基于环境激励数据的次同步振荡参数在线估计方法

An On-Line Estimation Method of Sub-Synchronous Oscillation Parameters Based on Ambient Excitation Data

环境激励信号是一种时间序列信号,具有很强的非线性特征。基于门控循环单元神经网络(gated recurrent unit,GRU)和Attention机制搭建人工智能模型,通过训练完成的人工智能模型对时序量测信号进行直接辨识,即可得出系统存在次同步振荡模式的频率和阻尼比。算例分析表明,所提方法可在多种复杂多变的电力系统运行场景下提取环境激励数据中的次同步振荡参数信息,拥有优秀的泛化使用性;模型计算速度快,拥有良好的实时性,适于在线的次同步振荡参数估计;模型基于数据驱动,拥有免模型分析的便利性。

In this paper,an artificial intelligence model is built based on the gated recurrent unit(GRU)and Attention mechanism.Through the artificial intelligence model completed by training,the sequential measurement signal is directly identified,and the frequency and damping ratio of the sub-synchronous oscillation mode can be obtained.Examples show that the proposed method can extract the sub-synchronous oscillation parameter information of ambient excitation data in a variety of complex and changeable power system operation scenarios,and has excellent generalization applicability.In addition,the model has fast computation speed and good real-time performance,which is suitable for online estimation of sub-synchronous oscillation parameters.The model is data-driven,which has convenience of model free analysis.