基于信息融合技术的电力系统暂态稳定评估.pdfVIP

27 卷 16 期 中 国 电 机 工 程 学 报 Vol.27 No.16 Jun. 2007 2007 年6 月 Proceedings of the CSEE 2007 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2007) 16-0019-05 中图分类号：TM76 文献标识码：A 学科分类号：47040 基于信息融合技术的电力系统暂态稳定评估 辉，舒乃秋，李自品，李 玲，裴春明 （武汉大学电气工程学院电机与控制研究所，湖北省武汉市 430072 ） Power System Transient Stability Assessment Based on Information Fusion Technology HUANG Hui, SHU Nai-qiu, LI Zi-ping, LI Ling, PEI Chun-ming (Motor and Control Graduate School, School of Electrical Engineering, Wuhan University, Wuhan 430072, Hubei Province, China) ABSTRACT: A power system transient stability assessment 利用D-S 证据理论实现时间域和空间域的决策级融合，从而 method is proposed based on an information fusion model of 提高了电力系统暂态稳定评估的可靠性。利用中国版 BPA combining artificial neural net (ANN) method and D-S 暂态稳定程序和电力系统全过程动态仿真软件，对7 机 24 evidence theory in the paper. When accidents occur, much 节点系统进行了仿真。仿真结果表明，基于信息融合技术的 information obtained from power networks and generators are 电力系统暂态稳定评估方法较基于人工神经网络的评估方 synthesized to diagnose power system transient stability by the 法更为快速、准确。 studied method. Firstly, the characteristic parameters that can 关键词 特征量；信息融合；人工神经网络；D-S 证据理论； rapidly reflect the transient process, such as power angle, 电力系统暂态稳定分析 acceleration and rotor kinetic energy, etc., are selected for image-level fusion of ANN. Then the characteristic parameters 0 引言 are classified into time and spatial symptom field, and inputted 目前，许多学者将人工智能和模式识别技术相 respectively to