人工神经网络和短时仿真结合的暂态安全评估事故筛选方法  

INTEGRATION OF ANNS AND SHORT-DURATION NUMERICAL SIMULATION FOR CONTINGENCY SCREENING OF TRANSIENT SECURITY ASSESSMENT

作　　者：顾雪平[1,2] 曹绍杰[1,2] 张文勤[1] 

机构地区：[1]华北电力大学电力工程系 [2]香港城市大学

出　　处：《电力系统自动化》1999年第8期16-19,26,共5页Automation of Electric Power Systems

摘　　要：结合人工神经网络（ＡＮＮ）和短时数字仿真提出一个用于在线暂态安全评估的事故筛选方法，将３层ＢＰ网络作为模式分类器，用来建立稳定评估结果和所选特征量之间的映射关系。在故障切除时刻终止的短时数字仿真被用来生成ＡＮＮ的输入量，每个ＡＮＮ处理一个特定的事故状态。使用一个半监督学习算法，ＡＮＮ可产生一个能够指示相对稳定度的连续分布的暂态稳定指标。基于这个连续分布的稳定指标，设置一个相对保守的分类门槛值，避免了不安全状态的漏报。１０机新英格兰电力系统的应用结果证实了该方法的有效性。Integration of short-duration numerical simulation techniques and artificial neural networks is investigated for application to contingency screening of dynamic security assessment. In the proposed approach, the back-propagation neural networks are employed to assess transient stability of power systems. The short-duration numerical simulation is employed to produce the input atributes to the ANNs. Each ANN is designed to handle a single contingency scenario. The ANN can derive a continuous-spread stability index to indicate the relative stability degree by means of a semi-supervised learning algorithm. Based on the stability index, a conservative classification threshold is set to avoid omission of insecure cases. Applications to the 10-unit New England Power System demonstrate the validity of the proposed approach.

关 键 词：电力系统 暂态稳定 神经网络 安全评估 事故筛选 

分 类 号：TM712[电气工程—电力系统及自动化] TP18[自动化与计算机技术—控制理论与控制工程]