Transformer winding looseness diagnosis method based on multiple feature extraction and sparrow search algorithm optimized XGBoost

被引：2

作者：

Ma, Hongzhong ^{[1
]}

Xiao, Yusong ^{[1
]}

Yan, Jin ^{[2
]}

Sun, Yongteng ^{[1
]}

机构：

[1] College of Energy and Electrical Engineering, Hohai University, Nanjing

[2] Hengyang Power Supply Branch, State Grid Hunan Electric Power Co., Hengyang

来源：

Dianji yu Kongzhi Xuebao/Electric Machines and Control | 2024年 / 28卷 / 06期

关键词：

fault diagnosis; kernel principal component analysis; sparrow search algorithm; transformer vibration; winding looseness; XGBoost;

D O I：

10.15938/j.emc.2024.06.009

中图分类号：

学科分类号：

摘要：

In order to solve the problem of overlap and insufficient anti-interference ability under different load conditions in diagnosing transformer winding looseness using a single feature quantity, a vibration signal diagnosis method for transformer winding looseness based on kernel principal component analysis (KPCA) and extreme gradient boosting (XGBoost) optimized by improved sparrow search algorithm (SSA) was proposed. Firstly, feature quantities in vibration signals were extracted from three dimensions: time domain, frequency domain, and entropy; Then, the feature quantity was dimensionally reduced through grid search optimized KPCA; Finally, a fault diagnosis model based on XGBoost was constructed and sparrow search algorithm was used to optimize the parameters for achieving accurate identification of transformer winding looseness faults under different currents. The experimental verification was conducted on a 110 kV transformer. The diagnosis results show that the extracted feature quantities can accurately reflect the fault characteristics, have stronger anti-interference ability, and the diagnostic accuracy rate of the diagnostic model is 99. 00% . Compared with other diagnostic algorithms, the accuracy and stability are higher, and have good recognition effects under different load conditions. © 2024 Editorial Department of Electric Machines and Control. All rights reserved.

引用

页码：87 / 97

页数：10

共 32 条

[11]

ZHANG Lin, MA Hongzhong, JIANG Ning, Et al., Recognition and location of transformer winding looseness based on singular value spectrum entropy and SVM, Power System Protection and Control, 45, 18, (2017)

[12]

DU Houxian, LIU Hao, LEI Longwu, Et al., Power transformer fault detection based on multi-eigenvalues of vibration signal, Transaction of China Electrotechnical Society, 38, 1, (2023)

[13]

ZHAO Lihua, ZHANG Zhendong, ZHANG Jiangong, Et al., Diagnosis methods for transformer faults based on vibration signal under fluctuating operating conditions, High Voltage Engineering, 46, 11, (2020)

[14]

HONG K X, HUANG H, FU Y, Et al., A vibration measurement system for health monitoring of power transformers, Measurement, 93, (2016)

[15]

HONG K X, HUANG H, ZHOU J., Winding condition assessment of power transformers based on vibration correlation, IEEE Transactions on Power Delivery, 30, 4, (2015)

[16]

LI Nan, MA Hongzhong, ZHANG Yuliang, Et al., Voiceprint recognition of transformer internal mechanical state based on feature screening and improved deep forest, Electric Machines & Control Application, 49, 9, (2022)

[17]

ZHANG Youwen, FENG Bin, CHEN Ye, Et al., Fault diagnosis method for oil-immersed transformer based on XGBoost optimized by genetic algorithm, Electric Power Automation Equipment, 41, 2, (2021)

[18]

LI Xuan, MEI Fei, SHA Haoyuan, Et al., Operation state evaluation of UHV converter valve based on multi-state data equalization and XGBoost, High Voltage Engineering, 48, 2, (2022)

[19]

YAN Jin, MA Hongzhong, ZHU Hao, Et al., Diagnosis for transformer winding looseness based on LMD marginal spectrum energy entropy and FWA-SVM, Electrical Measurement & Instrumentation, 58, 11, (2021)

[20]

ZHANG Shimin, FENG Yao, Discrimination method of transformer core and winding fault based on vibration signal, Electrical Measurement & Instrumentation, 58, 6, (2021)

← 1 2 3 4 →