Accurate Surface Condition Classification of High Voltage Insulators based on Deep Convolutional Neural Networks

Arailym Serikbay, Mehdi Bagheri, Amin Zollanvari, B. T. Phung

Research output: Contribution to journalArticlepeer-review

15 Citations (Scopus)

Abstract

Outdoor insulators in high voltage power lines serve as electrical insulation barriers and mechanical supports for live conductors. They are exposed to environmental contaminants and physical deterioration or damage. Hence, polluted insulator analysis is a fundamental concern for proper power system operation. This study harvests a comprehensive insulator surface dataset composed of 4500 images under different surface conditions: clean surface, clean surface with the water droplets, contaminated surfaces with the soil and cement, as well as a wet surface, which is mixed with the soil and cement contaminants. Convolutional neural networks (CNNs) are employed, and a systematic model selection methodology is introduced to construct an accurate classifier of insulator surface conditions while taking into consideration the potential implementation of the constructed CNN in resource-limited embedded devices. The results show the proposed model complexity reduction technique leads to a lighter architecture by a factor of 3 at the expense of a slight reduction of 6.5% in classification accuracy.

Original languageEnglish
Pages (from-to)2126-2133
Number of pages8
JournalIEEE Transactions on Dielectrics and Electrical Insulation
Volume28
Issue number6
DOIs
Publication statusPublished - Dec 1 2021

Keywords

  • convolutional neural network
  • outdoor high voltage insulators
  • surface condition classification
  • transfer learning
  • Deep Learning
  • Machine Learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Accurate Surface Condition Classification of High Voltage Insulators based on Deep Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this