基于多尺度行波功率的T接线路故障识别方法

为提高T接输电线路故障识别算法的精确性与可靠性,提出了一种基于多尺度行波有功功率和概率神经网络的T接输电线路故障识别方法。基于S变换分别计算区内3个行波保护单元多频率下的初始行波平均有功功率,并以此组成T接输电线路故障特征向量样本集。建立概率神经网络故障识别模型,并利用T接线路故障特征样本集对其进行训练和测试,从而识别出故障所在支路。仿真结果表明,所提算法在各种工况下均能快速准确地识别T接输电线路区内外故障所在支路,在近O点故障、数据丢失、噪声影响、CT饱和等情况下也能较好地识别故障支路。

Fault Identification Method for T-connection Transmission Lines Based on Multiscale Traveling Wave Power

To improve the accuracy and reliability of the fault identification algorithm for T-connection transmission lines,a novel method for identifying the fault occurring on T-connection transmission lines is proposed,which is based on multiscale traveling wave active power and probabilistic neural network(PNN)according to the characteristics of Tconnection transmission lines.Based on the S-transform,the average active power of initial traveling wave of three trav?eling wave protection units at multiple frequencies in the area are calculated,respectively,which are used to form a sample set of T-connection transmission line fault feature vectors accordingly.A PNN fault identification model is estab?lished,which is trained and tested using the T-connection transmission line fault feature sample set,thus identifying the fault branch.Simulation results show that the proposed algorithm can quickly and accurately identify the branches where faults are located inside and outside the T-connection transmission line under various operating conditions.More?over,it can better identify faults under conditions such as the near O-point fault,data loss,noise impact,and CT satu?ration.