基于深度迁移学习的配电线路绝缘子状态监测方法*

doi:10.11985/2022.04.029

电气工程学报 ›› 2022, Vol. 17 ›› Issue (4): 275-281.doi: 10.11985/2022.04.029

扫码分享

基于深度迁移学习的配电线路绝缘子状态监测方法^*

宰红斌¹(), 刘建国¹(), 张文岗¹(), 封士永²(), 祖国强³()

1.国网晋城供电公司晋城 048000
2.南瑞集团(国网电力科学研究院)有限公司南京 211106
3.国网天津市电力公司电力科学研究院天津 300384

收稿日期:2021-03-29 修回日期:2021-10-14 出版日期:2022-12-25 发布日期:2023-02-03
作者简介:宰红斌，男，1971年生，高级工程师。主要研究方向为输电线路防灾减灾，运行维护与带电作业等。E-mail：qazw3182@163.com
刘建国，男，1969年生，高级工程师。主要研究方向为电气工程及其自动化。E-mail：ljg8837490@126.com
张文岗，男，1979年生，高级工程师。主要研究方向为电力系统自动化。E-mail：zhangwengang0517@126.com
封士永，男，1988年生，硕士，高级工程师。主要研究方向为电力物联网。E-mail：s398493858009@gmail.com
祖国强，男，1989年生，博士，工程师。主要研究方向为配电网规划运行。E-mail：guoqiangzu1@tj.sgcc.com.cn
基金资助:
*国家重点研发计划(2017YFB0902800);国网天津市电力公司科技(KJ20-1-27)

Insulator Condition Monitoring Method of Distribution Line Based on Deep Transfer Learning

ZAI Hongbin¹(), LIU Jianguo¹(), ZHANG Wengang¹(), FENG Shiyong²(), ZU Guoqiang³()

1. State Grid Jincheng Power Supply Company, Jincheng 048000
2. NARI Group (State Grid Electric Power Research Institute) Co., Ltd., Nanjing 211106
3. State Grid Tianjin Electric Power Research Institute, Tianjin 300384

Received:2021-03-29 Revised:2021-10-14 Online:2022-12-25 Published:2023-02-03

摘要/Abstract

摘要：

针对传统人工巡线的方法不适用于近距离监测配电线路绝缘子状态以及现有方法精度低等问题，提出一种基于深度迁移学习的配电线路绝缘子状态监测方法。首先，智能配电终端汇集配电线路上的摄像机获取的绝缘子图像，利用尺度不变特征变换(Oriented FAST and rotated BRIEF，ORB)算法提取图像特征，采用灰度质心法以保证图像特征点发生旋转后性质不改变。然后，根据获取的图像特征，将深度学习与迁移学习算法结合，对图像特征进行训练，实现绝缘子状态的分类。最后，基于Matlab仿真平台将所提方法与其他组合方法在常见场景中进行试验分析。试验结果表明，相比于其他组合方法，所提方法能够在不同环境中准确监测绝缘子状态，并且分类准确度更高。

关键词: 绝缘子状态监测, ORB算法, 特征分析, 深度迁移学习, 状态分类

Abstract:

In view of the fact that the traditional manual line inspection method is not suitable for short-range monitoring of insulator status of distribution lines, and the existing methods have the problems of low accuracy, a new method based on deep transfer learning for insulator status monitoring of distribution lines is proposed. Firstly, the intelligent distribution terminal collects the insulator images obtained by the camera on the distribution line, extracts the image features by oriented FAST and rotated BRIEF(ORB) algorithm, and adopts gray centroid method to ensure that the properties of the image feature points do not change after rotation. Then, according to the acquired image features, the depth learning and transfer learning algorithm are combined to train the image features and realize the insulator state classification. Finally, based on Matlab simulation platform, the proposed method and other combination methods are tested and analyzed in common scenes. Experimental results show that compared with other combination methods, the proposed method can accurately monitor insulator status in different environments, and the classification accuracy is higher.

Key words: Insulator state monitoring, ORB algorithm, feature analysis, deep transfer learning, state classification

中图分类号:

TM726

宰红斌, 刘建国, 张文岗, 封士永, 祖国强. 基于深度迁移学习的配电线路绝缘子状态监测方法^*[J]. 电气工程学报, 2022, 17(4): 275-281.

