GSM-XGBoost Prediction of Ice Types for Overhead Transmission Lines Driven by the Fusion of Images and Micrometeorological Data from the Past Three Days

Sirui CHEN; Yanpeng HAO; Lei HUANG; Wei LIANG; Zijian WU; Jinqiang HE; Huan HUANG

doi:10.13648/j.cnki.issn1674-0629.2026.07.014

PDF(4863 KB)

South Power Sys Technol ›› 2026, Vol. 20 ›› Issue (7) : 143-154. DOI: 10.13648/j.cnki.issn1674-0629.2026.07.014

GSM-XGBoost Prediction of Ice Types for Overhead Transmission Lines Driven by the Fusion of Images and Micrometeorological Data from the Past Three Days

Author information +

History +

Abstract

The safety of overhead transmission lines is threatened by icing. Due to the different degrees of damage caused by ice types including glaze, mixed rime, rime, and wet snow to overhead transmission lines, the de-icing measures taken are also different. When the icing of overhead transmission lines reaches a certain level, appropriate operation and maintenance decisions will be made according to different icing type, including melting the ice, using mechanical removal and adjusting the operation mode. Icing type prediction can provide insights into future icing risks. On the basis of study on identifying insulator icing types through images, a data-driven ice type prediction model is proposed, which fuses monitoring images with micrometeorological data from the past three days. Based on the icing monitoring data of China Southern Power Grid from 2014 to 2021, the nearest micrometeorological monitoring time from the same terminal is searched according to the image capture time. Micrometeorological time series from this time and the past three days is combined with the image to form a sample, constructing a fused dataset of images and micrometeorological data for the data-driven ice type prediction model. The Grid Search Method-eXtreme Gradient Boosting （GSM-XGBoost） is used as the model algorithm, and the micrometeorological time series at 6h intervals from the past three days are used as inputs. The icing types identified from images are used as outputs. With 4 503 fused samples of the training set and 1 931 fused samples of the test set, the macro precision （P _m）, macro recall （R _m）, and macro F1 score of the data-driven icing type prediction model are 95.0 %, 96.3 %, and 95.6 %, respectively. The icing type prediction for overhead transmission lines is achieved accurately.

Key words

icing types / monitoring images / micrometeorology / data fusion

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Sirui CHEN , Yanpeng HAO , Lei HUANG , et al . GSM-XGBoost Prediction of Ice Types for Overhead Transmission Lines Driven by the Fusion of Images and Micrometeorological Data from the Past Three Days[J]. Southern Power System Technology. 2026, 20(7): 143-154 https://doi.org/10.13648/j.cnki.issn1674-0629.2026.07.014

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis

[1]

李庆峰，范峥，吴穹，等. 全国输电线路覆冰情况调研及事故分析［J］. 电网技术， 2008， 32（9）： 33 - 36.

Qingfeng

， FAN

Zheng

， WU

Qiong

， et al. Investigation of ice-covered transmission lines and analysis on transmission line failures caused by ice-coating in China［J］. Power System Technology， 2008， 32（9）： 33 - 36.

Cited in this article [2]

[2]	胡毅. 电网大面积冰灾分析及对策探讨［J］. 高电压技术， 2008， 34（2）： 215 - 219. HU Yi. Analysis and countermeasures discussion for large area icing accident on power grid［J］. High Voltage Engineering， 2008， 34（2）： 215 - 219. Cited in this article [1]

[3]	蒋兴良，易辉. 输电线路覆冰及防护［M］. 北京：中国电力出版社， 2002. Cited in this article [2]

[4]	黄新波，刘家兵，蔡伟，等. 电力架空线路覆冰雪的国内外研究现状［J］. 电网技术， 2008， 32（4）： 23 - 28. HUANG Xinbo， LIU Jiabing， CAI Wei， et al. Present research situation of icing and snowing of overhead transmission lines in China and foreign countries［J］. Power System Technology， 2008， 32（4）： 23 - 28.

[5]	阳林，郝艳捧，黎卫国，等. 架空输电线路在线监测覆冰力学计算模型［J］. 中国电机工程学报， 2010， 30（19）： 100 - 105. YANG Lin， HAO Yanpeng， LI Weiguo， et al. A mechanical calculation model for online icing-monitoring system of overhead transmission lines［J］. Proceedings of the CSEE， 2010， 30（19）： 100 - 105. Cited in this article [2]

[6]	王敩青，戴栋，郝艳捧，等. 基于在线监测系统的输电线路覆冰数据统计与分析［J］. 高电压技术， 2012， 38（11）： 3000 - 3007. WANG Xiaoqing， DAI Dong， HAO Yangpeng， et al. Statistics and analysis of transmission lines icing data based on online monitoring system［J］. High Voltage Engineering， 2012， 38（11）： 3000 - 3007. Cited in this article [2]

[7]	国家能源局. 重覆冰架空输电线路设计技术规程： DL/T 5440—2009 ［S］. 北京：中国电力出版社， 2009. Cited in this article [1]

[8]

薛艺为，阳林，郝艳捧，等. 输电线路悬式复合绝缘子雨凇与轻雾凇覆冰形态和覆冰过程对比研究［J］. 电工技术学报， 2016， 31（8）： 212 - 219.

