基于PSO-SVM的多场景绝缘子劣化判定研究
Research on Multi-scenario Insulator Degradation Determination Based on PSO-SVM
- 高压电器 2026年62卷第4期 页码：113-121
- 作者机构：
兰州交通大学自动化与电气工程学院，兰州 730070
兰州交通大学甘肃省轨道交通电气自动化工程实验室，兰州 730070
- 作者简介：
王思华（1968—），男，硕士，教授，研究方向为高电压与绝缘技术（通信作者）（E-mail：lzjdwsh@163.com）。
徐贺节（2000—），女，硕士研究生，研究方向为高电压与绝缘技术（E-mail：2654820513@qq.com）。
刘爽（2000—），女，硕士研究生，研究方向为柔性直流输电（E-mail：1825298894@qq.com）。
王俊喆（1996—），男，硕士研究生，研究方向为高电压绝缘子（E-mail：907457368@qq.com）。
石天舒（1997—），男，硕士研究生，研究方向为电气化铁路过电压（E-mail：1304899636@qq.com）。
- 基金信息：国家自然科学基金资助项目;Project Supported by National Natural Science Foundation of China(51767014);中国铁路总公司科技研究开发计划项目。;China Railway Corporation Science and Technology Research and Development Plan Project(2017010-C)
DOI：10.13296/j.1001-1609.hva.2026.04.013
中图分类号：收稿：2025-09-25，
修回：2025-12-20，
纸质出版：2026-04-16
- 稿件说明：
移动端阅览
王思华, 徐贺节, 刘爽, 等. 基于PSO-SVM的多场景绝缘子劣化判定研究[J]. 高压电器, 2026,62(4):113-121.
WANG Sihua, XU Hejie, LIU Shuang, et al. Research on Multi-scenario Insulator Degradation Determination Based on PSO-SVM[J]. High Voltage Apparatus, 2026, 62(4): 113-121.
王思华, 徐贺节, 刘爽, 等. 基于PSO-SVM的多场景绝缘子劣化判定研究[J]. 高压电器, 2026,62(4):113-121. DOI： 10.13296/j.1001-1609.hva.2026.04.013.
WANG Sihua, XU Hejie, LIU Shuang, et al. Research on Multi-scenario Insulator Degradation Determination Based on PSO-SVM[J]. High Voltage Apparatus, 2026, 62(4): 113-121. DOI： 10.13296/j.1001-1609.hva.2026.04.013.
摘要
输电线路一般是根据不同的输电等级以及环境差异配置的，不同电压等级及环境的瓷绝缘子串配置不同，目前基于同一判定标准对多场景下绝缘子劣化判定容易造成误判。因此需要一种可以对不同场景下瓷绝缘子劣化状态有效判定方法。文中利用有限元软件模拟得到不同场景下分布电压数据集，基于PSOSVM算法构建了绝缘子劣化判定模型。通过有限元仿真模拟了不同结构变量的多场景330 kV交流输电线路瓷绝缘子串电场分布，确定主要影响瓷绝缘子串电压分布的因素；根据主要影响因素进行场景分类，使用PSO-SVM模型对不同场景的绝缘子劣化状态分类判定。同时，为验证模型的实用性及有效性，将PSO-SVM（particle swarm optimization-support vector machines）模型与支持向量机（SVM）和遗传算法支持向量机（genetic algorithm-optimization support vector，GA-SVM）进行对比，结果表明PSO-SVM预测精度高于其他两种算法，计算速度也更快，对不同场景下的瓷绝缘子串劣化判定具有一定的参考意义。
Abstract
Transmission lines are generally configured in acordance with different transmission levels and environmens
and the porcelain insulator strings are configured differently for different voltage levels and environments
At present
the determination of insulator degradation in multiple scenarios based on the same determination criteria is prone to misjudgment. Therefore
an effective method is required to determine the degradation status of porcelain insulator under different scenarios. In this paper the distributed voltage data set under different scenarios is obtained by simulation with finite element software. The insulator degradation determination model is constructed based on PSO-SVM algorithm.The electric field distribution of porcelain insulator strings of 330 kV AC transmission lines with different structure variables is simulated by using finite element software so to determine the main factors affecting the voltage distribution of porcelain insulator strings. Then
the scenarios are classified in accordance with the main influencing factors
and the insulator deterioration status of different scenarios is classified and determined using the PSO-SVM model. At the same time
the particle swarm optimization-support vector machines(PSO-SVM) model is compared with the support vector machines(SVM)and genetic algorithm-optimization support vector machines(GA-SVM)to verify both practicality and effectiveness of the model. The results show that the prediction accuracy of PSO-SVM is higher than that of other two algorithms
and the computation speed is also faster
which has a reference significance for the determination of porcelain insulator string degradation in different scenarios.
