Fault Recognition of On-load Tap-changer in Power Transformer Based on Convolutional Neural Network

Quanhao ZENG; Fenghua WANG; Yiming ZHENG; Wenlin HE

doi:10.7500/AEPS20191108003

您当前的位置：

首页 >

文章列表页 >

Fault Recognition of On-load Tap-changer in Power Transformer Based on Convolutional Neural Network

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

- Fault Recognition of On-load Tap-changer in Power Transformer Based on Convolutional Neural Network
- Automation of Electric Power Systems Vol. 44, Issue 11, Pages: 144-151(2020)
- 作者机构：
  
  1.上海交通大学电子信息与电气工程学院，上海市 200240
  2.国网浙江省电力有限公司电力科学研究院，浙江省杭州市 310014
- 作者简介：
- 基金信息：
  
  National Key R&D Program of China;Sate Grid Zhejiang Electric Power Co., Ltd
- DOI：10.7500/AEPS20191108003
  CLC：
- Received：08 November 2019，
  
  Revised：2020-02-10，
  
  Published Online：03 April 2020，
  
  Published：10 June 2020
- 稿件说明：
移动端阅览
曾全昊,王丰华,郑一鸣等.基于卷积神经网络的变压器有载分接开关故障识别[J].电力系统自动化,2020,44(11):144-151.

ZENG Quanhao,WANG Fenghua,ZHENG Yiming,et al.Fault Recognition of On-load Tap-changer in Power Transformer Based on Convolutional Neural Network[J].Automation of Electric Power Systems,2020,44(11):144-151.
曾全昊,王丰华,郑一鸣等.基于卷积神经网络的变压器有载分接开关故障识别[J].电力系统自动化,2020,44(11):144-151. DOI： 10.7500/AEPS20191108003.

ZENG Quanhao,WANG Fenghua,ZHENG Yiming,et al.Fault Recognition of On-load Tap-changer in Power Transformer Based on Convolutional Neural Network[J].Automation of Electric Power Systems,2020,44(11):144-151. DOI： 10.7500/AEPS20191108003.

摘要

为进一步提高变压器有载分接开关(OLTC)故障识别的精度，从OLTC切换过程中振动信号递归图的纹理特征出发，提出了一种基于卷积神经网络(CNN)的变压器OLTC故障识别方法。首先根据OLTC振动信号的相空间分布，基于相点距离映射构建了OLTC振动信号的距离映射递归图(DMRP)，然后通过合理选取CNN的网络层数、卷积核尺寸等结构超参数和对卷积核进行降维处理，提出了基于CNN的OLTC故障识别模型。对某CM型OLTC正常与典型故障下振动信号的计算结果表明，DMRP能自适应地对振动信号的相空间相点分布进行描述，所提出的识别模型对OLTC的典型故障均具有良好的识别性能，尤其在轻微故障的识别上相比于现有方法准确率提升了至少10%。

Abstract

To further improve the fault recognition accuracy of on-load tap-changer (OLTC) of power transformer

this paper presents a fault recognition method of OLTC based on convolutional neural network (CNN) considering the texture features of recurrence plot for vibration signal during the switching process of OLTC. The distance mapping recurrence plot (DMRP) is constructed by using the phase point distance mapping according to the phase space distribution of vibration signals for OLTC. Then a CNN based OLTC fault recognition model is proposed by reasonably selecting the structure hyper-parameters of CNN

including the number of network layers and convolution kernel size

and reducing the convolution kernel dimensionality. The calculation results of vibration signals from a CM type OLTC under normal and typical mechanical fault conditions show that the DMRP can adaptively describe the point distribution of the vibration signals in phase space. The recognition model has excellent recognition performance on OLTC typical faults. Especially

the recognition rate of slight fault is improved by at least 10% compared with the existing methods.

关键词

Keywords

references

段若晨，王丰华，周荔丹，等 . 利用窄带噪声辅助多元经验模态分解算法检测换流变压器用有载分接开关机械状态 [J]. 电工技术学报， 2017 ， 32 ( 10 )： 182 - 189 .

DUAN Ruochen , WANG Fenghua , ZHOU Lidan , et al . Mechanical condition detection on on-load tap-changer in converter transformer based on narrowband noise assisted multivariate empirical mode decomposition algorithm [J]. Transactions of China Electrotechnical Society , 2017 , 32 ( 10 ): 182 - 189 .

ZHENG Yiming , HE Wenlin , WANG Fenghua . Vibration monitoring of converter transformer onload tap-changer using phase space reconstruction and Poincare section [C]// 2017 4th International Conference on ICEPE-ST , October 22 - 25 , 2017 , Xi’an, China: 365 - 369 .

