基于IPSO‑BP神经网络的导线舞动预警方法
作者:
作者单位:

(1.长沙理工大学土木工程学院,湖南 长沙 410114;2.长沙理工大学电气与信息工程学院,湖南 长沙 410114)

作者简介:

通讯作者:

杨春侠(1972—),女,博士,副教授,主要从事结构可靠度、机器学习方面的研究;E?mail:13973183346@126.com

中图分类号:

TM75

基金项目:

国家自科基金面上项目(52077010);国家自然科学基金(51678067);国家自然科学基金青年科学基金(51808054)


A prediction method of line galloping based on IPSO‑BP neural network
Author:
Affiliation:

(1.School of Civil Engineering, Changsha University of Science & Technology, Changsha 410114, China; 2.School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China)

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为确保输电线路在易舞气象条件下的正常运维,根据线路舞动与气象条件之间的复杂映射关系,采用改进粒子群算法(improved particle swarm optimization,IPSO)对BP神经网络进行优化,提出一种基于改进粒子群算法优化BP(IPSO?BP)神经网络的导线舞动预测方法。利用文本挖掘技术分析舞动影响因素,确定以档距、覆冰厚度、温度、风速、风向、相对湿度及风向与线路走向夹角为特征输入的IPSO?BP神经网络模型,通过舞动历史数据训练模型以达到预测的功能。对比IPSO?BP神经网络模型与其他算法模型的精度和稳定性,结果表明该方法具有一定的优越性。最后采用该方法预测河南谢庄地区的导线舞动,验证该方法的准确性和实用性。

    Abstract:

    To ensure the normal operation and maintenance of transmission lines under meteorological conditions prone to galloping, according to the complex mapping relationship between line galloping and meteorological conditions, the improved particle swarm optimization (IPSO) is used to optimize the BP neural network, and a line galloping prediction method based on the improved particle swarm optimization BP (IPSO-BP) neural network is proposed. Text mining technology is used to analyze the influencing factors of line galloping, and an IPSO-BP neural network model with characteristic as inputs of span, ice thickness, temperature, wind speed, wind direction, relative humidity, and the angle between wind direction and line direction is determined. The model is trained through historical line galloping data to achieve the prediction function. Comparing the accuracy and stability of the IPSO-BP neural network model with other algorithm models, the results show that this method has certain advantages. Finally, this method is used to predict the line galloping in Xiezhuang area of Henan Province, which verifies the accuracy and practicability of the method.

    参考文献
    相似文献
    引证文献
引用本文

杨春侠,曹 倩,于增豪,等.基于IPSO‑BP神经网络的导线舞动预警方法[J].电力科学与技术学报,2024,39(2):152-158.
YANG Chunxia, CAO Qian, YU Zenghao, et al. A prediction method of line galloping based on IPSO‑BP neural network[J]. Journal of Electric Power Science and Technology,2024,39(2):152-158.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-05-29
  • 出版日期: