mediante un análisis estadístico de la varianza (MANOVA). Los atributos más relevantes se han utilizado para la obtención de reglas de clasificación mediante algoritmos de aprendizaje automático. Los resultados fueron obtenidos empleando datos de 484 eventos reales y 38 eventos simulados.

Palabras clave:
Análisis estadístico
Calidad de la potencia eléctrica
Atributos
Eventos de tensión
Sistema basado en reglas
Abstract

This paper focuses on diagnosis of voltage events collected in power distribution networks. Fault networks, induction motor starting, transformer energization and capacitor bank switching cause voltage events. A characterization of voltage events using attributes directly extracted from the voltage and current waveforms is done in this paper. The used attributes are highly related with the event root-cause as well as the relative location of the event source with respect to the measurement point. The relevance of each attribute has been assessed applying a statistical analysis of variance (MANOVA). The most relevant attributes have been used as input to rule-extraction algorithms in order to extract classification rules. The results were obtained using 484 real-world and 38 synthetic voltage events.

Keywords:
Statistical analysis
power quality
attributes
voltage sag event
rule based system
Referencias
[Barrera et al., 2008]
Barrera V., Berjaga X., Melendez J., Herraiz S., (2008). Two new methods for voltage sag source location. 13th International Conference on Harmonics & Quality of Power, 28 de Septiembre a 1 de Octubre, Australia.
[Barrera et al., 2009]
V. Barrera, J. Meléndez, S. Herraiz.
Evaluation of Fault relative location algorithms using voltage sag data collected at 25-kv substations.
European Transactions on Electrical Power, 20 (2009), pp. 34-51
[Barrera et al., 2010a]
Barrera V., Meléndez J., Kulkarni S., Santoso S. (2010) Feature analysis and automatic classification of short-circuit faults resulting from external causes. European Transactions on Electrical Power, DOI: 10.1002/etep.674, January 2012.
[Barrera et al., 2010b]
Barrera V., Bollen, M., Yu-Hua Gu I., Meléndez, J. (2010). Feature characterization of power quality events according to their underlying causes. 14th International Conference on Harmonics & Quality of Power, 26-29 de Septiembre, Italy.
[Barrera et al., 2010c]
Barrera V., Kulkarni S., Santoso S., Meléndez J. (2010) SVM-Based classification methodology for overhead distribution fault events. 14th International Conference on Harmonics & Quality of Power, 26-29 de Septiembre, Italy.
[Barrera et al., 2010d]
Barrera V., Kulkarni S., Santoso S., Melendez J. (2010) Feature analysis and classification methodology for overhead distribution fault events. IEEE Power & Energy Society, 2010 General Meeting. 25-29 de Julio, USA.
[Blanco et al., 2009]
Blanco J., Jagua J., Barrera. V, Jaimes, L. (2009) Metodología para el diagnóstico de la causa de huecos de tensión: análisis de fallas, Tesis de grado, Publicaciones UIS, http://tangara.uis.edu.co/biblioweb/tesis/2009/132235.PDFColombia.
[Bollen, 2000]
Bollen M. (2000) Understanding Power Quality Problems: Voltages Sags and Interruptions, IEEE PRESS, New York.
[Bollen, 2003]
M. Bollen.
Algorithms for characterizing measured three-phase unbalanced voltage dips.
IEEE Transactions on Power Delivery, 18 (2003), pp. 937-944
[Bollen et al., 2007]
M. Bollen, I. Yu-Hua, P. Axelberg, E. Styvaktakis.
Classification of underlying causes of power quality disturbances: Deterministic versus Statistical methods.
EURASIP Journal on Advances in Signal Processing., 2007 (2007), pp. 1-17
[Clark and Niblett, 1989]
Clark P, Niblett T. (1989) The CN2 induction algorithm. Machine Learning Journal, 3/4: 261-283.
[Clark and Boswell., 1991]