KANG P , BIRTWHISTLE D . Condition monitoring of power transformer on-load tap-changers: Part Ⅰ Automatic condition diagnostics [J]. IEE Proceedings: Generation , Transmission and Distribution , 2001 , 148 ( 4 ): 301 - 306 .

KANG P , BIRTWHISTLE D . Condition monitoring of power transformer on-load tap-changers: Part Ⅱ detection of ageing from vibration signatures [J]. IEE Proceedings: Generation , Transmission and Distribution , 2001 , 148 ( 4 ): 307 - 311 .

KANG P , BIRTWHISTLE D . Condition assessment of power transformer on load tap changers using wavelet analysis and self-organizing map: field evaluation [J]. IEEE Transactions on Power Delivery , 2003 , 18 ( 1 ): 78 - 84 .

RIVAS E , BURGOS J C , GARCIA J C . Condition assessment of power OLTC by vibration analysis using wavelet transform [J]. IEEE Transactions on Power Delivery , 2009 , 24 ( 2 ): 687 - 694 .

RIVAS E , BURGOS J C , GARCIA J C . Vibration analysis using envelope wavelet for detecting faults in the OLTC tap selector [J]. IEEE Transactions on Power Delivery , 2010 , 25 ( 3 ): 1629 - 1636 .

LIU Jinxin , WANG Guan , ZHAO Tong , et al . Fault diagnosis of on-load tap-changer based on variational mode decomposition and relevance vector machine [J]. Energies , 2017 , 10 ( 7 ): 946 - 959 .

DUAN Xiaomu , ZHAO Tong , LI Tan , et al . Method for diagnosis of on-load tap-changer based on wavelet theory and support vector machine [J]. Journal of Engineering , 2017 ( 13 ): 2193 - 2197 .

赵彤，张黎，李庆民 . OLTC振动信号的多维空间相轨图几何特征 [J]. 高电压技术， 2007 ， 33 ( 8 )： 102 - 105 .

ZHAO Tong , ZHANG Li , LI Qingmin . Feature analysis methodology for phase portrait structure of mechanical vibration signals of on-load tap changers in multidimensional space [J]. High Voltage Engineering , 2007 , 33 ( 8 ): 102 - 105 .

赵彤，李庆民，陈平 . OLTC振动信号特征提取的动力学分析方法 [J]. 电工技术学报， 2007 ， 22 ( 1 )： 41 - 46 .

ZHAO Tong , LI Qingmin , CHEN Ping . Dynamic analysis method for feature extraction of mechanical vibration signals of on-load tap changers [J]. Transactions of China Electrotechnical Society , 2007 , 22 ( 1 ): 41 - 46 .

LI Qingmin , ZHAO Tong , ZHANG Li , et al . Mechanical fault diagnosis of on load tap changer within power transformers based on hidden Markov model [J]. IEEE Transactions on Power Delivery , 2012 , 27 ( 2 ): 596 - 601 .

周翔，王丰华，傅坚，等 . 基于混沌理论和 K -means聚类的有载分接开关机械状态监测 [J]. 中国电机工程学报， 2015 ， 35 ( 6 )： 1541 - 1548 .

ZHOU Xiang , WANG Fenghua , FU Jian , et al . Mechanical condition monitoring of on-load tap changers based on chaos theory and K -means clustering method [J]. Proceedings of the CSEE , 2015 , 35 ( 6 ): 1541 - 1548 .

刘兵，郑剑 . 基于卷积神经网络的变压器局部放电模式识别 [J]. 高压电器， 2017 ， 53 ( 5 )： 70 - 74 .

LIU Bing , ZHENG Jian . Partial discharge pattern recognition in power transformers based on convolutional neural networks [J]. High Voltage Apparatus , 2017 , 53 ( 5 ): 70 - 74 .

林刚，王波，彭辉，等 . 基于强泛化卷积神经网络的输电线路图像覆冰厚度辨识 [J]. 中国电机工程学报， 2018 ， 38 ( 11 )： 3393 - 3401 .

LIN Gang , WANG Bo , PENG Hui , et al . Identification of icing thickness of transmission line based on strongly generalized convolutional neural network [J]. Proceedings of the CSEE , 2018 , 38 ( 11 ): 3393 - 3401 .

杨茂，齐玥 . 基于相空间重构的风电功率波动特性分析及其对预测误差影响 [J]. 中国电机工程学报， 2015 ， 35 ( 24 )： 6304 - 6314 .

YANG Mao , QI Yue . Volatility of wind power sequence and its influence on prediction error based on phase space reconstruction [J]. Proceedings of the CSEE , 2015 , 35 ( 24 ): 6304 - 6314 .

刘世明，许志成，李森林，等 . 基于相空间的励磁涌流新特征分析 [J]. 电力系统自动化， 2012 ， 36 ( 18 )： 134 - 138 .

