基于神经网络的黑启动操作过电压的快速预测.pdfVIP

30 卷 3 期 电 网 技 术 Vol. 30 No. 3 2006 年2 月 Power System Technology Feb. 2006 文章编号：1000-3673 （2006 ）03-0066-05 中图分类号：TM732 文献标识码：A 学科代码：470 4054 基于神经网络的黑启动操作过电压快速预测 李膨源，顾雪平 （电力系统保护与动态安全监控教育部重点实验室（华北电力大学），河北省 保定市 071003 ） Fast Determination of Switching Overvoltage in Black Start Process Based on Artificial Neural Networks LI Peng-yuan，GU Xue-ping （Key Laboratory of Power System Protection and Dynamic Security Monitoring and Control (North China Electric Power University) ，Ministry of Education，Baoding 071003 ，Hebei Province，China ） ABSTRACT ：During the process to work out black start 局部系统的故障可能在保护和自动装置不正确动 scheme of power system, it is necessary to repeatedly calculate 作的情况下发展成大面积的停电事故，甚至整个电 and verify the switching overvoltage of the energized [1] 力系统的崩溃瓦解，给国民经济带来巨大的损失 。 transmission line for various black start schemes. The authors 因此研究大系统故障后的恢复问题 （ 黑启动）显 propose a method to quickly determine black start caused 得十分重要。黑启动涉及电力系统运行的许多方 switching overvoltage by artificial neural network. By means [2] [3,4] 面，例如合闸过电压 、静态稳定与低频振荡 、 of choosing a group of effective input features a total sample [5] 电压与频率稳定性等 。黑启动方案的制定需要大 space is composed and using EMTP software package the training sample set and test sample set are built up. The 量的计算分析，并包含人类大量的智能活动，是一 back-propagation neural network is used to construct the 项非常重要而繁重的工作。借助人工智能技术，并 mapping relation between input feature and peak values o