Clark P and R. Boswell. (1991) Rule induction with CN2: Some recent improvements. In Y. Kodratoff, editor, Machine Learning - EWSL-91, Springer-Verlag: Berlin, 151-163.
[Coury and Tavarez, 1998]
Coury, D.V., Tavarez C.J. (1998) Transient analysis resulting from shunt capacitor switching in an actual electrical distribution system, 8th International Conference on Harmonics & Quality of Power, Athens. Grid 2030 - A National Vision for Electricity's Second 100 Years (2003), United States Department of Energy.
[Hamzah et al., 2005]
Hamzah N., Mohamed A., Hussain A. (2005) Locating voltage sag source at the point of common coupling in industrial distribution systems. IEEE International Conference on Power Electronics and Drive Systems. 28-1 de Noviembre, Malasia.
[Hernández et al., 2004]
Hernández, J, Quintana, M.J, Ramírez, C. (2004) Introducción a la minería de datos. Pearson Prentice Hall, Addison-Wesley.
[Ibrahim and Morcos, 2002]
W. Ibrahim, M. Morcos.
Artificial Intelligence and Advanced Mathematical Tools for Power Quality Aplications: A Survey”.
IEEE Transactions on Power Delivery, 17 (2002), pp. 668
[Kersting, 2000]
Kersting, W.H. (2000) Radial distribution test feeders. Power engineering Society, USA.
[Kulkarni et al., 2010]
Kulkarni S., Lee D., Allen A., Santoso S., Short T., (2010) Waveform Characterization of Animal Contact, Tree Contact, and Lightning Induced Faults, IEEE Power & Energy Society, 2010 General Meeting. 25-29 de Julio, USA.
[McGranaghan and Roettger., 2002]
M. McGranaghan, B. Roettger.
Economic evaluation of power quality”.
IEEE Power Engineering Review, 22 (2002), pp. 8-12
[McGranahan, 2001]
McGranahan M. (2001) “Trends in Power Quality Monitoring”, IEEE Power Engineering Review.
[Pradhan et al., 2007]
A.K. Pradhan, A. Routray, S. Madhan.
Fault direction estimation in radial distribution system using phase change in sequence current.
IEEE Transactions on Power Delivery, 22 (2007), pp. 2065-2071
[Seon et al., 2004]
A. Seon, W. Dong, C. Li, M. Seung.
Determination of the Relative Location of Voltage sag source According to event Cause”.
Power Engineering Society General Meeting, 1 (2004), pp. 620-625
[Styvaktakis, 2002]
Styvaktakis E., (2002) Automating power quality analysis, Ph.D. thesis, Chalmers University of Technology, Sweden, 2002.
[Tayjasanant et al., 2005]
Tayjasanant T., C. Li, and W. Xu. (2005) A resistance sign-based method for voltage sag source detection. IEEE Transactions on Power Delivery, 20, 2544-51, 2005.
[Velandia et al., 2010]
Velandia R., Hernández F., Barrera, V., Vargas, H. (2010) Evaluación de algoritmos de extracción de reglas de decisión para el diagnóstico de huecos de tensión, Tesis de grado, Publicaciones Universidad Industrial de Santander, Colombia.
[Xu and Mo-Yuen, 2006]
L. Xu, C. Mo-Yuen.
A classification approach for power distribution systems fault cause identification.
IEEE Transaction on Power System;, 21 (2006), pp. 53-60
[Xu et al., 2007]
L. Xu, M. Chow, L. Taylor.
Power Distribution Fault Cause Identification With Imbalanced Data Using the Data Mining-Based Fuzzy Classification E-Algorithm.
IEEE Transaction on Power Systems, 22 (2007), pp. 164-171
[Yalcinkaya et al., 1998]
G. Yalcinkaya, M.H.J. Bollen, P.A. Crossley.
Characterization of voltage sags in industrial distribution Systems.
IEEE Transactions on Industry Applications, 34 (1998), pp. 682-688
[Yixin et al., 2010a]
Yixin C, Mo-Yuen C, Wenbin L, Lexin L. (2010) Evaluation of distribution fault diagnosis algorithms using ROC curves, 25 a 29 de Julio, USA.
[Yixin et al., 2010b]
C. Yixin, C. Mo-Yuen, L. Wenbin, L. Lexin.
Statistical Feature Selection From Massive Data in Distribution Fault Diagnosis.
IEEE Transaction on Power Systems, 25 (2010), pp. 642-648
Copyright © 2012. CEA
Opciones de artículo