关键词
Keywords
references
谢金鹏,张素慧,李军,等.某变电站高压跌落式熔断器瓷绝缘子断裂原因分析[J].电瓷避雷器,2024(6):153-159.
XIE Jinpeng,ZHANG Suhui,LI Jun,et al. Cause of porcelain insulator fracture of high-voltage drop fuse in a certain substation[J]. Insulators and Surge Arresters,2024(6):153-159.
阎法强,袁志勇,周军,等.高温保温时间对绝缘子瓷件弯曲强度和电气强度的影响[J].电瓷避雷器,2025(4):129-136.
YAN Faqiang,YUAN Zhiyong,ZHOU Jun,et al. Influence of high temperature insulation time on the bending strength and electrical strength of insulator ceramic parts[J]. Insulators and Surge Arresters,2025(4):129-136.
马峰,赵法伟,郑哲钰,等.基于改进递归分析与自适应粒子滤波的支柱绝缘子裂纹演化预测[J].电子设计工程,2025,33(22):80-86.
MA Feng,ZHAO Fawei,ZHENG Zheyu,et al.Prediction of crack evolution in pillar insulators based on improved recursive analysis and adaptive particle filtering[J]. Electronic Design Engineering, 2025,33(22):80-86.
杜伯学,姚航,梁虎成,等.时变温差工况下直流GIL/GIS盆式绝缘子动态电场畸变抑制[J].电工技术学报,2024,39(9):2851-2859.
DU Boxue,YAO Hang,LIANG Hucheng,et al.Electric field relaxation of basin spacer under variable temperature gradient in DC-GIL/GIS[J]. Transactions of China Electrotechnical Society, 2024,39(9):2851-2859.
赖秋频,杨军,谭本东,等.基于YOLOv2网络的绝缘子自动识别与缺陷诊断模型[J].中国电力,2019,52(7):31-39.
LAI Qiupin,YANG Jun,TAN Bendong,et al.An automatic recognition and defect diagnosis model of transmission line insulator based on YOLOv2 network[J]. Electric Power,2019,52 (7):31-39.
苏凯第,赵巧娥.基于YOLOv5的绝缘子图像识别算法轻量化改进研究[J].电瓷避雷器,2024(4):173-180.
SU Kaidi,ZHAO Qiaoe. Lightweight improvement of insulator image recognition algorithm based on YOLOv5[J]. Insulators and Surge Arresters,2024(4):173-180.
卞建鹏,朱泽明,陈璇,等.基于Res-CapsNet与改进YOLOv4的绝缘子破损识别与定位[J].电瓷避雷器,2025(6):106-116.
BIAN Jianpeng,ZHU Zeming,CHEN Xuan,et al. Insulator damage identification and location based on Res-CapsNet and improved YOLOv4[J]. Insulators and Surge Arresters,2025(6):106-116.
张东东,常泽中,万武艺,等.基于局部电场的零值绝缘子检测技术研究[J].电力工程技术,2024,43(4):193-201.
