Eleanor Dias De Sousa

Eleanor Dias De Sousa

Auto-generated profile, based on publicly available information

Eleanor Dias De Sousa

High and Extra High Voltage Laboratory (LEAT), Guam Science and Technology Park, Federal University of Par, Belm, Pará, 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
15 May 2026 in IEEE Access
Verified
Journal Article
Open access
ESEleanor Dias De Sousa
Eleanor Dias De Sousa
MRMarcel Antonionni De Andrade Romano
Marcel Antonionni De Andrade Romano
AMAndré Melo de Morais
André Melo de Morais
MNMarcus Vinicius Alves Nunes
Marcus Vinicius Alves Nunes
UBUbiratan Holanda Bezerra
Ubiratan Holanda Bezerra
Reliable detection of partial discharges (PD) is essential for condition monitoring of high-voltage electrical equipment. In applications based on high-frequency current transformer (HFCT) sensors, the construction of phase-resolved partial discharge (PRPD) diagrams depends on the accurate discrimination of pulses in signals often contaminated by noise and interference. Traditional signal processing methods present limitations regarding parameterization, scalability, and automation, particularly in continuous monitoring scenarios. This work proposes a new automated pipeline for detecting time windows containing PD pulses from time-domain raw signals acquired with an off-the-shelf 8-bit data acquisition system coupled with an HFCT sensor, integrating deep-learning-based detection with the construction of PRPD diagrams. An aspect that characterizes the originality of this work lies in the fact that a hybrid convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) model are employed to classify temporal segments without the use of fixed statistical thresholds or heuristic rules. The identified windows are used to construct PRPD diagrams, explicitly preserving the phase and amplitude information associated with each pulse. In the test set, composed of acquisitions in a high-voltage (HV) laboratory involving equipment taken out of operation, the model achieved an accuracy of 97.49%, with a recall greater than 97% for the positive class and an area under the curve (AUC) of 0.993. The amplitude estimate derived from the maximum absolute value of the pulse is consistent with baseline reference results and conventional measurements in accordance with the IEC 60270 standard, providing quantitative and qualitative validation of the constructed PRPD patterns. The results indicate that the proposed original method increases the level of automation, preserves physical interpretability, and shows strong potential for application in intelligent continuous monitoring systems for HV equipment.

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.