TY - JOUR
T1 - Accurate Surface Condition Classification of High Voltage Insulators based on Deep Convolutional Neural Networks
AU - Serikbay, Arailym
AU - Bagheri, Mehdi
AU - Zollanvari, Amin
AU - Phung, B. T.
N1 - Funding Information:
The authors acknowledge the financial support of this study by the Collaborative Research Project (CRP) Grant of Nazarbayev University under grant no. (021220CRP0322).
Publisher Copyright:
© 1994-2012 IEEE.
PY - 2021/12/1
Y1 - 2021/12/1
N2 - 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.
AB - 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.
KW - convolutional neural network
KW - outdoor high voltage insulators
KW - surface condition classification
KW - transfer learning
KW - Deep Learning
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85123626699&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85123626699&partnerID=8YFLogxK
U2 - 10.1109/TDEI.2021.009648
DO - 10.1109/TDEI.2021.009648
M3 - Article
AN - SCOPUS:85123626699
SN - 1070-9878
VL - 28
SP - 2126
EP - 2133
JO - IEEE Transactions on Dielectrics and Electrical Insulation
JF - IEEE Transactions on Dielectrics and Electrical Insulation
IS - 6
ER -