Sistema Digital de Detecção e Classificação de Eventos de Qualidade de Energia (Digital System for Detection and Classification of Power Quality Disturbances)

Augusto S. Cerqueira (santiago@lacee.ufjf.br)1, Carlos A. Duque (carlos.duque@ufjf.edu.br)2, Moisés V. Ribeiro (mribeiro@ieee;org)2, Rogério M. Trindade (rogerio_marques@yahoo.com.br)2


1Departamento de Engenharia Elétrica daDepartamento de Engenharia Elétrica da Universidade Federal de Juiz de Fora, Juiz de Fora, 36036-330, Brasil.
2Departamento de Engenharia Elétrica da Universidade Federal de Juiz de Fora, Juiz de Fora, 36036-330, Brasil.

This paper appears in: Revista IEEE América Latina

Publication Date: Sept. 2006
Volume: 4,   Issue: 5 
ISSN: 1548-0992


Abstract:
This paper presents a new method for detection and classification of power quality disturbances which achieves good performance with low computational cost. The event detection is based on the analysis of the statistical properties of the error signal which is defined as the difference between the sampled signal and its fundamental sinusoidal component, generated by the proposed algorithm. The classification is performed using a multi-rate technique for features extraction over the error signal and a multilayer feed-forward neural network. Numerical results from computational simulation showed the good performance of the proposed method.

Index Terms:
neural networks, pattern recognition, power quality, signal processing, instrumentation   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (210)]