Caio Queiroz Silva

Caio Queiroz Silva

Auto-generated profile, based on publicly available information

Caio Queiroz Silva

Federal University of Par,Extra High Voltage Laboratory,Belm,Brazil

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 October 2025
Verified
Conference Paper
Closed access
ACAntonio Fernando Martins Cardoso
Antonio Fernando Martins Cardoso
MNMarcus Vinicius Alves Nunes
Marcus Vinicius Alves Nunes
RSRobson Do Nascimento Silva
Robson Do Nascimento Silva
VAVanilze Vaz Monteiro de Almeida
Vanilze Vaz Monteiro de Almeida
ESEleanor Dias de Sousa
Eleanor Dias de Sousa
CSCaio Queiroz Silva
Caio Queiroz Silva
This work proposes an automatic method for the classification of partial discharge signals in insulation systems of high voltage electric generators, using a computer vision technique based on the Bag of Features algorithm in a database composed of images of Phase-Resolved Partial Discharge of corona, internal, and surface discharges in the electrical insulation of the stator bars of high voltage generators. The algorithm was implemented in a computational environment, combining the extraction of characteristics from images through the Bag of Features technique with the supervised learning process, Support Vector Machine, in the training actions and classification of signals of the automated routine. The proposed method achieved a very high classification accuracy for the three types of partial discharge signals. The results demonstrate the feasibility of integrating this approach into predictive maintenance systems for high-voltage electrical equipment, in this case, high-voltage electric machines, enhancing operational reliability and reducing costs in maintenance processes.

14 October 2025
Verified
Conference Paper
Closed access
ASAdriel B. da Silva
Adriel B. da Silva
AMAndré Melo de Morais
André Melo de Morais
CSCaio Q. Silva
Caio Q. Silva
AMAllan R. A. Manito
Allan R. A. Manito
MRMarcel A. De A. Romano
Marcel A. De A. Romano
MNMarcus Vinicius Alves Nunes
Marcus Vinicius Alves Nunes
This article analyzes the performance of different filtering techniques applied to the phenomenon known as partial discharges (PD), which occur in electrical insulation and, when undetected, can evolve into serious failures, such as short circuits and power outages. Therefore, PD analysis becomes an essential tool in the operation, maintenance, and asset management of power grids, since identifying these PD pulses is not trivial due to the presence of noise from both internal and external sources within the power systems, such as adjacent equipment and pollution levels. The study compared filtering and analysis methods on non-invasive measurements made with a high-frequency current transformer, evaluating traditional digital filters, adaptive techniques, and the wavelet transform (WT). A set of seven metrics was used to verify their effectiveness in minimizing noise and preserving signal characteristics, such as signal-to-noise ratio (SNR), cross-correlation (CC), and root mean square error (RMSE), among others. The results demonstrated that advanced approaches, such as the use of adaptive filters and wavelet combinations, outperform classical methods, reducing noise in measurement signals and favoring clearer detection of PD pulses in real data. This contribution improves monitoring and increases reliability in high-voltage electrical systems.