Fault Identification Method for Transmission Line Based on Transfer Learning-AlexNet with Imbalanced Samples

WANG Jian; WU Hao; ZHANG Bo; NAN Dongliang; OUYANG Jinxin; XIONG Xiaofu

doi:10.7500/AEPS20211128001

您当前的位置：

首页 >

文章列表页 >

Fault Identification Method for Transmission Line Based on Transfer Learning-AlexNet with Imbalanced Samples

Application Research | 更新时间：2025-06-16

- Fault Identification Method for Transmission Line Based on Transfer Learning-AlexNet with Imbalanced Samples
- Automation of Electric Power Systems Vol. 46, Issue 22, Pages: 182-191(2022)
- 作者机构：
  
  1.输配电装备及系统安全与新技术国家重点实验室(重庆大学),重庆市 400044
  2.国网新疆电力有限公司电力科学研究院,新疆维吾尔自治区乌鲁木齐市 830011
- 作者简介：
- 基金信息：
  
  Abstract:
  When large-scale wind power are integrated to the grid in a centralized way, an N-1 fault in the sending transmission channel may overload the transmission lines and step-up transformers. However, the existing overload protection and stability and control strategies cannot adapt to this short-term power flow overload, so a large number of wind turbines need to be cut off, which is not conducive to wind power consumption. The paper analyzes the key parameters and safety boundaries of safety overload capacity for power equipment , and determines the long-term and short-term overload zones of transmission lines and transformers. According to the safety overload capacity of the equipment, the emergency overload operation strategy of the transmission channel is proposed, which is suitable for the grid connection of the wind farm cluster, including the heavy overload alarm based on the long-term overload zone, the wind turbine cutting-off and the over-limit-tripping due to the temperature rising of the equipment based on the short-term overload zone. The test results show that the proposed strategy is feasible, which can fully tap the overload capacity of the transmission channel and improve the wind power transmission capacity on the premise of ensuring the safe operation of the transmission channel.
  Foundation:This work is supported by National Natural Science Foundation of China(51707018);Research Foundation for Post-doctor Who Came to Chongqing(2020LY23)
- DOI：10.7500/AEPS20211128001
  CLC：
- Received：28 November 2021，
  
  Revised：2022-03-17，
  
  Published Online：18 July 2022，
  
  Published：25 November 2022
- 稿件说明：
移动端阅览
王建,吴昊,张博等.不平衡样本下基于迁移学习-AlexNet的输电线路故障辨识方法[J].电力系统自动化,2022,46(22):182-191.

WANG Jian,WU Hao,ZHANG Bo,et al.Fault Identification Method for Transmission Line Based on Transfer Learning-AlexNet with Imbalanced Samples[J].Automation of Electric Power Systems,2022,46(22):182-191.
王建,吴昊,张博等.不平衡样本下基于迁移学习-AlexNet的输电线路故障辨识方法[J].电力系统自动化,2022,46(22):182-191. DOI： 10.7500/AEPS20211128001.

WANG Jian,WU Hao,ZHANG Bo,et al.Fault Identification Method for Transmission Line Based on Transfer Learning-AlexNet with Imbalanced Samples[J].Automation of Electric Power Systems,2022,46(22):182-191. DOI： 10.7500/AEPS20211128001.

摘要

输电线路不同故障类型和故障原因的故障样本集具有类不平衡性，为基于图像深度学习的故障分类辨识带来挑战。文中提出类不平衡样本下基于迁移学习-AlexNet神经网络的输电线路故障辨识方法。首先，统计分析了输电线路故障的特征与概率分布，使用MATLAB/Simulink仿真产生了符合实际情况的不平衡故障样本集。然后，以故障暂态波形图像为输入集，采用迁移学习-AlexNet神经网络构建故障分类器，降低了故障特征提取的复杂性。算例测试结果表明，现有按类平衡故障样本集开展故障辨识的方法，分类准确率偏于乐观，即使采用抽样法也无法准确识别类不平衡样本中的小样本故障类型；而所提方法可以很好地应对类不平衡故障样本集，相比于经典的卷积神经网络，对故障类型与故障原因的辨识准确率也更高，训练模型用于类似线路的真实故障录波数据也能很好地辨识出故障类型。

Abstract

The fault sample sets of transmission lines with different fault types and fault causes have a characteristic of class imbalance

which brings challenges to fault classification and identification based on image deep learning. A fault identification method for transmission lines based on transfer learning-ALexNet neural network is proposed for class imbalanced samples. Firstly

the characteristics and probability distribution of transmission line faults are statistically analyzed

and an imbalanced fault sample set that conforms to the actual situation is generated using MATLAB/Simulink simulation. Then

using the fault transient waveform image as the input set

the fault classifier is constructed by transfer learning-AlexNet neural network

which reduces the complexity of fault feature extraction. The case test results show that the existing fault identification methods with class balanced fault sample sets have a speciously high classification accuracy. Even if the sampling method is adopted

the fault type of a small sample in the class imbalanced sample cannot be accurately identified. However

the proposed method can give a better solution to the class imbalanced fault sample set. Compared with the classical convolutional neural network

the identification accuracy of the fault type and fault cause with the proposed method is also better. The training model used for the real fault recording data of similar lines can also identify the fault types well.

