Banca de QUALIFICAÇÃO: INGRID THAÍS AZEVÊDO DANTAS

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : INGRID THAÍS AZEVÊDO DANTAS
DATE: 10/07/2024
TIME: 14:00
LOCAL: Online
TITLE:

Industry 4.0-Compliant Wavelet-Based Power Transformer Fault Classification Method During Data Missing Conditions

KEY WORDS:

Power transformers, fault classification, wavelet transform, data missing conditions, industry 4.0.

PAGES: 30
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUBÁREA: Sistemas Elétricos de Potência
SPECIALTY: Medição, Controle, Correção e Proteção de Sistemas Elétricos de Potência
SUMMARY:

Faults in power transformers can occur due to insulation degradation in their windings and must be quickly cleared by protective systems to preserve the transformer's integrity. In addition to transformer protection, classifying faults is also an essential task since it allows a better understanding of the transformer’s health over time. This work proposes a simple and efficient fault classification method in power transformers using the real-time boundary stationary wavelet transform (RT-BSWT). In this method, the low-frequency and high-frequency components
of faulted currents are computed, respectively, through the energies of the scaling and wavelet coefficients of the currents measured by current transformers installed on both sides of a power transformer. The preliminary method uses a simple threshold-based algorithm and can properly classify faults even in challenging conditions of data missing. The preliminary results reveal the effectiveness of the fault classifier even under unfavorable scenarios of data missing. Such robustness against the presence of gaps during the data analysis enhances the applicability of the classification method in real-world scenarios. Besides, this fact makes the proposed method very promising for applications involving industry 4.0 concepts, given the large use of sensors, data transmission, and simulations
based on data-driven models.

COMMITTEE MEMBERS:
Presidente - 1807863 - FLAVIO BEZERRA COSTA
Interno - 1543191 - LUIZ FELIPE DE QUEIROZ SILVEIRA
Externo ao Programa - 1141792 - RODRIGO PRADO DE MEDEIROS - UFRNExterno à Instituição - MÁRIO OLESKOVICZ - USP