电工电气杂志社

基于机器学习的紧凑型架空线路脱冰跳跃风险预测研究

来源：电工电气发布时间：2025-07-24 11:24 浏览次数：10

基于机器学习的紧凑型架空线路脱冰跳跃风险预测研究

陈易飞¹，王睿君¹，张宇¹，杜乐¹，林杏¹，莫姝¹，刘子其^{2, 3}，黄欢⁴

(1 广东电网有限责任公司广州供电局，广东广州 510640；

2 国网湖南省电力有限公司技术技能培训中心，湖南长沙 410131；

3 长沙电力职业技术学院供电服务系，湖南长沙 410131；

4 贵州电网有限责任公司电力科学研究院，贵州贵阳 550000)

摘要：架空线路发生脱冰跳跃会导致线间间距减小，甚至会发生放电事故，影响电网的安全运行。对基于机器学习的紧凑型架空线路脱冰跳跃风险预测进行研究，提出了一种基于最大跳跃幅值的脱冰线路放电风险评估流程。以中国南方地区某500 kV紧凑型架空线路为例，利用数值模拟方法得到不同仿真工况下架空线路的最大跳跃幅值，构建样本数据集；建立基于 BP 神经网络的脱冰线路最大跳跃幅值预测模型，将线路覆冰厚度、脱冰率、档距、高差、导线截面积作为输入，最大跳跃幅值作为输出，通过机器学习实现对脱冰线路最大跳跃幅值的预测，并结合所提风险评估流程，进一步实现对脱冰线路放电风险的预测。基于该紧凑型线路实际放电案例，验证所提预测模型的准确性，结果表明：预测和仿真得到的最大跳跃幅值的绝对误差不超过0.3 m，且预测和仿真条件下对应脱冰线路的风险状态一致；预测风险结果与实际脱冰线路放电案例结果吻合，说明了所提风险预测方法可以方便快捷地实现脱冰线路风险的预测。

关键词： 覆冰；脱冰跳跃；风险预测；风险评估；紧凑型架空线路

中图分类号：TM726.3 文献标识码：A 文章编号：1007-3175(2025)07-0060-08

Study on Risk Prediction of Ice-Shedding Jump for Compact Overhead

Lines Based on Machine Learning

CHEN Yi-fei¹, WANG Rui-jun¹, ZHANG Yu¹, DU Le¹, LIN Xing¹, MO Shu¹, LIU Zi-qi^{2, 3}, HUANG Huan⁴

（1 Guangdong Power Grid Co., Ltd. Guangzhou Power Supply Bureau, Guangzhou 510640, China;

2 Technical Skills Training Center of State Grid Hunan Electric Power Co., Ltd, Changsha 410131, China;

3 Power Supply Service Department, Changsha Electric Power Technical College, Changsha 410131, China;

4 Guizhou Power Grid Co., Ltd. Electric Power Science Research Institute, Guiyang 550000, China）

Abstract: The occurrence of ice-shedding jumps on overhead lines can lead to a reduction in the spacing between lines, and even discharge accidents can occur, affecting the safe operation of the power grid. In this paper, machine learning-based risk prediction of ice-shedding jumps for compact overhead lines is investigated, and a process for assessing the risk of ice-shedding lines discharges based on the maximum jump amplitude is proposed. Taking a 500 kV compact overhead line in southern China as an example, the maximum jump amplitude of the overhead line under different simulation conditions was obtained by numerical simulation method, and the sample dataset was constructed. A prediction model of the maximum jump amplitude of the ice-shedding line based on BP neural network was established, and the ice thickness, ice-shedding rate,pitch, height difference, and cross-sectional area of the wire were taken as inputs, and the maximum jump amplitude was used as the output, and the maximum jump amplitude of the ice-shedding line was predicted through machine learning, and the risk of discharge risk of the ice-shedding line was further predicted by combining the proposed risk assessment process. Based on the actual discharge case of the compact line, the accuracy of the proposed prediction model is verified, and the results show that the absolute error of the maximum jump amplitude obtained by the prediction and simulation is not more than 0.3 m, and the risk state of the corresponding ice-shedding line is consistent under the prediction and simulation conditions. The prediction risk results are consistent with the actual ice-shedding line discharge case results, which indicates that the proposed risk prediction method can easily and quickly realize the risk prediction of ice-shedding lines.

Key words: icing; ice-shedding jump; risk prediction; risk assessment; compact overhead line

参考文献

[1] 于幼文，金永纯，高毅. 我国 500 kV 紧凑型输电线路的研究与应用[J]. 电力设备，2004，5(6) ： 9-12.

[2] 习近平向《联合国气候变化框架公约》第二十六次缔约方大会世界领导人峰会发表书面致辞[N] . 人民日报，2021-11-02(1)．

[3] 张行，王逸飞，何迪，等. 电网防灾减灾现状分析及建议[J]. 电网技术，2016，40(9) ：2838-2844.

[4] YANG Lin, CHEN Yifei, MEI Lulu, et al.Prediction Method for Response Characteristics Parameters of Isolated-Span Overhead Lines after Ice-Shedding Based on Finite Element Simulation and Machine Learning[J].Electric Power Systems Research，2024，229 ：110141.