关键词

Keywords

references

彭向阳，钱冠军，李鑫，等 . 架空输电线路跳闸故障智能诊断［J］. 高电压技术， 2012 ， 38 （ 8 ）： 1965 - 1972 .

PENG Xiangyang ， QIAN Guanjun ， LI Xin ， et al . Intelligent trip-out fault diagnosis of overhead transmission line ［J］. High Voltage Engineering ， 2012 ， 38 （ 8 ）： 1965 - 1972 .

徐舒玮，邱才明，张东霞，等 . 基于深度学习的输电线路故障类型辨识［J］. 中国电机工程学报， 2019 ， 39 （ 1 ）： 65 - 74 .

XU Shuwei ， QIU Caiming ， ZHANG Dongxia ， et al . A deep learning approach for fault type identification of transmission line ［J］. Proceedings of the CSEE ， 2019 ， 39 （ 1 ）： 65 - 74 .

任萱，王宾，俞斌，等 . LCC-HVDC逆变侧换流站近区交流线路高阻接地故障保护［J］. 电力系统自动化， 2021 ， 45 （ 23 ）： 162 - 169 .

REN Xuan ， WANG Bin ， YU Bin ， et al . High resistance grounding fault protection of ac line near converter station at inverter side of LCC-HVDC ［J］. Automation of Electric Power Systems ， 2021 ， 45 （ 23 ）： 162 - 169 .

SALEHI M ， NAMDARI F . Fault classification and faulted phase selection for transmission line using morphological edge detection filter ［J］. IET Generation ， Transmission & Distribution， 2018 ， 12 （ 7 ）： 1595 - 1605 .

MINNAAR U J ， NICOLLS F ， GAUNT C T . Automating transmission-line fault root cause analysis ［J］. IEEE Transactions on Power Delivery ， 2016 ， 31 （ 4 ）： 1692 - 1700 .

WIJEKOON J ， RAJAPAKSE A D ， HALEEM N M . Fast and reliable method for identifying fault type and faulted phases using band limited transient currents ［J］. IEEE Transactions on Power Delivery ， 2021 ， 36 （ 5 ）： 2839 - 2850 .

FAHIM S R ， SARKER Y ， SARKER S K ， et al . Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification ［J］. Electric Power Systems Research ， 2020 ， 187 ： 106437 .

杨毅，范栋琛，殷浩然，等 . 基于深度-迁移学习的输电线路故障选相模型及其可迁移性研究［J］. 电力自动化设备， 2020 ， 40 （ 10 ）： 165 - 172 .

YANG Yi ， FAN Dongchen ， YIN Haoran ， et al . Transmission line fault phase selection model based on deep-transfer learning and its transferability ［J］. Electric Power Automation Equipment ， 2020 ， 40 （ 10 ）： 165 - 172 .

饶超平，肖博文，严星，等 . 基于Seq2Seq技术的输电线路故障类型识别方法［J］. 智慧电力， 2020 ， 48 （ 5 ）： 99 - 105 .

RAO Chaoping ， XIAO Bowen ， YAN Xing ， et al . Fault type recognition method of transmission line based on Seq2Seq technology ［J］. Smart Power ， 2020 ， 48 （ 5 ）： 99 - 105 .

顾婷 . 基于双端行波法的多端输电线故障测距研究［D］. 淮南：安徽理工大学， 2017 .

GU Ting . Research on fault location of multi-terminal transmission line based on double terminal traveling wave method ［D］. Huainan ： Anhui University of Science & Technology ， 2017 .

杜文 . 基于录波数据和深度学习的输电线路故障起因辨识［D］. 济南：山东大学， 2020 .

DU Wen . Fault cause identification for transmission lines based on recorded data and deep learning ［D］. Jinan ： Shandong University ， 2020 .

王浩，杨东升，周博文，等 . 基于并联卷积神经网络的多端直流输电线路故障诊断［J］. 电力系统自动化， 2020 ， 44 （ 12 ）： 84 - 92 .

WANG Hao ， YANG Dongsheng ， ZHOU Bowen ， et al . Fault diagnosis of multi-terminal HVDC transmission line based on parallel convolutional neural network ［J］. Automation of Electric Power Systems ， 2020 ， 44 （ 12 ）： 84 - 92 .

GODSE R ， BHAT S . Mathematical morphology-based feature-extraction technique for detection and classification of faults on power transmission line ［J］. IEEE Access ， 2020 ， 8 ： 38459 - 38471 .

ABDULLAH A . Ultrafast transmission line fault detection using a DWT-based ANN ［J］. IEEE Transactions on Industry Applications ， 2018 ， 54 （ 2 ）： 1182 - 1193 .

