AUTOMATIC CLASSIFICATION OF POLES IN ENERGY TRANSMISSION LINES WITH DEEP LEARNING

Creative Commons License

Noğay H. S.

9 INTERNATIONAL CONGRESS ON ENGINEERING AND TECHNOLOGY MANAGEMENT, İstanbul, Türkiye, 29 Nisan - 01 Mayıs 2023, ss.124-132

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.124-132
  • Bursa Uludağ Üniversitesi Adresli: Evet

Özet

Abstract: The fact that different types of power transmission poles have different properties and are designed to withstand different loads and weather conditions reveals that the poles used in energy transmission lines should be classified. By classifying the poles, engineers can ensure that the appropriate pole is selected for each location along the transmission line. This helps ensure that the transmission line can transmit energy safely, efficiently and reliably. It may be useful and necessary to use a deep learning model trained and tested with visual data to classify poles used in power transmission lines. Automating the pole classification process can save time and resources and help ensure that the appropriate pole is selected for each location along the transmission line. Classifying poles using deep learning techniques such as Convolutional Neural Networks (CNNs) can contribute to science by improving our understanding of the physical properties and behavior of power transmission poles. In this study, automatic classification of poles used in power transmission lines was performed using CNN and an accuracy rate of 96.6% was obtained.