[5] YANG L, CHEN Y F, HAO Y P, et al.Detection Method for Equivalent Ice Thickness of 500 kV Overhead Lines Based on Axial Tension Measurement and Its Application [J].IEEE Transactions Instrumentation Measurement，2023，72 ：1-11.

[6] 陈易飞，阳林，郝艳捧，等. 冰风荷载作用下架空线路脱冰跳跃风险评估方法[J] . 电力大数据，2024，27(1) ：1-9.

[7] MORGAN V T, SWIFT D A.Jump height of overheadline conductors after the sudden release of ice loads[J].Proceedings of the Institution of Electrical Engineers，1964，111(10) ：1736-1746.

[8] JAMALEDDING A, MCCLURE G, ROUSSELET J, et al.Simulation of ice-shedding on electrical transmission lines using ADINA[J].Computers and Structures，1993，47(4/5) ：523-536.

[9] VAN DYKE P, LANEVILLE A.Galloping of a single conductor covered with a D-section on a highvoltage overhead test line[J].Journal of Wind Engineering and Industrial Aerodynamics，2008，96(6/7) ：1141-1151.

[10] 陈勇，胡伟，王黎明，等. 覆冰导线脱冰跳跃特性研究[J]. 中国电机工程学报，2009，29(28) ：115-121.

[11] 谢献忠，李丹，黄伟，等. 塔线体系脱冰跳跃动力特性实验研究[J]. 应用力学学报，2017，34(5) ：855-861.

[12] HUANG Guizao, YAN Bo, WEN Nan, et al.Study on jump height of transmission lines after ice-shedding by reduced-scale modeling test[J].Cold Regions Science and Technology，2019，165 ：102781.

[13] KOLLAR L E, FARZANEH M, VAN DYKE P.Modeling Ice Shedding Propagation on Transmission Lines with or without Interphase Spacers[J].IEEE Transactions on Power Delivery，2013，28(1) ：261-267.

[14] YAN Bo, CHEN Kequan, GUO Yueming, et al.Numerical simulation study on jump height of iced transmission lines after ice shedding[J].IEEE Transactions on Power Delivery，2013，28(1) ：216-225．

[15] WU Chuan, YAN Bo, ZHANG Liang, et.al.A method to calculate jump height of iced transmission lines after ice-shedding[J].Cold Regions Science and Technology，2016，125 ：40-47.

[16] 张殿生. 电力工程高低压送电线路设计手册[M]. 北京：中国电力出版社，2005.

[17] RADMER D T, KUNTZ P A, CHRISTIE R D, et al.Predicting vegetation-related failure rates for overhead distribution feeders[J].IEEE Transactions on Power Delivery，2002，17(4) ：1170-1175．

[18] 廖峥，熊小伏，李新，等. 基于 BP 神经网络的输电线路舞动预警方法[J] . 电力系统保护与控制，2017，45(19) ：154-161.

[19] WANG Jian, XIONG Xiaofu, ZHOU Ning, et al.Early warning method for transmission line galloping based on SVM and AdaBoost bi-level classfiers[J].IET Generation, Transmission &Distribution，2016，10(14) ：3499-3507.

[20] YUAN S, QUIRING S M, ZHU L, et al.Development of a typhoon power outage model in Guangdong,China[J].International Journal of Electrical Power & Energy Systems，2020，117 ：105711.

[21] 郑凌铭，舒胜文，陈彬，等. 强台风环境下基于格点化和支持向量机的 10 kV 杆塔受损量预测方法[J]. 高电压技术，2020，46(1) ：42-50．

[22] 谢云云，薛禹胜，文福拴，等. 冰灾对输电线故障率影响的时空评估[J] . 电力系统自动化，2013，37(18) ：32-41.

[23] 谢云云，薛禹胜，王昊昊，等. 电网雷击故障概率的时空在线预警[J] . 电力系统自动化，2013，37(17) ：44-51.

[24] 中国电力企业联合会.110 kV～750 kV 架空输电线路设计规范：GB 50545—2010[S] . 北京：人民出版社，2010 ：109.

[25] WEN Yi, CHEN Yifei, WU Jianrong, et al.Research on Risk Assessment and Suppression Measures for Ice-Shedding on 500 kV Compact Overhead Lines[J].Energies，2022，15(21) ：8005.

[26] 邵天晓. 架空送电线路的电线力学计算[M]. 北京：中国电力出版社，2003.

[27] 王斌，李立浧，魏发生，等. 不均匀覆冰下的架空地线覆冰在线监测力学计算模型改进[J] . 高电压技术，2022，48(11) ：4538-4545.

[28] HAYKIN S.Neural Networks: A Comprehensive Foundation[M].New Jersey ：Prentice Hall PTR，1998.

[29] 陆益锰，安旭文，刘智勇，等. 输电线路覆冰厚度的概率分布模型比较分析[J] . 四川建筑，2015，35(2) ：263-266.

返回索引列表

Article retrieval

文章检索

基于机器学习的紧凑型架空线路脱冰跳跃风险预测研究