Artificial neural network based thermal model for a three-phase medium frequency transformer
Authors
Molinero Blanco, David; Santamargarita Mayor, Daniel; Bueno Peña, Emilio José; Marrón Romera, Marta; Vasic Matic, MiroslavIdentifiers
Permanent link (URI): http://hdl.handle.net/10017/61252DOI: 10.1109/ISIE51358.2023.10227917
ISBN: 979-8-3503-9971-4
Publisher
IEEE
Date
2023-06-19Embargo end date
2025-06-19Funders
Junta de Comunidades de Castilla-La Mancha
Universidad de Alcalá
Bibliographic citation
Molinero, D., Santamargarita, D., Bueno, E., Marrón, M. & Vasic, M. 2023, “Artificial neural network based thermal model for a three-phase medium frequency transformer”, in 2023 32nd International Symposium on Industrial Electronics (ISIE), Helsinki, Finland, 19-21 June 2023, pp 1-6.
Keywords
Artificial Neural Network
Medium Frequency Transformer
Three-phase Dual Active Bridge
Finite Element Method simulations
Thermal model
Description / Notes
32nd IEEE International Symposium on Industrial Electronics, 19/06/2023-21/06/2023, Helsinki, Finland.
Project
info:eu-repo/grantAgreement/JCCM//SBPLY%2F19%2F180501%2F000147
info:eu-repo/grantAgreement/UAH//CM-JIN-2021-019
Document type
info:eu-repo/semantics/conferenceObject
Version
info:eu-repo/semantics/acceptedVersion
Publisher's version
https://doi.org/10.1109/ISIE51358.2023.10227917Rights
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
© 2023 IEEE
Access rights
info:eu-repo/semantics/embargoedAccess
Abstract
This paper proposes an Artificial Neural Network (ANN) as a method to thermally analyze a three-phase medium frequency transformer (MFT). This transformer is part of a 50kW three-phase Dual Active Bridge (DAB). After choosing the most suitable architecture for the ANN, it is trained with the results of finite element method (FEM) simulations that model its behavior. The ANN is thus able to calculate temperature increments of the core and of each winding with high reliability. This performance of the ANN is studied by comparing its results with some other from widely used state-of-the-art theoretical thermal models that emulate the transformer?s thermal behavior. The neural network-based solution is proved to be as accurate as the FEM simulations ground truth, and as fast to apply as the theoretical thermal model, therefore fusing the advantage of using any of these two in power converter design optimization.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Artificial_David_ISIE_2023.pdf | 809.4Kb |
|
Files | Size | Format |
|
---|---|---|---|
Artificial_David_ISIE_2023.pdf | 809.4Kb |
|