LIU Shiming , XU Zhicheng , LI Senlin , et al . A novel characteristic of magnetizing inrush current based on phase space [J]. Automation of Electric Power Systems , 2012 , 36 ( 18 ): 134 - 138 .

徐进 . 基于递归相似性的非线性振动损伤敏感识别 [J]. 应用力学学报， 2015 ， 32 ( 4 )： 636 - 641 .

XU Jin . Damage detection for non-linear vibration using recurrence similarity [J]. Chinese Journal of Applied Mechanics , 2015 , 32 ( 4 ): 636 - 641 .

李洋麟，江全元，颜融，等 . 基于卷积神经网络的电力系统小干扰稳定评估 [J]. 电力系统自动化， 2019 ， 43 ( 2 )： 50 - 59 .

LI Yanglin , JIANG Quanyuan , YAN Rong , et al . Small-signal stability assessment of power system based on convolutional neural network [J]. Automation of Electric Power Systems , 2019 , 43 ( 2 ): 50 - 59 .

周念成，廖建权，王强钢，等 . 深度学习在智能电网中的应用现状分析与展望 [J]. 电力系统自动化， 2019 ， 43 ( 4 )： 180 - 197 .

ZHOU Niancheng , LIAO Jianquan , WANG Qianggang , et al . Analysis and prospect of deep learning application in smart grid [J]. Automation of Electric Power Systems , 2019 , 43 ( 4 ): 180 - 197 .

DONG Chao , CHEN C L , HE Kaiming , et al . Image super-resolution using deep convolutional networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 38 ( 2 ): 295 - 307 .

李元诚，曾婧 . 基于改进卷积神经网络的电网假数据注入攻击检测方法 [J]. 电力系统自动化， 2019 ， 43 ( 20 )： 97 - 104 .

LI Yuancheng , ZENG Jing . Detection method of false data injection attack on power grid based on improved convolutional neural network [J]. Automation of Electric Power Systems , 2019 , 43 ( 20 ): 97 - 104 .

SZEGEDY C , LIU W , JIA Y , et al . Going deeper with convolutions [C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR) , June 7 - 12 , 2015 , Boston, USA: 1 - 9 .

崔浩，王丰华，穆卡，等 . 基于实际波速的多端输电线路行波故障测距方法 [J]. 电工电能新技术， 2017 ， 36 ( 2 )： 74 - 80 .

CUI Hao , WANG Fenghua , MU Ka , et al . Real-time velocity based fault location method of travelling wave for multi-terminal transmission lines [J]. Advanced Technology of Electrical Engineering and Energy , 2017 , 36 ( 2 ): 74 - 80 .

李天云，陈昌雷，程汪刘，等 . 交叉验证方法在电能质量信号白噪声抑制中的应用 [J]. 电力系统自动化， 2007 ， 31 ( 16 )： 75 - 78 .

LI Tianyun , CHEN Changlei , CHENG Wangliu , et al . Application of cross validation in power quality de-noising [J]. Automation of Electric Power Systems , 2007 , 31 ( 16 ): 75 - 78 .

王福忠，石秀立 . AGA-BP 神经网络的变压器分接开关机械故障诊断 [J]. 现代制造工程， 2017 ， 35 ( 4 )： 11 - 16 .

WANG Fuzhong , SHI Xiuli . Application of tap-changer fault diagnosis of transformer based on AGA-BP neural network [J]. Modern Manufacturing Engineering , 2017 , 35 ( 4 ): 11 - 16 .

王旭，岳应娟，蔡艳平，等 . 基于递归图纹理特征分析的可视化故障诊断方法 [J]. 图学学报， 2017 ， 38 ( 6 )： 797 - 803 .

WANG Xu , YUE Yingjuan , CAI Yanping , et al . Visualization fault diagnosis method based on textural features of recurrence plots [J]. Journal of Graphics , 2017 , 38 ( 6 ): 797 - 803 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Lissajous Locus-based Efficient Identification Framework for Power Quality Disturbances Based on Edge-Cloud Collaboration

Ultra-short-term Regional Load Forecasting Based on Spatio-Temporal Graph Attention Network

Operation Section Image Generation and Feature Extraction for New Power System Considering Spatio-Temporal Integrity

Medium- and Long-term Industry Load Forecasting Method Considering Multi-dimensional Temporal Features

Short-term Load Forecasting for Multi-task Consumers Based on Multi-dimensional Fusion Feature and Convolutional Neural Network

Related Author

ZHANG Xi

ZHENG Jianyong

MEI Fei

MIAO Huiyu

ZHAO Ziyu

CHEN Yuanrui

CHEN Tingwei

LIU Junfeng

Related Institution

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

College of Energy and Electrical Engineering, Hohai University

School of Electrical Engineering, Southeast University

School of Cyber Science and Engineering, Southeast University

School of Automation Science and Engineering, South China University of Technology

⁰