ZHANG Dongdong,CHANG Zezhong,WAN Wuyi,et al.Zerovalue insulator detection technology based on local electric field[J]. Electric Power Engineering Technology,2024,43(4):193-201.
KIM T,SANYAL S,RABELO M,et al.Analysis of the deterioration of high-voltage insulators in service areas due to contamination factors[J]. ECS Journal of Solid State Science and Technology, 2022,11(7):ac7f56.
杜晓亮.基于深度学习的接触网绝缘子表面状态检测方法研究[D].兰州:兰州交通大学,2022.
DU Xiaoliang.Research on contact network insulator surface condition detection method based on deep learning[D]. Lanzhou:Lanzhou Jiaotong University,2022.
任欢,苏涛,李朋,等.基于改进CenterNet的输电线路绝缘子缺陷检测方法[J/OL].南方电网技术:1-11[2025-09-25].
https://nfdwjs.csg.cn/gateway-web/zh/debutDetail.html?serialNum=20240413002. REN Huan ,SU Tao ,LI Peng ,et al.Detecting method for insulator defects of transmission lines based on improved CenterNet[J/OL]. Southern Power System Technology:1-11[2025-09-25]. https://nfdwjs.csg.cn/gateway-web/en/debutDetail.html?serialNum=20240413002.
严俊杰.基于深度学习的接触网绝缘子破损检测算法研究[D].南昌:华东交通大学,2022.
YAN Junjie.Research on deep learning based contact network insulator breakage detection algorithm[D]. Nanchang:East China Jiaotong University,2022.
梁纲,马斌,饶宇飞,等.基于ADFE-Net的航拍图像绝缘子缺陷检测[J].智慧电力,2025,53(3):107-116.
LIANG Gang,MA Bin,RAO Yufei,et al.Insulator defect detection in aerial images based on ADFE-Net[J]. Smart Power,2025,53(3):107-116.
普子恒,彭朕,方春华,等.基于大数据分类与SVDD模型的多场景500 kV劣化绝缘子判定研究[J].电瓷避雷器,2022(2):189-196.
PU Ziheng,PENG Zhen,FANG Chunhua,et al. Multi-scenario judgment of 500 kV deteriorated insulator based on big data classification and SVDD model[J]. Insulators and Surge Arresters, 2022(2):189-196.
常波,张启哲,王胜辉,等.动车组车顶隔离开关用支柱绝缘子污秽状态下的电场分布特性研究[J].电测与仪表,2024,61(4):81-85.
CHANG Bo,ZHANG Qizhe,WANG Shenghui,et al.Research on the electric field distribution characteristics under polluted conditionsof EMU roof isolation switch post insulators[J]. Electrical Measurement & Instrumentation,2024,61(4):81-85.
孙喆,张静,李建兴,等.基于轻量化YOLOv7-DenseBlock的绝缘子检测算法[J].电网与清洁能源,2025,41(5):68-74.
SUN Zhe,ZHANG Jing,LI Jianxing,et al.An insulator detection algorithm based on lightweight YOLOv7-DenseBlock[J]. Power System and Clean Energy,2025,41(5):68-74.
刘悦,黄新波,刘天娇.基于深度学习的架空输电线路绝缘子缺陷检测方法研究综述[J].电力电容器与无功补偿,2024,45 (3):167-177.
LIU Yue,HUANG Xinbo,LIU Tianjao.Overview on defect detection methods of insulator for overhead transmission lines based on deep learning[J]. Power Capacitor & Reactive Power Compensation,2024,45(3):167-177.
TAN Chao,YANG Long,CHEN Haoran,et al.Fault diagnosis method for rolling bearing based on VMD and improved SVM optimized by METLBO[J]. Journal of Mechanical Science and Technology,2022,36(10):4979-4991.
尹向雷,解永芳,屈少鹏,等.基于动态蛇形卷积和非跨步卷积的绝缘子缺陷检测[J]. 电力系统保护与控制,2024,52(20):177-187.
