摘要
在黑启动方案制定的过程中,需要对方案进行反复的空充输电线路操作过电压统计计算和校验,带来沉重的工作负担。提出利用人工神经网络快速预测黑启动空载合闸统计过电压的方法。通过选择一组有效的输入特征并采用过电压时域仿真程序建立训练样本集,误差反向传播神经网络被用来构造输入特征和最大统计过电压之间的映射关系,从而实现黑启动合闸统计过电压的快速预测。算例表明方法的有效性。
In the black-start scheme design, a majority of the work is to calculate and assess the switching overvoltages for transmission line energization. A fast forecasting method to determine the no-load switching statistical overvohages of black-start is proposed by use of artificial neural r^etworks. By selecting a group of effective input features and building a training sample set by a time-domain simulation program of no-load switching overvoltage, the back-propagation neu- ral network is trained to constructing the mapping between the input features and the peak values of the statistical over- voltages, The trained neural network is used to determine the switching statistical overvoltages quickly without time-con- suming simulation. The effectiveness of the proposed method is validated by a numerical example.
出处
《华北电力大学学报（自然科学版）》
CAS
北大核心
2012年第5期6-11,92,共7页
Journal of North China Electric Power University：Natural Science Edition
基金
国家自然科学基金项目(50907021
50837002)
"111"引智计划(B08013)
中央高校基本科研业务费专项资金项目(11MG01
09QX64)
河北自然科学基金项目(E2012502034)
教育部留学回国人员科研启动基金资助项目(教外司留[2011]1139号)
关键词
空充输电线路
操作过电压
统计过电压
黑启动
人工神经网络
电力系统
transmission line energization
switching overvoltage
statistic overvohage
black start
artificial neuralnetworks
power systems
