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%.
21 April 2025 in IEEE Transactions on Instrumentation and Measurement
Outdoor insulation systems often suffer from partial discharge (PD) faults that compromise the reliability of electrical grids. This paper proposes an integrated approach combining a non-invasive downsized discone antenna to capture ultra-high-frequency signals and an optimized capsule network (CapsPDNet) for robust PD fault prediction. The CapsPDNet is chosen as it overcomes the information loss associated with pooling operations and leverages vector representations, providing more nuanced predictions than scalar values, especially when the predictions are made across different antenna locations. Three typical PD fault types are targeted, surface discharges on ceramic and polymeric materials, internal discharges, and corona discharges, and then multiple signal processing techniques are evaluated to determine the most effective feature extraction and reconstruction technique. Experimental results show that the proposed model achieves up to a 18.89% improvement in PD fault prediction accuracy over benchmark approaches, demonstrating high generalizability and scalability when considering different antenna locations. The patented antenna used in this study offers a compact size through a novel size reduction technique, covers a wide bandwidth, and exhibits high sensitivity to PD activities. Additionally, discrete wavelet decomposition (DWT) is chosen as the feature extractor as it provides high-importance features with the lowest computational time, offering a more reliable and scalable solution for early PD fault detection and real-time condition monitoring of insulation systems.