Título
Hot-spot temperature forecasting of the instrument transformer using an artificial neural network
Autor
EDGAR ALFREDO JUÁREZ BALDERAS
Joselito Medina-Marin
Juan C. Olivares-Galvan
Norberto Hernández Romero
Juan Carlos Seck Tuoh Mora
Alejandro Rodriguez-Aguilar
Nivel de Acceso
Acceso Abierto
Identificador alterno
pissn: 2169-3536
doi: 10.1109/ACCESS.2020.3021673
https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639
Materias
Artificial neural networks - (PALABRA CLAVE DEL AUTOR) Resin-cast instrument transformer - (PALABRA CLAVE DEL AUTOR) Epoxy resins - (PALABRA CLAVE DEL AUTOR) Finite element analysis - (PALABRA CLAVE DEL AUTOR) INGENIERÍA Y TECNOLOGÍA - (CTI) CIENCIAS TECNOLÓGICAS - (CTI) TECNOLOGÍA DE LOS ORDENADORES - (CTI) INTELIGENCIA ARTIFICIAL - (CTI) INTELIGENCIA ARTIFICIAL - (CTI)
Resumen o descripción
Cast resin medium voltage instrument transformer are highly used because of several benefits over other type of transformers. Nevertheless, the high operating temperatures affects their performance and durability. It is important to forecast the hot spots in the transformer. The aim of this study is to develop a model based on Artificial Neural Networks (ANN) theory to be able to forecast the temperature in seven points, taking into account twenty-six input data of transformer design features. 792 simulations were carried out in COMSOL Multiphysics® to emulate the heat transfer in the transformer. The data obtained were used to train 1110 ANN with different number of neurons and hidden layers. The ANN with the best performance (R D 1, MSE D 0.003455) has three hidden layers with 10, 9 and 9 neurons respectively. The ANN predictions were validated with finite element simulations and laboratory thermal tests which present similar patterns. With this accuracy in the prediction of hot-spot temperature, this ANN can be used to optimize the design of instrument transformers.
This work was supported in part by the Consejo Nacional de Ciencia y Tecnología (CONACYT) in coordination with the Postgrado de CIATEQ, A. C., Mexico; in part by the Universidad Autónoma del Estado de Hidalgo under Project CONACYT CB-2017-2018-A1-S-43008; in part by the Universidad Autónoma Metropolitana; and in part by the company Arteche North America, S. A. de C. V.
Editor
IEEE
Fecha de publicación
2020
Tipo de publicación
Artículo
Versión de la publicación
Versión publicada
Recurso de información
Formato
application/pdf
Fuente
IEEE Access, v. 8, p. 164392-164406
Idioma
Inglés
Relación
&
Rodriguez-Aguilar, A. (2020). Hot-spot temperature forecasting of the instrument transformer using an artificial neural network. IEEE Access, 8, 164392-164406. https://doi.org/10.1109/ACCESS.2020.3021673
Audiencia
Público en general
Sugerencia de citación
Juarez-Balderas, E. A., Medina-Marin, J., Olivares-Galvan, J. C., Hernandez-Romero, N., Seck-Tuoh-Mora, J. C.,
Repositorio Orígen
CIATEQ Digital
Descargas
638