基于BP神经网络的输电线路电场屏蔽效果预测  

Prediction of electric field shielding effect of transmission line based on BP neural network

作　　者：于利佳 田瑾[1] 吴飞[1] 龚利[2] YU Lijia;TIAN Jin;WU Fei;GONG Li(College of Electronic and Electrical Engineering,Shanghai University of Engineering Science,Shanghai 201620,China;School of Urban and Regional Sciences,East China Normal University,Shanghai 200062,China)

机构地区：[1]上海工程技术大学电子电气工程学院,上海201620 [2]华东师范大学城市与区域科学学院,上海200062

出　　处：《传感器与微系统》2022年第2期108-110,114,共4页Transducer and Microsystem Technologies

基　　金：上海市科委重点科技项目(18511101600);上海工程技术大学检测技术与自动化装置学科学位点建设项目(19XXK003)。

摘　　要：针对超高压(EHV)同塔双回交流(AC)输电线路下方工频电场,首先基于有限元法建立输电线路模型,通过架设屏蔽线研究屏蔽线数量、位置的变化与屏蔽效果之间关系,计算得到部分屏蔽线位置电场强度值作为训练值,对于未知位置对应的屏蔽效果,提出采用反向传播(BP)神经网络进行预测。结果表明:预测值与真实值之间最大误差仅为0.6%,具有良好的预测效果,可为交流超高压输电线路电场环境优化及建设提供参考依据。Aiming at the power frequency electric field under the double-circuit alternating current(AC)transmission line on the same tower,the transmission line model is first established based on the finite element method,and the relationship between the change in the number and position of the shielded wires and the shielding effect is studied by erecting the shielded wires.The position electric field strength value is used as the training value.For the shielding effect corresponding to the unknown position,a back propagation(BP)neural network is proposed for prediction.The results show that the maximum error between the predicted value and the true value is only 0.6%,which has a good prediction effect,and can provide a reference for the optimization and construction of the electric field environment of AC extra high voltage(EHV)transmission lines.

关 键 词：输电线路 有限元法 屏蔽线 反向传播神经网络 

分 类 号：TM723[电气工程—电力系统及自动化]