A Transformer Protection Method Based on Non-Inrush Feature Extraction of Differential Current Using Deep Metric Learning

HE Anyang; JIAO Zaibin

doi:10.7652/xjtuxb202605019

您当前的位置：

首页 >

文章列表页 >

A Transformer Protection Method Based on Non-Inrush Feature Extraction of Differential Current Using Deep Metric Learning

更新时间：2026-04-27

- A Transformer Protection Method Based on Non-Inrush Feature Extraction of Differential Current Using Deep Metric Learning
- Journal of Xi'an Jiaotong University Vol. 60, Issue 5, Pages: 194-205(2026)
- 作者机构：
  
  西安交通大学电气工程学院，710049，西安
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202605019
  CLC： TM77
- Received：17 June 2025，
  
  Published：10 May 2026
- 稿件说明：
移动端阅览
HE Anyang, JIAO Zaibin. A Transformer Protection Method Based on Non-Inrush Feature Extraction of Differential Current Using Deep Metric Learning[J]. Journal of Xi'an Jiaotong University, 2026, 60(5): 194-205.
DOI：

HE Anyang, JIAO Zaibin. A Transformer Protection Method Based on Non-Inrush Feature Extraction of Differential Current Using Deep Metric Learning[J]. Journal of Xi'an Jiaotong University, 2026, 60(5): 194-205. DOI： 10.7652/xjtuxb202605019.

摘要

为了避免励磁涌流对变压器故障识别的不利影响，提出一种利用改进深度度量学习提取差动电流非涌流特征的变压器智能保护方法。首先，受电力专家能够通过波形比较区分差动电流涌流部分和非涌流部分的启发，提出利用改进深度度量学习框架，以成对差动电流图像作为输入，最小化网络提取的正常差动电流与励磁涌流特征的差异以实现非涌流特征提取。其中，改进深度度量学习框架通过引入相似性鉴别损失，以避免经典深度度量学习损失中参数难以人工选取的问题。然后，基于提取的差动电流非涌流特征训练故障识别模块并构建变压器智能保护方法。最后，通过仿真及实验数据进行测试验证。结果表明：所提保护方法能够忽略励磁涌流干扰准确识别区内故障，对噪声、故障变压器合闸、电流互感器饱和、过励磁等场景均具有良好的适应性，其在各仿真场景下准确率均为100%，在实验场景下准确率达到99.20%，且满足变压器保护动作时间要求。

Abstract

To avoid the adverse effects of magnetizing inrush current on transformer fault identification

an intelligent transformer protection method based on non-inrush feature extraction of differential current using improved deep metric learning is proposed. First

inspired by the ability of power experts to distinguish between the inrush and non-inrush components of differential current through waveform comparison

the proposed method utilized an improved deep metric learning framework that takes paired differential current images as input and minimizes the feature differences between normal differential current and magnetizing inrush current

thereby achieving non-inrush feature extraction. The improved deep metric learning framework introduced a similarity discrimination loss to overcome the difficulty of manually selecting parameters in classical deep metric learning loss functions. Subsequently

based on the extracted non-inrush features of the differential current

a fault identification module was trained to construct the intelligent transformer protection method. Finally

the method was validated through simulations and experimental data. The results show that the proposed protection method can accurately identify internal faults while ignoring magnetizing inrush interference

demonstrating good adaptability in scenarios such as noise

transformer energization under fault conditions

current transformer saturation

and over-excitation. The method achieves an accuracy of 100% in all simulated scenarios and 99.20% in experimental scenarios

while also meeting the action time requirements for transformer protection.

关键词

Keywords

references

张保会，尹项根.电力系统继电保护[M].2版.北京：中国电力出版社，2010.

李晓.基于小波变换的励磁涌流识别方法研究[J].电工技术，2022（6）：144-145.

LI Xiao. Research on inrush current identification method based on wavelet transform[J].Electric Engineering，2022（6）：144-145.

张运驰，高厚磊，杜士昌.基于综合形态算法的变压器励磁涌流识别方法[J].电力系统自动化，2021，45（24）：165-173.

ZHANG Yunchi，GAO Houlei，DU Shichang.Identification method of transformer magnetizing inrush current based on comprehensive morphological algorithm[J]. Automation of Electric Power Systems，2021，45（24）：165-173.

宋九渊，符玲，熊思宇，等.基于二阶泰勒系数的励磁涌流识别方法[J].中国电机工程学报，2020，40（3）：1020-1029.

SONG Jiuyuan，FU Ling，XIONG Siyu，et al.Magnetizing inrush current identification method based on second-order Taylor derivative[J].Proceedings of the CSEE，2020，40（3）：1020-1029.

赵学文，付泽宇，李乐，等.基于VMD和PSO-SVM模型的和应涌流识别[J].电工技术，2021（19）：30-34.

ZHAO Xuewen，FU Zeyu，LI Le，et al.Sympathetic inrush current identification based on VMD and PSO-SVM model[J].Electric Engineering，2021（19）：30-34.

焦在滨，马涛，屈亚军，等.基于励磁电感参数识别的快速变压器保护[J].中国电机工程学报，2014，34（10）：1658-1666.

JIAO Zaibin，MA Tao，QU Yajun，et al.A novel excitation inductance-based power transformer protection scheme[J].Proceedings of the CSEE，2014，34（10）：1658-1666.

潘超，金明权，蔡国伟，等.基于漏感辨识的变压器交直流混合运行保护方法[J].电工技术学报，2018，33（4）：771-780.

PAN Chao，JIN Mingquan，CAI Guowei，et al.Protection for transformer in AC-DC hybrid operation mode based on leakage inductance identification[J]. Transactions of China Electrotechnical Society，2018，33（4）：771-780.

