基于域对抗迁移卷积神经网络的小样本GIS绝缘缺陷智能诊断方法

doi:10.19595/j.cnki.1000-6753.tces.211512

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2735 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract In recent years, the artificial intelligence diagnosis method driven by massive data has made a certain breakthrough in the diagnosis of gas-insulated switchgear (GIS) insulation defects. However, these methods built with massive laboratory data are difficult to deploy to complex working conditions and small sample conditions on site, which leads to difficulties in field application of existing diagnostic methods. In order to solve the problem of data scarcity that restricts the application of traditional diagnostic methods in the field and the problem of difficult field application of existing diagnostic models, this paper proposes a novel domain adversarial transfer convolutional neural network for small samples GIS insulation defect diagnosis. First, the convolutional neural network (CNN) constructed with automatic optimization learns transferable features from defective samples. The automatic optimization construction method reduces human intervention in the network construction process, and effectively improves the network accuracy and other aspects of performance. Then, domain adversarial transfer learning is introduced to realize the migration of the trained model under massive data (source domain) to small sample complex working conditions (target domain) to realize the reliable diagnosis under complex small samples. Through the adversarial training, the class boundary representation feature and the domain space representation feature are learned to realize the transfer of diagnostic knowledge. And two domain classifiers are introduced to align the domain space of the decision boundary, and a more suitable feature matching is realized. The experimental verification was carried out on the laboratory and on-site GIS, which verified that the proposed method achieved 99.35% and 90.35% diagnostic accuracy in the target domains, respectively. The results show that this method can effectively learn transferable features, and achieve high-precision and robust diagnosis of insulation defects in small samples of GIS.

Key words： Gas-insulated switchgear (GIS) domain adversarial transfer learning convolutional neural network small sample intelligence diagnosis

Received: 23 September 2021

PACS:

TM835

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Wang Yanxin
	Yan Jing
	Wang Jianhua
	Geng Yingsan
	Liu Zhiyuan

Cite this article:

Wang Yanxin,Yan Jing,Wang Jianhua等. Intelligent Diagnosis for GIS with Small Samples Using a Novel Adversarial Transfer Learning in Convolutional Neural Network[J]. Transactions of China Electrotechnical Society, 2022, 37(9): 2150-2160.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.211512 OR https://dgjsxb.ces-transaction.com/EN/Y2022/V37/I9/2150

