UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network

Partial discharge (PD) detection and localization is an important means for condition monitoring and diagnosis of power equipment. The existing time-difference based ultra-high frequency (UHF) PD localization techniques are limited in application due to their high costs. A novel PD localization meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Qichen YU, Lingen LUO, Fan WU, Gehao SHENG, Xiuchen JIANG
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2021-02-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202005016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226472235565056
author Qichen YU
Lingen LUO
Fan WU
Gehao SHENG
Xiuchen JIANG
author_facet Qichen YU
Lingen LUO
Fan WU
Gehao SHENG
Xiuchen JIANG
author_sort Qichen YU
collection DOAJ
description Partial discharge (PD) detection and localization is an important means for condition monitoring and diagnosis of power equipment. The existing time-difference based ultra-high frequency (UHF) PD localization techniques are limited in application due to their high costs. A novel PD localization method is proposed based on generalized regression neural network (GRNN) and received signal strength indicator (RSSI) fingerprint, which consists of two stages. In the off-line stage of algorithm, a RSSI fingerprint map is built. In the on-line stage, the GRNN is used to calculate the position of the PD source. The field testing shows that the proposed UHF PD localization method has an average localization error of 0.51 m, and a cumulative probability of 81.6% for the localization error of less than 1 m. Compared to the minimum mean square error (MSE) of the Cramér-Rao lower bound (CRLB), which is based on RSSI log normal shadowing model positioning method, the cumulative probability of the GRNN localization error with the mean square error less than 0.6 m2 is 66.7%, which is better than CRLB. The proposed method overcomes the shortcomings of low positioning accuracy and high costs of the traditional methods, and has the characteristics of low hardware cost and good environmental adaptability.
format Article
id doaj-art-e8012ebbbd214f9d854b1e7a377b49c8
institution OA Journals
issn 1004-9649
language zho
publishDate 2021-02-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-e8012ebbbd214f9d854b1e7a377b49c82025-08-20T02:05:04ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492021-02-01542111710.11930/j.issn.1004-9649.202005016zgdl-54-2-yuqichenUHF Partial Discharge Localization Methodology Based on Generalized Regression Neural NetworkQichen YU0Lingen LUO1Fan WU2Gehao 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, ChinaPartial discharge (PD) detection and localization is an important means for condition monitoring and diagnosis of power equipment. The existing time-difference based ultra-high frequency (UHF) PD localization techniques are limited in application due to their high costs. A novel PD localization method is proposed based on generalized regression neural network (GRNN) and received signal strength indicator (RSSI) fingerprint, which consists of two stages. In the off-line stage of algorithm, a RSSI fingerprint map is built. In the on-line stage, the GRNN is used to calculate the position of the PD source. The field testing shows that the proposed UHF PD localization method has an average localization error of 0.51 m, and a cumulative probability of 81.6% for the localization error of less than 1 m. Compared to the minimum mean square error (MSE) of the Cramér-Rao lower bound (CRLB), which is based on RSSI log normal shadowing model positioning method, the cumulative probability of the GRNN localization error with the mean square error less than 0.6 m2 is 66.7%, which is better than CRLB. The proposed method overcomes the shortcomings of low positioning accuracy and high costs of the traditional methods, and has the characteristics of low hardware cost and good environmental adaptability.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202005016partial dischargerssi fingerprintgrnnlog normal shadowing modelpositioning technology
spellingShingle Qichen YU
Lingen LUO
Fan WU
Gehao SHENG
Xiuchen JIANG
UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
Zhongguo dianli
partial discharge
rssi fingerprint
grnn
log normal shadowing model
positioning technology
title UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
title_full UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
title_fullStr UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
title_full_unstemmed UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
title_short UHF Partial Discharge Localization Methodology Based on Generalized Regression Neural Network
title_sort uhf partial discharge localization methodology based on generalized regression neural network
topic partial discharge
rssi fingerprint
grnn
log normal shadowing model
positioning technology
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202005016
work_keys_str_mv AT qichenyu uhfpartialdischargelocalizationmethodologybasedongeneralizedregressionneuralnetwork
AT lingenluo uhfpartialdischargelocalizationmethodologybasedongeneralizedregressionneuralnetwork
AT fanwu uhfpartialdischargelocalizationmethodologybasedongeneralizedregressionneuralnetwork
AT gehaosheng uhfpartialdischargelocalizationmethodologybasedongeneralizedregressionneuralnetwork
AT xiuchenjiang uhfpartialdischargelocalizationmethodologybasedongeneralizedregressionneuralnetwork