ZAI Hongbin, LIU Jianguo, ZHANG Wengang, FENG Shiyong, ZU Guoqiang. Insulator Condition Monitoring Method of Distribution Line Based on Deep Transfer Learning[J]. Journal of Electrical Engineering, 2022, 17(4): 275-281.

图/表 7

图1

图2

图3

表1

图4

表2

图5

参考文献 18

[1]	高立艾, 霍利民, 黄丽华, 等. 基于贝叶斯网络时序模拟的含微网配电系统可靠性评估[J]. 中国电机工程学报, 2019, 39(7):2033-2041.
	GAO Liai, HUO Limin, HUANG Lihua, et al. Reliability evaluation of distribution system with microgrid based on Bayesian network time series simulation[J]. Proceedings of the CSEE, 2019, 39 (7):2033-2041.
[2]	KHAN B, ALHELOU H H, MEBRAHTU F. A holistic analysis of distribution system reliability assessment methods with conventional and renewable energy sources[J]. AIMS Energy, 2019, 7(4):413-429. doi: 10.3934/energy.2019.4.413
[3]	席禹, 陈波, 郭晓斌, 等. 基于IEC61850配电系统自动化可靠性评估[J]. 电力系统保护与控制, 2019, 47(16):129-135.
	XI Yu, CHEN Bo, GUO Xiaobin, et al. Reliability evaluation of distribution system automation based on IEC61850[J]. Power System Protection and Control, 2019, 47(16):129-135.
[4]	杨亚超, 黄纯, 汪星耀, 等. 一种直流配电网线路故障测距新方法[J]. 电网技术, 2019(5):1787-1794.
	YANG Yachao, HUANG Chun, WANG Xingyao, et al. A new method for line fault location in DC distribution network[J]. Power System Technology, 2019(5):1787-1794.
[5]	王成斌, 贠志皓, 张恒旭, 等. 基于微型PMU的配电网多分支架空线路参数无关故障定位算法[J]. 电网技术, 2019, 43(9):3202-3211.
	WANG Chengbin, YUN Zhihao, ZHANG Hengxu, et al. Parameter independent fault location algorithm for multi branch overhead lines in distribution network based on micro PMU[J]. Power System Technology, 2019, 43(9):3202-3211.
[6]	DIXIT M, KUNDU P, JARIWALA H R. Integration of distributed generation for assessment of distribution system reliability considering power loss,voltage stability and voltage deviation[J]. Energy Systems, 2019, 10(2):489-515. doi: 10.1007/s12667-017-0248-6
[7]	FREDA L, GIANNI M, PIRRI F, et al. 3D multi-robot patrolling with a two-level coordination strategy[J]. Autonomous Robots, 2019, 43(7):1747-1779. doi: 10.1007/s10514-018-09822-3
[8]	任泓宇, 王主丁, 张超, 等. 高压配电网网格化规划优化模型和方法[J]. 电力系统自动化, 2019, 43(14):151-161.
	REN Hongyu, WANG Zhuding, ZHANG Chao, et al. Optimization model and method for grid planning of high voltage distribution network[J]. Automation of Electric Power Systems, 2019, 43(14):151-161.
[9]	YEUNG S, RINALDO F, JOPLING J, et al. A computer vision system for deep learning-based detection of patient mobilization activities in the ICU[J]. NPJ Digital Medicine, 2019, 2(1):1-5. doi: 10.1038/s41746-018-0076-7
[10]	李京, 黄良, 王博禹, 等. 无人机定位下绝缘子劣化状态检测系统设计[J]. 电子设计工程, 2019, 27(19):15-18.
	LI Jing, HUANG Liang, WANG Boyu, et al. Design of insulator deterioration detection system under UAV positioning[J]. Electronic Design Engineering, 2019, 27(19):15-18.
[11]	BHARGAVA C, LOKA R. An open source tool for reliability evaluation of distribution system using Monte Carlo simulation[J]. Indonesian Journal of Electrical Engineering and Computer Science, 2019, 14(3):1065-1075. doi: 10.11591/ijeecs.v14.i3.pp1065-1075
[12]	彭向阳, 梁福逊, 钱金菊, 等. 基于机载红外影像纹理特征的输电线路绝缘子自动定位[J]. 高电压技术, 2019, 45(3):922-928.
	PENG Xiangyang, LIANG Fuxun, QIAN Jinju, et al. Automatic positioning of transmission line insulators based on airborne infrared image texture features[J]. High Voltage Engineering, 2019, 45(3):922-928.
[13]	黄新波, 张慧莹, 张烨, 等. 基于改进色差法的复合绝缘子图像分割技术[J]. 高电压技术, 2018, 44(8):2493-2500.
	HUANG Xinbo, ZHANG Huiying, ZHANG Ye, et al. Composite insulator image segmentation technology based on improved color difference method[J]. High Voltage Engineering, 2018, 44(8):2493-2500.
[14]	卢胜男, 李小和. 基于对称FAST特征的车辆目标检测方法[J]. 微电子学与计算机, 2020, 37(2):41-46.
	LU Shengnan, LI Xiaohe. Vehicle target detection method based on symmetric fast feature[J]. Microelectronics & Computer, 2020, 37(2):41-46.
[15]	PERNEBAYEVA D, IRMANOVA A, SADYKOVA D, et al. High voltage outdoor insulator surface condition evaluation using aerial insulator images[J]. High Voltage, 2019, 4(3):178-185. doi: 10.1049/hve.2019.0079
[16]	DUAN L, HU J, ZHAO G, et al. Method of inter-turn fault detection for next-generation smart transformers based on deep learning algorithm[J]. High Voltage, 2019, 4(4):282-291. doi: 10.1049/hve.2019.0067
[17]	CHEN B, MIAO X. Distribution line pole detection and counting based on YOLO using UAV inspection line video[J]. Journal of Electrical Engineering & Technology, 2020, 15(1):441-448.
[18]	陈景文, 周鑫, 张蓉, 等. 基于U-net网络的航拍绝缘子检测[J]. 陕西科技大学学报, 2018, 36(4):153-157.
	CHEN Jingwen, ZHOU Xin, ZHANG Rong, et al. Aerial photo insulator detection based on U-net network[J]. Journal of Shaanxi University of Science, 2018, 36(4):153-157.