XUE

Yiwei

， YANG

Lin

， HAO

Yanpeng

， et al. A comparative study on icing morphology and process of glaze and light rime in suspension composite insulators on transmission lines［J］. Transactions of China Electrotechnical Society， 2016， 31（8）： 212 - 219.

Cited in this article [1]

[9]	国家能源局. 电力工程气象勘测技术规程： DL/T 5158—2012 ［S］. 北京：中国规划出版社， 2012. Cited in this article [1]

[10]

律方成，尤少华，刘云鹏，等. 雨雪天气下特高压交流单回试验线段电晕损失实测分析［J］. 高电压技术， 2011， 37（9）： 2089 - 2095.

Fangcheng

LÜ

， YOU

Shaohua

， LIU

Yunpeng

， et al. Analysis on corona loss measurement of ultra high voltage AC single circuit test line in rain and snow weather conditions［J］. High Voltage Engineering， 2011， 37（9）： 2089 - 2095.

Cited in this article [2]

[11]	何高辉，胡琴，喻建波，等. 导线雨凇覆冰及其直流电晕损失影响因素研究［J］. 中国电机工程学报， 2021， 41（24）： 8610 - 8618. HE Gaohui， HU Qin， YU Jianbo， et al. Research on the influence factors of conductor glaze icing and corresponding DC corona loss［J］. Proceedings of the CSEE， 2021， 41（24）： 8610 - 8618. Cited in this article [1]

[12]	李亚伟，张星海，贾志东，等. 不同覆冰类型绝缘子串的泄漏电流特征分析［J］. 电网技术， 2017， 41（11）： 3691 - 3697. LI Yawei， ZHANG Xinghai， JIA Zhidong， et al. Characteristic analysis of leakage current of insulator strings under different icing types［J］. Power System Technology， 2017， 41（11）： 3691 - 3697. Cited in this article [1]

[13]

周庆，李杰，万凌云，等. 基于D-S证据理论的多特征输电线路覆冰图像分类方法研究［J］. 仪器仪表学报， 2016， 37（S1）： 102 - 107.

ZHOU

Qing

， LI

Jie

， WAN

Lingyun

， et al. Research on image classifycation of multi feature based on D-S evidence theory for transmission line icing image［J］. Chinese Journal of Scientific Instrument， 2016， 37（S1）： 102 - 107.

Cited in this article [1]

[14]	YANG L， JIANG X， HAO Y， et al. Recognition of natural ice types on in-service glass insulators based on texture feature descriptor［J］. IEEE Transactions on Dielectrics and Electrical Insulation， 2017， 24（1）： 535 - 542. Cited in this article [1]

[15]	HAO Y， LIANG W， YANG L， et al. Methods of image recognition of overhead power line insulators and ice types based on deep weakly-supervised and transfer learning［J］. IET Generation， Transmission & Distribution， 2022， 16（11）： 2140 - 2153. Cited in this article [5]

[16]

阳林，郝艳捧，黎卫国，等. 输电线路覆冰与导线温度和微气象参数关联分析［J］. 高电压技术， 2010， 36（3）： 775 - 781.

YANG

Lin

， HAO

Yanpeng

， LI

Weiguo

， et al. Relationships among transmission line icing conductor temperature and local meteorology using grey relational analysis［J］. High Voltage Engineering， 2010， 36（3）： 775 - 781.

Cited in this article [1]

[17]	黄新波，王玉鑫，朱永灿，等. 基于遗传算法与模糊逻辑融合的线路覆冰预测［J］. 高电压技术， 2016， 42（4）： 1228 - 1235. HUANG Xinbo， WANG Yuxin， ZHU Yongcan， et al. Icing forecast of transmission line based on genetic algorithm and fuzzy logic［J］. High Voltage Engineering， 2016， 42（4）： 1228 - 1235. Cited in this article [1]

[18]	SUN W， WANG C. Staged icing forecasting of power transmission lines based on icing cycle and improved extreme learning machine［J］. Journal of Cleaner Production， 2019（208）： 1384 - 1392. Cited in this article [1]

[19]

熊玮，徐浩，徐林享，等. 计及时间累积效应的RF-APJA-MKRVM输电线路覆冰组合预测模型［J］. 高电压技术， 2022， 48（3）： 948 - 957.

XIONG

Wei

， XU

Hao

， XU

Linxiang

， et al. Combined model of icing prediction of transmission lines based on RF-APJA-MKRVM considering time cumulative effect［J］. High Voltage Engineering， 2022， 48（3）： 948 - 957.

Cited in this article [1]

[20]	韩兴波，陈孜铭，邢镔，等. 采用基本环境参数的导线覆冰预测方法［J］. 重庆大学学报， 2023， 46（11）： 69 - 77. HAN Xingbo， CHEN Ziming， XING Bin， et al. Prediction model of conductor icing based on basic environmental parameters［J］. Journal of Chongqing University， 2023， 46（11）： 69 - 77. Cited in this article [2]

[21]	李昊，傅闯，刘旭，等. 南方电网架空输电线路覆冰监测系统及其运行分析［J］. 陕西电力， 2013， 41（4）： 20 - 23. LI Hao， FU Chuang， LIU Xu， et al. Overhead transmission line ice monitoring system of China Southern Power Grid & its operation analysis［J］. Shanxi Power， 2013， 41（4）： 20 - 23. Cited in this article [1]

[22]	国家市场监督管理总局，国家标准化管理委员会. 架空输电线路运行状态监测系统： GB/T 25095—2020 ［S］. 北京：中国标准出版社， 2020. Cited in this article [1]

[23]	TUKEY J W. Exploratory data analysis［J］. Journal of the American Statistical Association， 1977， 26（2）： 163 - 182. Cited in this article [1]

[24]	CHEN T， GUESTRIN C. Xgboost： a scalable tree boosting system［C］//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining， August 13 - 17， 2016， San Francisco，USA. New York： ACM， 2016： 785 - 794. Cited in this article [1]

[25]	李轩，梅飞，沙浩源，等. 基于多状态数据均衡与XGBoost的特高压换流阀运行状态评估［J］. 高电压技术， 2022， 48（2）： 644 - 652. LI Xuan， MEI Fei， SHA Haoyuan， et al. Operation state evaluation of UHV converter valve based on multi-state data equalization and XGBoost［J］. High Voltage Engineering， 2022， 48（2）： 644 - 652. Cited in this article [1]

[26]	李楠，张家恒，等. 基于XGboost-DF 的电力系统暂态稳定评估方法［J］.电测与仪表，2024， 61（10）： 119 - 127. LI Nan， ZHANG Jiaheng.A transient stability assessment method of power system based on XGboost-DF［J］. Electrical Measurement & Instrumentation， 2024，61（10）： 119 - 127. Cited in this article [1]

[27]	PADILLA R， NETTO S， SILVA E. A survey on performance metrics for object-detection algorithms［C］//2020 International Conference on Systems， Signals and Image Processing， July 1 - 3， 2020， Niteroi， Brazil. New York： IEEE， 2020： 237 - 242. Cited in this article [1]

[28]	HOCHREITER S， SCHMIDHUBER J. Long short-term memory［J］. Neural Computation， 1997， 9（8）： 1735 - 1780. Cited in this article [1]

[29]	彭宇文，杨之乐，李冰，等.基于VMD-ISSA-LSTM的短期光伏发电功率预测［J］. 广东电力，2024，37（1）：18 - 26. PENG Yuwen， YANG Zhile， LI Bing，et al. Short term photovoltaic power generation prediction based on VMD-ISSA-LSTM［J］. Guangdong Electric Power，2024，37（1）： 18 - 26.

[30]	汪繁荣，李州.基于SCSSA-BiLSTM的变压器故障诊断模型［J］.南方电网技术，2026，20（2）：78 - 86. WANG Fanrong， LI Zhou.Transformer fault diagnosis model based on SCSSA-BiLSTM［J］. Southern Power System Technology，2026，20（2）：78 - 86. Cited in this article [1]

[31]	王洪彬，李智，童晓阳，等. 基于GRU 的智能变电站二次设备故障定位研究［J］.电测与仪表， 2025， 62（7）： 200 - 208. WANG Hongbin， LI Zhi， TONG Xiaoyang， et al.Fault location of secondary equipment in smart substation based on GRU［J］. Electrical Measurement & Instrumentation， 2025，62（7）： 200 - 208. Cited in this article [1]

[32]	CHO K， MERRIENBOER B V， GULCEHRE C， et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation［EB/OL］. （2014 - 06 - 03）［2014 - 9-3］. Cited in this article [1]

[33]	COVER T， HART P. Nearest neighbor pattern classification［J］. IEEE Transactions on Information Theory， 1967， 13（1）： 21 - 27. Cited in this article [1]