人工神经网络在电力系统暂态安全分析中的应用研究  

Artificial neural networks for power system transient security assessment

作　　者：陶兰 江缉光 肖达川[1] 

机构地区：[1]清华大学电机工程与应用电子技术系

出　　处：《清华大学学报（自然科学版）》1994年第4期62-68,共7页Journal of Tsinghua University(Science and Technology)

基　　金：国家博士点基金

摘　　要：探讨了两种人工神经网络用作电力系统暂态安全分析工具的适用性。首先将一个适度规模电网的暂态稳定性分析问题转化成适合于人工神经网络处理的识别问题。对样本数据进行适当的预处理后，分别将ＢＰＮ和ＫＮＮ两种神经网络用于该系统的暂稳分析；并就人工神经网络对暂稳分析问题的映射能力、插值可信度估计、网络大小等问题，分析和比较了两种模型的适用性和优劣。结果表明，ＫＮＮ模型作为暂稳分析工具有着更大的潜力。This paper explores the suitability of using two artificial neural network models(ANN) as tools for power system transient security assessment (TSA). Firstly, a TSAproblem of a local power net is converted into a pattern recognition problem suitable for anANN analysis with sample data preprocessed. Then BPN and KNN models are used respectively for this TSA problem. The suitability and advantages of the two models are discussed and compared on mapping capability of the problem, estimation of certainty factoro f interpolating results and ANN size. The results show that application KNN model isbetter than BPN from the point of view of TSA.

关 键 词：人工 神经网络 电力系统 暂态稳定 

分 类 号：TM712[电气工程—电力系统及自动化]