付华，金岑 . VMD-PE协同SNN的输电线路故障辨识方法［J］. 电子测量与仪器学报， 2020 ， 34 （ 6 ）： 86 - 92 .

FU Hua ， JIN Cen . Fault identification method of transmission lines based on VMD-PE and SNN ［J］. Journal of Electronic Measurement and Instrumentation ， 2020 ， 34 （ 6 ）： 86 - 92 .

TAN P ， STEINBACH M ， KARPATNE A ， et al . Introduction to data mining ［M］. London， UK ： Person ， 2019 .

黄景林，彭显刚，简胜超，等 . 基于深度学习与不平衡样本集的输电线路故障分类［J］. 智慧电力， 2021 ， 49 （ 2 ）： 114 - 119 .

HUANG Jinglin ， PENG Xiangang ， JIAN Shengchao ， et al . Transmission line fault classification based on deep learning and imbalanced sample set ［J］. Smart Power ， 2021 ， 49 （ 2 ）： 114 - 119 .

高侠 . 输电线路高阻接地故障检测装置的研究与设计［D］. 南昌：南昌大学， 2015 .

GAO Xia . Research and design of high-impedance-grounded fault detecting device in transmission line ［D］. Nanchang ： Nanchang University ， 2015 .

黄戬 . 输电线路故障类型辨识研究［D］. 广州：华南理工大学， 2014 .

HUANG Jian . Research on fault type identification of transmission line ［D］. Guangzhou ： South China University of Technology ， 2014 .

ZHANG H ， CHE R F . Fault cause identification based on characteristics of transition resistances for transmission lines ［C］// 2015 5th International Conference on Electric Utility Deregulation and Restructuring and Power Technologies （DRPT）， November 26-29 ， 2015 ， Changsha， China ： 1405 - 1409 .

李离南 . 高压交流输电线路故障特征挖掘与故障原因辨识［D］. 济南：山东大学， 2017 .

LI Linan . Fault feature mining and fault cause identification for HVAC transmission lines ［D］. Jinan ： Shandong University ， 2017 .

王建，熊小伏，梁允，等 . 地理气象相关的输电线路风险差异评价方法及指标［J］. 中国电机工程学报， 2016 ， 36 （ 5 ）： 1252 - 1259 .

WANG Jian ， XIONG Xiaofu ， LIANG Yun ， et al . Geographical and meteorological factor related transmission line risk difference assessment： method and indexes ［J］. Proceedings of the CSEE ， 2016 ， 36 （ 5 ）： 1252 - 1259 .

KRIZHEVSKY A ， SUTSKEVER I ， HINTON G E . ImageNet classification with deep convolutional neural networks ［J］. Communications of the ACM ， 2017 ， 60 （ 6 ）： 84 - 90 .

唐贵基，田寅初，田甜 . 基于AlexNet-Adaboost的多工况滚动轴承故障识别方法［J］. 振动与冲击， 2022 ， 41 （ 2 ）： 20 - 25 .

TANG Guiji ， TIAN Yinchu ， TIAN Tian . Multi-working condition rolling bearing fault identification method based on the AlexNet-Adaboost algorithm ［J］. Journal of Vibration and Shock ， 2022 ， 41 （ 2 ）： 20 - 25 .

郑玉平，司鑫尧，吴通华，等 . 特高压半波长交流输电线路的行波保护［J］. 电力系统自动化， 2020 ， 44 （ 18 ）： 124 - 131 .

ZHENG Yuping ， SI Xinyao ， WU Tonghua ， et al . Travelling wave protection of UHV half-wavelength AC transmission lines ［J］. Automation of Electric Power Systems ， 2020 ， 44 （ 18 ）： 124 - 131 .

DOS SANTOS A ， GASPAR C ， DE BARROS M T C ， et al . Transmission line fault resistance values based on field data ［J］. IEEE Transactions on Power Delivery ， 2020 ， 35 （ 3 ）： 1321 - 1329 .

王晋东，陈益强 . 迁移学习导论［M］. 北京：电子工业出版社， 2021 .

WANG Jindong ， CHEN Yiqiang . Introduction of transfer learning ［M］. Beijing ： Publishing House of Electronics Industry ， 2021 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Adaptive Short-term Wind Power Forecasting Under Extreme Weather Events Based on Transfer Learning and Autoencoder

Evaluation of Compound-disaster Failure Rate for Transmission Lines from Perspective of Whole Reductionism Thinking —Part Two Algorithm and Application

Related Author

Jian WANG

Hao WU

Bo ZHANG

Dongliang NAN

Jinxin OUYANG

Xiaofu XIONG

ZHANG Guangbin

SHU Banggui

Related Institution

Faculty of Electric Power Engineering, Kunming University of Science and Technology

Yunnan Grid Research Construction and Planning Center of Yunnan Power Grid Co., Ltd.

School of New Energy, North China Electric Power University

School of Electrical Engineering and Automation, Harbin Institute of Technology

State Grid Electric Power Research Institute (NARI Group Corporation)

⁰