Novel Antenna for Partial Discharge Detection and Classification: A Convolutional Neural Network-Based Deep Learning Approach
IEEE Transactions on Dielectrics and Electrical Insulation, cilt.31, sa.4, ss.1711-1720, 2024 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 31 Sayı: 4
- Basım Tarihi: 2024
- Doi Numarası: 10.1109/tdei.2024.3377603
- Dergi Adı: IEEE Transactions on Dielectrics and Electrical Insulation
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, Civil Engineering Abstracts
- Sayfa Sayıları: ss.1711-1720
- Anahtar Kelimeler: Condition monitoring, finite-element analysis, partial discharges (PDs), sensors, ultrahigh frequency (UHF) antennas
- Süleyman Demirel Üniversitesi Adresli: Evet
Özet
Inspection of high voltage (HV) devices using ultra-high frequency (UHF) sensors has been predominantly employed for partial discharge (PD) detection and classification. This work reports implementing and testing a coplanar waveguide (CPW)-fed annular monopole antenna for PD detection. The 3D Maxwell solver of COMSOL multi-physics is used in this paper to optimize the antenna parameters and improve its performance. The original size of the antenna is reduced by about 47% utilizing structural symmetry and current resonances. The proposed antenna exhibits a wide bandwidth over frequencies ranging between 0.5 GHz - 3 GHz (except at 0.6 GHz, 1.2 GHz, and 2.75 GHz) due to the applied size reduction, using a maximum reflection coefficient of -10 dB (based on measurements). Nonetheless, the antenna performance is still effective over the full UHF range (considering that -6 dB is sufficient to detect PD activities). The effectiveness of the proposed antenna in PD detection is verified by testing the antenna’s performance against three common types of PD defects, namely, sharp point-to-ground discharge, surface discharge, and internal discharge. Furthermore, deep learning is implemented to classify the three defects with a total classification accuracy of 96%.