Modified FEA and ExtraTree algorithm for transformer Green's function modelling

Research output: Chapter in Book/Conference paperConference paper

Abstract

The Green's function of a transformer is essential for prediction of its vibration. As the Green's function cannot be measured directly and completely, the finite element analysis (FEA) is typically used for its estimation. However, because of the complexity of the transformer structure, the calculations involved in FEA are time consuming. Therefore, in this paper, a method based on FEA modified by an extremely random tree algorithm call ExtraTree is proposed to efficiently estimate the Green's function of a transformer. A subset of the frequency response functions from FEA will be selected by a genetic algorithm that can well present the structural variation. The FEA calculation time can be reduced by simply calculating the frequency response functions on this subset and predicting remainder using the trained ExtraTree model. The errors introduced in this method can be estimated from the corresponding frequency and the genetic algorithm error.

Original languageEnglish
Title of host publicationINTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering
Subtitle of host publicationTaming Noise and Moving Quiet
Place of PublicationUnited States
PublisherInstitute of Noise Control Engineering
Pages1538-1545
Publication statusPublished - 1 Jan 2017
Event46th International Congress and Exposition on Noise Control Engineering - Hong Kong, China
Duration: 27 Aug 201730 Aug 2017

Conference

Conference46th International Congress and Exposition on Noise Control Engineering
CountryChina
CityHong Kong
Period27/08/1730/08/17

Fingerprint

transformers
Green's functions
genetic algorithms
frequency response
set theory
vibration
estimates
predictions

Cite this

Du, X., & Pan, J. (2017). Modified FEA and ExtraTree algorithm for transformer Green's function modelling. In INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering: Taming Noise and Moving Quiet (pp. 1538-1545). United States: Institute of Noise Control Engineering.
Du, Xuhao ; Pan, Jie. / Modified FEA and ExtraTree algorithm for transformer Green's function modelling. INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering: Taming Noise and Moving Quiet. United States : Institute of Noise Control Engineering, 2017. pp. 1538-1545
@inproceedings{5316ab07b3a645a3b81260862d2b3794,
title = "Modified FEA and ExtraTree algorithm for transformer Green's function modelling",
abstract = "The Green's function of a transformer is essential for prediction of its vibration. As the Green's function cannot be measured directly and completely, the finite element analysis (FEA) is typically used for its estimation. However, because of the complexity of the transformer structure, the calculations involved in FEA are time consuming. Therefore, in this paper, a method based on FEA modified by an extremely random tree algorithm call ExtraTree is proposed to efficiently estimate the Green's function of a transformer. A subset of the frequency response functions from FEA will be selected by a genetic algorithm that can well present the structural variation. The FEA calculation time can be reduced by simply calculating the frequency response functions on this subset and predicting remainder using the trained ExtraTree model. The errors introduced in this method can be estimated from the corresponding frequency and the genetic algorithm error.",
keywords = "ExtraTree, FEA, Green's function, Optimisation, Transformer",
author = "Xuhao Du and Jie Pan",
year = "2017",
month = "1",
day = "1",
language = "English",
pages = "1538--1545",
booktitle = "INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering",
publisher = "Institute of Noise Control Engineering",
address = "United States",

}

Du, X & Pan, J 2017, Modified FEA and ExtraTree algorithm for transformer Green's function modelling. in INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering: Taming Noise and Moving Quiet. Institute of Noise Control Engineering, United States, pp. 1538-1545, 46th International Congress and Exposition on Noise Control Engineering, Hong Kong, China, 27/08/17.

Modified FEA and ExtraTree algorithm for transformer Green's function modelling. / Du, Xuhao; Pan, Jie.

INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering: Taming Noise and Moving Quiet. United States : Institute of Noise Control Engineering, 2017. p. 1538-1545.

Research output: Chapter in Book/Conference paperConference paper

TY - GEN

T1 - Modified FEA and ExtraTree algorithm for transformer Green's function modelling

AU - Du, Xuhao

AU - Pan, Jie

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The Green's function of a transformer is essential for prediction of its vibration. As the Green's function cannot be measured directly and completely, the finite element analysis (FEA) is typically used for its estimation. However, because of the complexity of the transformer structure, the calculations involved in FEA are time consuming. Therefore, in this paper, a method based on FEA modified by an extremely random tree algorithm call ExtraTree is proposed to efficiently estimate the Green's function of a transformer. A subset of the frequency response functions from FEA will be selected by a genetic algorithm that can well present the structural variation. The FEA calculation time can be reduced by simply calculating the frequency response functions on this subset and predicting remainder using the trained ExtraTree model. The errors introduced in this method can be estimated from the corresponding frequency and the genetic algorithm error.

AB - The Green's function of a transformer is essential for prediction of its vibration. As the Green's function cannot be measured directly and completely, the finite element analysis (FEA) is typically used for its estimation. However, because of the complexity of the transformer structure, the calculations involved in FEA are time consuming. Therefore, in this paper, a method based on FEA modified by an extremely random tree algorithm call ExtraTree is proposed to efficiently estimate the Green's function of a transformer. A subset of the frequency response functions from FEA will be selected by a genetic algorithm that can well present the structural variation. The FEA calculation time can be reduced by simply calculating the frequency response functions on this subset and predicting remainder using the trained ExtraTree model. The errors introduced in this method can be estimated from the corresponding frequency and the genetic algorithm error.

KW - ExtraTree

KW - FEA

KW - Green's function

KW - Optimisation

KW - Transformer

UR - http://www.scopus.com/inward/record.url?scp=85042100884&partnerID=8YFLogxK

M3 - Conference paper

SP - 1538

EP - 1545

BT - INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering

PB - Institute of Noise Control Engineering

CY - United States

ER -

Du X, Pan J. Modified FEA and ExtraTree algorithm for transformer Green's function modelling. In INTER-NOISE 2017 - 46th International Congress and Exposition on Noise Control Engineering: Taming Noise and Moving Quiet. United States: Institute of Noise Control Engineering. 2017. p. 1538-1545