Fusão Entre Técnicas De Extração De Atributos Na Classificação De Isoladores De Redes De Distribuição Usando Redes Neurais

Abstract

The present work provides a methodology for automated image processing and classification of four types of insulators used in Overhead Power Distribution Lines (OPDLs). To this end, a didactic distribution network was developed to capture photos of the insulators at an external environment as well as a studio to acquire images at a controlled environment. Subsequently, the image attributes where extracted and used as inputs for diferent trained classifiers such as neural networks, suport vector machine, decision tree, n-nearest neigbors, naive-bayes and hidden markov model, for a gradual mixing ofthe databases (studio and external imagens). The classification efficiencies where compared considering the application of principal components analysis (PCA) to identify the minimum information required for the classification.

Detecção de Isoladores em Redes de Distribuição utilizando Aprendizado Profundo

“…Conforme mostra a Figura 1, estão disponíveis imagens de isoladores de diferentes tipos: porcelana (IPN), saia baiana (ISB) , vidro (IVD) e polimérico (IPL) obtidas em ambiente controlado e ambiente externo. Os dados foram adquiridos conforme descrito em [6] e divididos em:…”