[1] 刘青, 常丁戈, 邓军波. 用于变电站站域局部放电特高频测向的空间谱估计算法优化选择[J]. 电工技术学报, 2020, 35(16): 3551-3560.
Liu Qing, Chang Dingge, Deng Junbo.Optimal selection on spatial spectrum estimation algorithms for UHF direction finding of partial discharge in substation[J]. Transactions of China Electrotechnical Society, 2020, 35(16): 3551-3560.
[2] 吴其, 刘晓明, 杨田, 等. 基于复杂网络理论的气体绝缘金属封闭开关设备电场网络特征分析[J]. 电工技术学报, 2020, 35(20): 4317-4324.
Wu Qi, Liu Xiaoming, Yang Tian, et al.The characteristics of gas insulated metal-enclosed switchgear electric field network based on complex network theory[J]. Transactions of China Electrotechnical Society, 2020, 35(20): 4317-4324.
[3] 刘宝稳, 汤容川, 马钲洲, 等. 基于S变换D-SVM AlexNet模型的GIS机械故障诊断与试验分析[J]. 高电压技术, 2021, 47(7): 2526-2538.
Liu Baowen, Tang Rongchuan, Ma Zhengzhou, et al.GIS mechanical fault diagnosis and test analysis based on S transform D-SVM AlexNet model[J]. High Voltage Engineering, 2021, 47(7): 2526-2538.
[4] Wang Yanxin, Yan Jing, Sun Qifeng, et al.ShuffleNet-based comprehensive diagnosis for insulation and mechanical faults of power equipment[J]. High Voltage, 2021, 6(5): 861-872.
[5] 李泽, 王辉, 钱勇, 等. 基于加速鲁棒特征的含噪局部放电模式识别[J]. 电工技术学报, 2022, 37(3): 775-785.
Li Ze, Wang Hui, Qian Yong, et al.Pattern recognition of partial discharge in the presence of noise based on SURF[J]. Transactions of China Electrotechnical Society, 2022, 37(3): 775-785.
[6] 徐遐龄, 田国辉, 刘涛, 等.基于神经网络的电网潮流图自动拓扑布线方法[J]. 电力系统自动化, 2022, 46(6): 102-108.
Xu Xialing, Tian Guohui, Liu Tao, et. al. Automatic topology wiring method of power flow diagram based on neural network[J]. Automation of Electric Power Systems, 2022, 46(6): 102-108.
[7] Masoud K, Mehrdad M, Hamed M, et. al. A novel application of deep belief networks in learning partial discharge patterns for classifying corona surface and internal discharges[J]. IEEE Transactions on Industrial Electronics, 2020, 67(4): 3277-3287.
[8] 王卓, 王玉静, 王庆岩, 等. 基于协同深度学习的二阶段绝缘子故障检测方法[J]. 电工技术学报, 2021, 36(17): 3594-3604.
Wang Zhuo, Wang Yujing, Wang Qingyan, et al.Two stage insulator fault detection method based on collaborative deep learning[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3594-3604.
[9] 张重远, 岳浩天, 王博闻, 等. 基于相似矩阵盲源分离与卷积神经网络的局部放电超声信号深度学习模式识别方法[J]. 电网技术, 2019, 43(6): 1900-1907.
Zhang Zhongyuan, Yue Haotian, Wang Bowen, et al.Pattern recognition of partial discharge ultrasonic signal based on similar matrix BSS and deep learning CNN[J]. Power System Technology, 2019, 43(6): 1900-1907.
[10] Khan Q, Refaat S S, Haitham A R, et al.Partial discharge detection and diagnosis in gas insulated switchgear: state of the art[J]. IEEE Electrical Insulation Magazine, 2019, 35(4): 16-33.
[11] 杨志淳, 沈煜, 杨帆, 等. 考虑多元因素态势演变的配电变压器迁移学习故障诊断模型[J]. 电工技术学报, 2019, 34(7): 1505-1515.
Yang Zhichun, Shen Yu, Yang Fan, et al.A transfer learning fault diagnosis model of distribution transformer considering multi-factor situation evolution[J]. Transactions of China Electrotechnical Society, 2019, 34(7): 1505-1515.
[12] 李宗博, 焦在滨, 何安阳. 基于卷积神经网络特征迁移策略的变压器智能保护方法[J]. 中国电机工程学报, 2021, 41(15): 5201-5212.
Li Zongbo, Jiao Zaibin, He Anyang.Intelligence protection for power transformer using convolutional neural network integrated into features transferring strategy[J]. Proceedings of the CSEE, 2021, 41(15): 5201-5212.
[13] 王玉静, 吕海岩, 康守强, 等. 不同型号滚动轴承故障诊断方法[J]. 中国电机工程学报, 2021, 41(1): 267-276, 416.
Wang Yujing, Lü Haiyan, Kang Shouqiang, et al.Fault diagnosis method for different types of rolling bearings[J]. Proceedings of the CSEE, 2021, 41(1): 267-276, 416.
[14] 陈剑, 杜文娟, 王海风. 基于对抗式迁移学习的含柔性高压直流输电的风电系统次同步振荡源定位[J]. 电工技术学报, 2021, 36(22): 4703-4715.
Chen Jian, Du Wenjuan, Wang Haifeng.Location method of subsynchronous oscillation source in wind power system with VSC-HVDC based on adversarial transfer learning[J]. Transactions of China Electrotechnical Society, 2021, 36(22): 4703-4715.
[15] Ganguly B, Chaudhuri S, Biswas S, et al.Wavelet kernel based convolutional neural network for localization of partial discharge sources within a power apparatus[J]. IEEE Transactions on Industrial Informatics, 2021, 17(3): 1831-1841.
[16] Wang Yanxin, Yan Jing, Yang Zhou, et al.Optimizing GIS partial discharge pattern recognition in the ubiquitous power internet of things context: a mixnet deep learning model[J]. International Journal of Electrical Power & Energy Systems, 2021, 125: 106484.
[17] 高盎然, 朱永利, 张翼, 等. 基于边际谱图像和深度残差网络的变压器局部放电模式识别[J]. 电网技术, 2021, 45(6): 2433-2442.
Gao Angran, Zhu Yongli, Zhang Yi, et al.Partial discharge pattern recognition of power transformers based on marginal spectrum images and deep residual net-work[J]. Power System Technology, 2021, 45(6): 2433-2442.
[18] Tan Mingxing, Chen Bo, Pang Ruoming, et al.MnasNet: platform-aware neural architecture search for mobile[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 2820-2828.
[19] 宋思蒙, 钱勇, 王辉, 等. 基于方向梯度直方图属性空间的局部放电模式识别改进算法[J]. 电工技术学报, 2021, 36(10): 2153-2160.
Song Simeng, Qian Yong, Wang Hui, et al.Improved algorithm for partial discharge pattern recognition based on histogram of oriented gradient attribute space[J]. Transactions of China Electrotechnical Society, 2021, 36(10): 2153-2160.
[20] Behrmann G, Franz S, Smajic J, et al.UHF PD signal transmission in GIS: Effects of 90° bends and an L-shaped CIGRE step 1 test section[J]. IEEE Transactions on Dielectric Electrical Insulation, 2019, 26(4): 1293-1300.
[21] 侯慧娟, 盛戈皞, 孙岳, 等. 基于电磁波信号传播衰减模型的变电站局部放电定位方法[J].电工技术学报, 2014, 29(6): 326-332.
Hou Huijuan, Sheng Gehao, Sun Yue, et. al. The localization method of partial discharge in substation based on propagation and attenuation model of electromagnetic signal[J]. Transactions of China Electrotechnical Society, 2014, 29(6): 326-332.
[22] Wang Yanxin, Yan Jing, Yang Zhou, et al.GIS partial discharge pattern recognition via lightweight convolutional neural network in the ubiquitous power internet of things context[J]. IET Science Measurement & Technology, 2020, 14(8): 864-871.
[23] 杨为, 朱太云, 张国宝, 等. 电力物联网下基于卷积神经网络和迁移学习的GIS局部放电模式识别分类方法研究[J]. 高压电器, 2020, 56(9): 20-25, 32.
Yang Wei, Zhu Taiyun, Zhang Guobao, et. al. Research on partial discharge pattern recognition and classification in GIS based on CNN and transfer learning in power internet of things[J]. High Voltage Apparatus, 2020, 56(9): 20-25, 32.
[24] Chen Zhuyun, Gryllias K, Li Weihua.Intelligent fault diagnosis for rotary machinery using transferable convolutional neural network[J]. IEEE Transactions on Industrial Informatics, 2020, 16(1): 339-349.
[25] Cheng Hongsheng, Zhu Jian, Liu Ce, et al.Silhouette analysis for human action recognition based on supervised temporal t-SNE and incremental learning[J]. IEEE Transactions on Image Process, 2015, 24(10): 3203-3217.