A Transfer Ensemble Learning Method for Evaluating Power Transformer Health Conditions with Limited Measurement Data

Lin, J; Ma, J; Zhu, JG; Cui, Y

A Transfer Ensemble Learning Method for Evaluating Power Transformer Health Conditions with Limited Measurement Data

Lin, J Ma, J Zhu, JG Cui, Y

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Instrumentation and Measurement, 2022, 71
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	A_Transfer_Ensemble_Learning_Method_for_Evaluating_Power_Transformer_Health_Conditions_With_Limited_Measurement_Data.pdf	Published version	2.46 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, J
dc.contributor.author	Ma, J
dc.contributor.author	Zhu, JG
dc.contributor.author	Cui, Y
dc.date.accessioned	2023-03-19T23:40:44Z
dc.date.available	2023-03-19T23:40:44Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Transactions on Instrumentation and Measurement, 2022, 71
dc.identifier.issn	0018-9456
dc.identifier.issn	1557-9662
dc.identifier.uri	http://hdl.handle.net/10453/167627
dc.description.abstract	Health condition evaluation of power transformers is of great importance for the safe and reliable operation of power grids. The data-driven methods have been widely studied and applied. However, in practical applications, collecting high-quality data is difficult and expensive. Therefore, it is still challenging to build effective diagnostic models with insufficient labeled training data. This article proposes a transfer ensemble model to address this data scarcity problem. First, a 1-D convolutional neural network is pretrained using the large source-domain dataset. Then, the target model parameters are initialized with those of the source model and fine-tuned using the target dataset. A transfer strategy is proposed to decide what and where the diagnostic knowledge should be transferred from the source domain to the target domain. Finally, an ensemble model is built on the basis of a series of target models with different transfer strategies, which can further alleviate the overfitting issue and improve the generalization ability. The experimental results validate the effectiveness of the proposed method and show the feasibility of practical applications.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Instrumentation and Measurement
dc.relation.isbasedon	10.1109/TIM.2022.3175268
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0299 Other Physical Sciences, 0906 Electrical and Electronic Engineering
dc.subject.classification	Electrical & Electronic Engineering
dc.title	A Transfer Ensemble Learning Method for Evaluating Power Transformer Health Conditions with Limited Measurement Data
dc.type	Journal Article
utslib.citation.volume	71
utslib.for	0299 Other Physical Sciences
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-19T23:40:42Z
pubs.publication-status	Published
pubs.volume	71

Abstract:

Health condition evaluation of power transformers is of great importance for the safe and reliable operation of power grids. The data-driven methods have been widely studied and applied. However, in practical applications, collecting high-quality data is difficult and expensive. Therefore, it is still challenging to build effective diagnostic models with insufficient labeled training data. This article proposes a transfer ensemble model to address this data scarcity problem. First, a 1-D convolutional neural network is pretrained using the large source-domain dataset. Then, the target model parameters are initialized with those of the source model and fine-tuned using the target dataset. A transfer strategy is proposed to decide what and where the diagnostic knowledge should be transferred from the source domain to the target domain. Finally, an ensemble model is built on the basis of a series of target models with different transfer strategies, which can further alleviate the overfitting issue and improve the generalization ability. The experimental results validate the effectiveness of the proposed method and show the feasibility of practical applications.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167627