孙德娟，孙士云，范小红，等.基于励磁电感计算的双馈风电场送出变差动保护[J].电工技术学报，2020，35（2）：395-407.

SUN Dejuan，SUN Shiyun，FAN Xiaohong，et al.Doubly-fed wind farm outgoing transformer differential protection based on excitation inductance calculation[J]. Transactions of China Electrotechnical Society，2020，35（2）：395-407.

FAN Rui，LIU Yu，MELIOPOULOS S，et al.Comparison of transformer legacy protective functions and a dynamic state estimation-based approach [J].Electric Power Systems Research，2020，184：106301.

黄永红，马锋，沈敏.基于最小二乘支持向量机的变压器励磁涌流识别方法研究[J].电力系统保护与控制，2010，38（23）：93-96.

HUANG Yonghong，MA Feng，SHEN Min.Research of magnetizing inrush current identification method based on LS-SVM[J].Power System Protection and Control，2010，38（23）：93-96.

丁晓兵，周红阳，黄佳胤，等.基于逻辑斯蒂回归的变压器涌流识别[J].电力系统及其自动化学报，2020，32（12）：77-84.

DING Xiaobing，ZHOU Hongyang，HUANG Jiayin，et al.Transformer inrush current identification based on logistic regression[J].Proceedings of the CSU-EP-SA，2020，32（12）：77-84.

OZGONENEL O，KARAGOL S.Power transformer protection based on decision tree approach [J].IET Electric Power Applications，2014，8（7）：251-256.

李宗博，焦在滨，何安阳.基于等效磁化曲线智能识别的变压器保护原理[J].电工技术学报，2020，35（7）：1464-1475.

LI Zongbo，JIAO Zaibin，HE Anyang.Equivalent magnetization curve intelligent recognition based transformer protection[J].Transactions of China Electrotechnical Society，2020，35（7）：1464-1475.

俞小勇，秦丽文，桂海涛，等.新一代人工智能在配电网智能感知与故障诊断中的应用[J].南方电网技术，2022，16（5）：34-43.

YU Xiaoyong，QIN Liwen，GUI Haitao，et al.Application of new generation artificial intelligence technology in intelligent sensing and fault detection of power distribution network[J]. Southern Power System Technology，2022，16（5）：34-43.

AFRASIABI S，AFRASIABI M，PARANG B，et al. Integration of accelerated deep neural network into power transformer differential protection [J].IEEE Transactions on Industrial Informatics，2020，16（2）：865-876.

MURUGAN S K，SIMON S P，EAPEN R R.A novel signal localized convolution neural network for power transformer differential protection [J].IEEE Transactions on Power Delivery，2022，37（2）：1242-1251.

AFRASIABI S，AFRASIABI M，PARANG B，et al. Fast GRNN-based method for distinguishing inrush currents in power transformers [J].IEEE Transactions on Industrial Electronics，2022，69（8）：8501-8512.

张国栋，刘凯，蒲海涛，等.基于长短时记忆神经网络的励磁涌流与故障电流识别方法[J].上海交通大学学报，2024，58（5）：730-738.

ZHANG Guodong，LIU Kai，PU Haitao，et al.Identification of inrush current and fault current based on long short-term memory neural network[J].Journal of Shanghai Jiao Tong University，2024，58（5）：730-738.

LI Zongbo，JIAO Zaibin，HE Anyang，et al.A denoising-classification neural network for power transformer protection [J].Protection and Control of Modern Power Systems，2022，7（1）：52.

LIN Zexuan，YANG Songhao，ZHANG Yubo，et al. A data-aided power transformer differential protection without inrush blocking module [J].IEEE Transactions on Power Delivery，2023，38（3）：2000-2010.

韩笑，郭剑波，蒲天骄，等.电力人工智能技术理论基础与发展展望：（一）假设分析与应用范式[J].中国电机工程学报，2023，43（8）：2877-2890.

HAN Xiao，GUO Jianbo，PU Tianjiao，et al.Theoretical foundation and directions of electric power artificial intelligence：（Ⅰ）hypothesis analysis and application paradigm[J].Proceedings of the CSEE，2023，43（8）：2877-2890.

KAYA M，BILGE H S. Deep metric learning： a survey [J].Symmetry，2019，11（9）：1066.

刘冰，李瑞麟，封举富.深度度量学习综述[J].智能系统学报，2019，14（6）：1064-1072.

LIU Bing，LI Ruilin，FENG Jufu.A brief introduction to deep metric learning[J].CAAI Transactions on Intelligent Systems，2019，14（6）：1064-1072.

国家技术监督局.电能质量　公用电网谐波：GB/T 14549—1993 [S].北京：中国标准出版社，1993.

中华人民共和国国家质量监督检验检疫总局，中国国家标准化管理委员会.变压器保护装置通用技术要求：GB/T 14598.300—2017 [S].北京：中国标准出版社，2017.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Protection Methods for Offshore Wind Power Low-Frequency Transformers

On-Line Identification Algorithm for Transformer Leakage Inductance

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Influence of Structural Parameters on the Summer Operational Characteristics of a Three-Tower-in-One Indirect Air-Cooling System

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

Related Author

HE Anyang

JIAO Zaibin

GAO Shuping

JIA Taohui

SONG Guobing

WANG Chenqing

QUAN Zhe

ZHOU Yongning

Related Institution

School of Electrical Engineering, Xi’an Jiaotong University

School of Electrical and Control Engineering, Xi'an University of Science and Technology

Xi'an Key Laboratory of Electrical Equipment Condition Monitoring and Power Supply Security

Research Institute, State Grid Jiangsu Electric Power Co., Ltd.

⁰