|本期目录/Table of Contents|

[1]邓军,肖遥,郝艳捧,等.基于支持向量机的无线电干扰预测算法 [J].电机与控制学报,2017,21(08):18-24.[doi:: 10.15938 /j.emc.2017.08.003]
 DENG Jun,XIAO Yao,HAO Yan-peng,et al. Radio interference prediction method based on support vector machine method [J].,2017,21(08):18-24.[doi:: 10.15938 /j.emc.2017.08.003]
点击复制

基于支持向量机的无线电干扰预测算法
()
分享到:

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:
21
期数:
2017年08
页码:
18-24
栏目:
出版日期:
2018-01-01

文章信息/Info

Title:
 Radio interference prediction method based on support vector machine method
作者:
 邓军12 肖遥2 郝艳捧1 李立浧1 赵宇明3 张建功4
 ( 1.华南理工大学 电力学院,广东 广州 510640; 2.南方电网 超高压输电公司检修试验中心,广东 广州 510663; 3.南方电网 科学研究院,广东 广州 510080; 4.国网电力 科学研究院,湖北 武汉 430074)
Author(s):
 DENG Jun 12 XIAO Yao 2 HAO Yan-peng 1 LI Li-cheng 1 ZHAO Yu-ming 3 ZHANG Jian-gong 4
 ( 1.School of Electric Power,South China University of Technology,Guangzhou 510640,China; 2.Maintenance & Test Center,EHV,China Southern Power Grid,Guangzhou 510663,China; 3.Electric Power Research Institute,China Southern Power Grid,Guangzhou 510080,China; 4.Research Institute,State Grid Power,Wuhan 430074,China)
关键词:
特高压直流 无线电干扰 灰色关联度 电磁环境 遗传算法 最小二乘支持向量机
Keywords:
ultra high voltage direct current the radio interference degree of grey incidence electromagnetic environment genetic algorithm least squares support vector machine
分类号:
TM 151
DOI:
: 10.15938 /j.emc.2017.08.003
文献标志码:
A
摘要:
针对给定海拔高度、温湿度、风速风向等环境因素下的特高压直流线路无线电干扰分布无法仿真计算的问题,采用灰色关联度模型提取给定环境参数相似的现场测试样本数据,利用遗传算法优化惩罚系数和支持向量的核宽度,提出了特高压直流无线电干扰预测的最小二乘支持向量机
法( lest squares support vector machine,LSSVM) 。通过分析迭代步数与训练误差证明了灰色关联度的遗传 LSSVM 方法计算效率和计算精确度优于 LSSVM 方法和遗传 LSSVM 方法。对比本文预测方法的计算结果与实际测量值、同类算法计算结果表明: 低海拔时 0.5 MHz 无线电干扰水平负极全压下平均偏差为 10.1%,正极半压负极全压下平均偏差为 6.75%,双极全压下平均偏差为4.64%; 海拔 1 900 m 时,双极全压下 0.5 MHz 和 10MHz 无线电干扰水平平均偏差分别为 4.63%和 3.5%。
Abstract:
Great efforts have been made in this paper for the radio interference ( RI) of ultera high voltage direct current( UHVDC) transmission lines for the given altitude,temperature,humidity,wind velocity, wind direction,etc.The degree of grey incidence and least squares support vector machine method,whose penalty coefficient and kernel functions can be optimized by genetic algorithm,has been presented to predict the RI of UHVDC transmission lines,where the degree of grey incidence model can extract the analogous sample data for the given environment.The numeric example has demonstrated that the better computational efficiency performance of least squares support vector machine( LSSVM) with the degree of grey incidence and genetic algorithm than that of the traditional LSSVM and the genetic LSSVM method.Furthermore,the maximum average relative error of the low altitude between the prediction results and test samples values for 0.5 MHz RI is 6.75%,4.64% and 10.1% for half-voltage of positive pole and full-voltage of negative pole,full-voltage of bipolar and full-voltage of the negative pole.Moreover,the average relative error for 10 MHz RI of full-voltage of bipolar with the 1 900 m altitude is less than that of the same measurement point for 0.5 MHz RI.

参考文献/References:

相似文献/References:

备注/Memo

备注/Memo:
收稿日期: 2013-12-27
基金项目: 国家高技术研究发展计划( 2012AA050209)
作者简介: 邓 军( 1985—) ,男,博士,高级工程师,研究方向为高压直流输电技术;
肖 遥( 1960—) ,男,本科,教授级高工,研究方向为高压直流输电技术、电网谐波等;
郝艳捧( 1974—) ,男,教授,博士生导师,研究方向为关键电力设备绝缘状态诊断、电力系统过电压及其防护等研究;
李立浧( 1941—) ,男,博士生导师,工程院院士,研究方向为高压直流输电验技术;
赵宇明( 1978—) ,男,博士,教授级高工,研究方向为高压直流输电技术;
张建功( 1975—) ,男,博士,高级工程师,研究方向为电磁环境技术。
更新日期/Last Update: 2017-11-20