Banca de QUALIFICAÇÃO: MATEUS DE MELO ARAUJO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE: MATEUS DE MELO ARAUJO
DATA: 21/02/2022
HORA: 09:00
LOCAL: meet.google.com/ojp-qjbh-ivx
TÍTULO: Using Decision Tree Transparency to Assess the Gas Formation Theory in Power Transformers with New Observations Regarding the Decomposition Temperatures of Insulating Mineral Oil
PALAVRAS-CHAVES: Decision Tree, Dissolved Gas Analysis (DGA), Fault Diagnosis, Power Transformers
PÁGINAS: 10
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
SUBÁREA: Sistemas Elétricos de Potência
ESPECIALIDADE: Máquinas Elétricas e Dispositivos de Potência
RESUMO:

The analysis of gases dissolved in oil is the main technique used to predict possible failures in power transformers. Currently, there are some assessment algorithms for the predictive analysis, but all of them have in common the fact that they are based on the classical gas formation theory. This work aims to analyze the use of decision trees (DTs) for the analysis of gases dissolved in mineral oil, also establishing a relationship associated with decision-making during the formation of trees and the formation of gases. In this way, some important aspects involving the insulating mineral oil can be better understood and quantified. For this purpose, two data sets containing 162 and 201 samples are used in the study. The results provided by the tree are arranged in a Cartesian plane and the gases are analyzed based on the ratios used by Doernenburg. DT is discussed in detail to validate the algorithm performance based on the classical gas formation theory.

MEMBROS DA BANCA:
Presidente - 289819 - OTACILIO DA MOTA ALMEIDA
Interno - 1789334 - ARYFRANCE ROCHA ALMEIDA
Interno - 1615907 - FABIO ROCHA BARBOSA
Interno - 1785470 - JOSE MARIA PIRES DE MENEZES JUNIOR