Georgia Southern University
Machine Learning Based Three-Limb Core-Type Transformer Core Aspect Ratios Identification
Abstract
dc:description.abstractPower transformers are considered one of the key elements of electric grids. Transient studies include transformer transient analysis which is required for the continuous power supply. However, to perform the transient analysis, the details of the internal structure of the transformer are required which are unobtainable and considered as confidential information. Therefore, the application of topological-based transformer models is limited although the models can accurately represent the transformers. To address this concern, a novel approach utilizing Machine Learning (ML) to identify the core aspect ratios of the three-limb core-type transformer is introduced. The proposed approach, using only the voltage and current measurements in the steady-state, no-load condition, employs the Extreme Gradient boosting (XGBoost) algorithm to identify the core aspect ratios. MATLAB/Simscape is used to model transformers. The results illustrate that the proposed algorithm is able to identify the core aspect ratios correctly.
Degree
thesis:*- Name thesis:degree_name
- Master of Science, Electrical Engineering
- Level thesis:degree_level
- Thesis (open access)
- Discipline thesis:degree_discipline
- Department of Electrical Engineering
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Bhadra, Ananta Bijoy
- Contributors dc:contributor
-
- Mohammad Ahad
- Fernando Rios
Subjects
dc:subject × 6Rights
- Licence dc:rights.license
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.georgiasouthern.edu/etd/2803