Power Transformer Operating State Prediction Method Based on an LSTM Network

The state of transformer equipment is usually manifested through a variety of information. The characteristic information will change with different types of equipment defects/faults, location, severity, and other factors. For transformer operating state prediction and fault warning, the key influen...

Full description

Bibliographic Details
Main Authors:	Hui Song, Jiejie Dai, Lingen Luo, Gehao Sheng, Xiuchen Jiang
Format:	Article
Language:	English
Published:	MDPI AG 2018-04-01
Series:	Energies
Subjects:	power transformer state prediction data-driven method long short-term memory network state panoramic information
Online Access:	http://www.mdpi.com/1996-1073/11/4/914

id	doaj-0c10c58fb01c4f73965c72dfa3de6121
record_format	Article
spelling	doaj-0c10c58fb01c4f73965c72dfa3de61212020-11-24T23:48:00ZengMDPI AGEnergies1996-10732018-04-0111491410.3390/en11040914en11040914Power Transformer Operating State Prediction Method Based on an LSTM NetworkHui Song0Jiejie Dai1Lingen Luo2Gehao Sheng3Xiuchen Jiang4Department of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaDepartment of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaDepartment of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaDepartment of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaDepartment of Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, ChinaThe state of transformer equipment is usually manifested through a variety of information. The characteristic information will change with different types of equipment defects/faults, location, severity, and other factors. For transformer operating state prediction and fault warning, the key influencing factors of the transformer panorama information are analyzed. The degree of relative deterioration is used to characterize the deterioration of the transformer state. The membership relationship between the relative deterioration degree of each indicator and the transformer state is obtained through fuzzy processing. Through the long short-term memory (LSTM) network, the evolution of the transformer status is extracted, and a data-driven state prediction model is constructed to realize preliminary warning of a potential fault of the equipment. Through the LSTM network, the quantitative index and qualitative index are organically combined in order to perceive the corresponding relationship between the characteristic parameters and the operating state of the transformer. The results of different time-scale prediction cases show that the proposed method can effectively predict the operation status of power transformers and accurately reflect their status.http://www.mdpi.com/1996-1073/11/4/914power transformerstate predictiondata-driven methodlong short-term memory networkstate panoramic information
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Hui Song Jiejie Dai Lingen Luo Gehao Sheng Xiuchen Jiang
spellingShingle	Hui Song Jiejie Dai Lingen Luo Gehao Sheng Xiuchen Jiang Power Transformer Operating State Prediction Method Based on an LSTM Network Energies power transformer state prediction data-driven method long short-term memory network state panoramic information
author_facet	Hui Song Jiejie Dai Lingen Luo Gehao Sheng Xiuchen Jiang
author_sort	Hui Song
title	Power Transformer Operating State Prediction Method Based on an LSTM Network
title_short	Power Transformer Operating State Prediction Method Based on an LSTM Network
title_full	Power Transformer Operating State Prediction Method Based on an LSTM Network
title_fullStr	Power Transformer Operating State Prediction Method Based on an LSTM Network
title_full_unstemmed	Power Transformer Operating State Prediction Method Based on an LSTM Network
title_sort	power transformer operating state prediction method based on an lstm network
publisher	MDPI AG
series	Energies
issn	1996-1073
publishDate	2018-04-01
description	The state of transformer equipment is usually manifested through a variety of information. The characteristic information will change with different types of equipment defects/faults, location, severity, and other factors. For transformer operating state prediction and fault warning, the key influencing factors of the transformer panorama information are analyzed. The degree of relative deterioration is used to characterize the deterioration of the transformer state. The membership relationship between the relative deterioration degree of each indicator and the transformer state is obtained through fuzzy processing. Through the long short-term memory (LSTM) network, the evolution of the transformer status is extracted, and a data-driven state prediction model is constructed to realize preliminary warning of a potential fault of the equipment. Through the LSTM network, the quantitative index and qualitative index are organically combined in order to perceive the corresponding relationship between the characteristic parameters and the operating state of the transformer. The results of different time-scale prediction cases show that the proposed method can effectively predict the operation status of power transformers and accurately reflect their status.
topic	power transformer state prediction data-driven method long short-term memory network state panoramic information
url	http://www.mdpi.com/1996-1073/11/4/914
work_keys_str_mv	AT huisong powertransformeroperatingstatepredictionmethodbasedonanlstmnetwork AT jiejiedai powertransformeroperatingstatepredictionmethodbasedonanlstmnetwork AT lingenluo powertransformeroperatingstatepredictionmethodbasedonanlstmnetwork AT gehaosheng powertransformeroperatingstatepredictionmethodbasedonanlstmnetwork AT xiuchenjiang powertransformeroperatingstatepredictionmethodbasedonanlstmnetwork
_version_	1725487768053743616

Power Transformer Operating State Prediction Method Based on an LSTM Network

Similar Items