首页 | 本学科首页   官方微博 | 高级检索  
     

特高压复合绝缘子电场计算及基于神经网络遗传算法的均压环结构优化设计
引用本文:司马文霞,施健,袁涛,杨庆,孙才新. 特高压复合绝缘子电场计算及基于神经网络遗传算法的均压环结构优化设计[J]. 高电压技术, 2012, 38(2): 257-265
作者姓名:司马文霞  施健  袁涛  杨庆  孙才新
作者单位:重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆,400030
基金项目:国家创新研究群体基金,国家重点基础研究发展计划(973计划)
摘    要:为了满足超/特高压大容量输电技术的发展需求,研究复合绝缘子的电场分布,寻找合理的电场优化措施已成为影响输电线路安全运行的关键因素。利用有限元法(FEM)建立了工程实际应用情况下特高压(UHV)交流输电线路复合绝缘子的单串、双串和V串电场计算模型,在考虑横担、分裂导线和均压环及其金具连接情况下,对复合绝缘子的电位和沿面电场分布进行了计算。针对特高压复合绝缘子电位分布极不均匀,且最大沿面电场强度大大超过电晕起始场强的情况,分析了不同的均压环配合方式对复合绝缘子沿面电场分布的影响。针对单串绝缘子下的计算结果,引入神经网络遗传算法(BP-GA),对均压环的结构参数进行了优化设计,利用BP神经网络的高度非线性映射能力直接计算遗传算法的适应度函数值,解决了穷举法计算时间冗长的问题。计算结果表明:加装均压环能够大大降低最大沿面电场强度,明显改善复合绝缘子沿面电位和电场的分布;通过遗传算法优化后的均压环结构参数,能使均压环表面场强和绝缘子沿面场强均小于电晕起始场强,为特高压绝缘子均压环的选取提供了一种可靠、实用的设计方法,可为我国特高压输电线路外绝缘优化设计提供新的参考。

关 键 词:复合绝缘子  电位  沿面电场  均压环  优化  神经网络  遗传算法

Electric Field Calculation of Ultra High Voltage Composite Insulator and Optimization Design of Corona Ring Structure Based on Neural Network and Genetic Algorithm
SIMA Wenxia,SHI Jian,YUAN Tao,YANG Qing,SUN Caixin. Electric Field Calculation of Ultra High Voltage Composite Insulator and Optimization Design of Corona Ring Structure Based on Neural Network and Genetic Algorithm[J]. High Voltage Engineering, 2012, 38(2): 257-265
Authors:SIMA Wenxia  SHI Jian  YUAN Tao  YANG Qing  SUN Caixin
Affiliation:(State Key Laboratory of Power Transmission Equipment & System Security and New Technology,Chongqing University,Chongqing 400030,China)
Abstract:To meet requirement of UHV/EHV transmission development,study on electric field distribution along composite insulator surface and finding a reasonable electric field optimization method have become critical in transmission line operation safety.By finite element method(FEM),we established a calculation model for I,II and V type composite insulator of UHV AC transmission lines,and calculated the potential distribution and the electric field along the surface of composite insulator by taking cross arm,bundled conductors and corona ring with connecting metal into consideration.In accordance with the extremely inhomogeneous potential distribution and the fact that the maximum value of electric field is much more than critical coronal electric field,we analyzed the influence of different combination of corona rings on surface electric field distribution of composite insulator.Basing on the calculation results,we introduced the back propagation neural network and genetic algorithm to optimize design of corona structural parameters.Moreover,by using the highly nonlinear mapping capability to directly calculate fitness function of genetic algorithm,we solved the time lengthy problem of exhaustion method.The results reveal that,after installing corona ring,the maximum surface electrical field is greatly lowered and the surface potential and electrical field distribution along composite insulator are apparently improved.By using the corona ring structural parameters which are optimized from back propagation neural network and genetic algorithm,the surface electrical fields of corona ring and composite insulator are smaller than respective critical coronal electric field.The calculation method provides a method for selecting the parameters of corona rings and the conclusions can be used to optimize the design of external insulation of UHV transmission lines in China.
Keywords:composite insulator  potential  surface electric field  corona ring  optimization  neural network  genetic algorithm
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号