YIN Xianglei,XIE Yongfang,QU Shaopeng,et al.Insulator defect detection based on dynamic snake convolution and space-to-depth convolution[J]. Power System Protection and Control,2024,52(20):177-187.
李亮,范瑾,闫林,等.基于混合采样和支持向量机的变压器故障诊断[J].中国电力,2021,54(12):150-155.
LI Liang,FAN Jin,YAN Lin,et al.Transformer fault diagnosis based on hybrid sampling and support vector machines[J]. Electric Power,2021,54(12):150-155.
邹红波,宋家乐,刘媛,等.基于PSO-SVM算法的输电线路覆冰舞动预测模型[J].振动与冲击,2023,42(3):280-286.
ZOU Hongbo,SONG Jiale,LIU Yuan,et al.Prediction model of galloping of iced transmission lines based on PSO-SVM algorithm[J]. Journal of Vibration and Shock,2023,42(3):280-286.
李云淏,咸日常,张海强,等.基于改进灰狼算法与最小二乘支持向量机耦合的电力变压器故障诊断方法[J].电网技术, 2023,47(4):1470-1477.
LI Yunhao,XIAN Richang,ZHANG Haiqiang,et al.Fault diagnosis for power transformers based on improved grey wolf algorithm coupled with least squares support vector machine[J]. Power System Technology,2023,47(4):1470-1477.
黄新波,高玉菡,张烨,等.基于联合分量灰度化算法和深度学习的玻璃绝缘子目标识别算法[J].电力自动化设备,2022,42(4):203-209.
HUANG Xinbo,GAO Yuhan,ZHANG Ye,et al. Glass insulator target recognition algorithm based on joint component grayscale algorithm and deep learning[J]. Electric Power Automation Equipment,2022,42(4):203-209.
包金山,杨定坤,张靖,等.基于特征提取与INGO-SVM的变压器故障诊断方法[J].电力系统保护与控制,2024,52(7):24-32.
BAO Jinshan,YANG Dingkun,ZHANG Jing,et al.Transformer fault diagnosis method based on feature extraction and INGO-SVM[J]. Power System Protection and Control,2024,52(7):24-32.
国家能源局.劣化悬式绝缘子检测规程:DL/T 626—2015[S].2015.
National Energy Administration.Deterioration suspension insulator testing procedure:DL/T 626—2015[S].2015.
李进,王禹淮,张黎明,等.抛光方式对交流电压下盆式绝缘子表面电荷分布和沿面闪络特性的影响[J].高电压技术,2022, 48(10):4093-4101.
LI Jin,WANG Yuhuai,ZHANG Liming,et al.Influence of polishing treatments on surface charge distribution and flashover characteristics of basin spacer under AC voltage[J]. High Voltage Engineering,2022,48(10):4093-4101.
房子祎,郝金鹏,伍弘,等. 220 kV复合绝缘子均压环类型及结构对其电场分布的影响[J].绝缘材料,2023,56(1):51-61.
FANG Ziyi,HAO Jinpeng,WU Hong,et al.Influence of grading ring type and structure on electric field distribution of 220 kV composite insulator[J]. Insulating Materials,2023,56(1):51-61.
刘行谋,田浩,杨永明,等.复杂环境背景下绝缘子缺陷图像检测方法研究[J].电子测量与仪器学报,2022,36(2):57-67.
LIU Hengmou,TIAN Hao,YANG Yongming,et al.Research on insulator defect image detection method in complex environment background[J]. Journal of Electronic Measurement and Instrument, 2022,36(2):57-67.
0
浏览量
0
下载量
0
CSCD
- 网络PDF下载
- Meta-XML下载
- BibTeX下载
- Endnote下载
- RefMan 下载
- NoteExpress下载
- NoteFirst下载
关联资源
相关文章
相关作者
相关机构
- 技术支持由北京北大方正电子有限公司提供 陕ICP备05005324号-4
陕公网安备 61010402000197 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies