特重冰区特高压直流孤立档导线脱冰动力响应参数预测模型  

Dynamic response parameters prediction models of isolated-span conductor lines in ultra-heavy ice zones after ice-shedding

作　　者：张立光 滕宇 董松昭 王炜 李占岭 高英博 严波[3] ZHANG Liguang;TENG Yu;DONG Songzhao;WANG Wei;LI Zhanling;GAO Yingbo;YAN Bo(Power Chins Hebei Electric Power Engineering Co.,Ltd.,Shijiazhuang 050000,China;Heibei Electric Power Design&Survey Technology Innovation Center,Shijiazhuang 050000,China;College of Aerospace Engineering,Chongqing University,Chongqing 400044,China)

机构地区：[1]中国电建集团河北省电力勘测设计研究院有限公司,石家庄050000 [2]河北省电力勘测设计技术创新中心,石家庄050000 [3]重庆大学航空航天学院,重庆400044

出　　处：《振动与冲击》2024年第12期221-231,275,共12页Journal of Vibration and Shock

基　　金：中国电建集团河北省电力勘测设计研究院有限公司科技项目(22-KJDW001)。

摘　　要：特重冰区特高压直流线路导线覆冰设计厚度达60~80 mm,多采用孤立档。该文针对特重冰区特高压直流六分裂导线,建立有限元模型,模拟研究不同档距、高差比、覆冰厚度、脱冰率和风速条件下孤立档导线脱冰动力响应,并分析其响应特征。给出导线冰跳高度包络线、有风情况下导线脱冰后横向摆幅参数和纵向不平衡张力的定义。结合利用数值模拟结果建立的数据集和BP(back propagation)神经网络机器学习算法,建立以档距、高差比、覆冰厚度、脱冰率和风速为输入,导线冰跳高度包络线、最大横向摆幅、最小横向摆幅、脱冰前平衡位置、孤立档两端纵向不平衡张力为输出的预测模型,为特重冰区特高压直流线路塔头设计提供依据。The design ice thickness for the ultra-high voltage DC lines in ultra-heavy ice zones may arrive at 60 mm-80 mm,and isolated-span lines are usually employed.In this paper,the finite element models of the ultra-high voltage DC lines in ultra-heavy ice zones were set up,the dynamic responses of the lines with different span length,elevation difference ratio under different ice thickness,ice-shedding rate and wind speed were numerically simulated,and the dynamic response characteristics were analyzed.The conductor jump height envelop,transverse swing amplitude and axial unbalanced tension were defined.Combining numerical simulations and the BP(back propagation) neural network algorithm,the prediction models for the dynamic response parameters with span length,elevation difference ratio,ice thickness,ice-shedding rate and wind speed as input were established.The prediction models provide instruction for the tower head design of the ultra-high voltage DC lines in ultra-heavy ice zones.

关 键 词：特重冰区 特高压直流线路 脱冰动力响应参数 机器学习 预测模型 

分 类 号：TM75[电气工程—电力系统及自动化] O39[理学—工程力学]