绝缘子样本编号	监测准确率(%)
绝缘子样本编号	噪声	视线遮挡	光线
1	90.13	88.59	92.08
2	92.81	89.78	90.45
3	90.64	87.26	90.31
4	90.77	88.85	89.09
5	92.23	89.52	90.86

状态	健康	临界	风险
场景1	80	76	96
场景2	7	4	3
场景3	22	16	20
场景4	190	172	164
场景5	133	117	138

基于深度迁移学习的配电线路绝缘子状态监测方法^*

Insulator Condition Monitoring Method of Distribution Line Based on Deep Transfer Learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 18

相关文章 6

编辑推荐

Metrics

本文评价

[1]	雷亚国, 杨彬, 李乃鹏, 李响, 武通海. 跨设备的机械故障靶向迁移诊断方法[J]. 机械工程学报, 2022, 58(12): 1-9.
[2]	任尊松, 赵宇嘉, 李玉怡, 王斌杰, 吴养民. 高速动车组转向架牵引制动载荷及损伤特征研究[J]. 机械工程学报, 2022, 58(12): 151-158.
[3]	石志新, 叶梅燕, 罗玉峰. 弯曲平移机构运动特征描述与分析方法研究[J]. 机械工程学报, 2020, 56(21): 79-88.
[4]	孟宗, 石桂霞, 王福林, 詹旭阳, 樊凤杰. 基于时变啮合刚度的裂纹故障齿轮振动特征分析[J]. 机械工程学报, 2020, 56(17): 108-115.
[5]	李守忠. 两种新颖的柔性机构自由度分析方法[J]. 机械工程学报, 2016, 52(1): 41-46.
[6]	孙殿柱;范志先;李延瑞;孙肖霞. 散乱数据点云型面特征分析算法的研究与应用[J]. , 2007, 43(6): 133-136.