一种特高压直流输电线路神经网络双端故障测距新方法

A Novel Two Terminal Fault Location Method Used ANN for UHVDC Transmission Line

提出一种基于高频量衰减特性的特高压直流输电线路神经网络双端故障测距方法。传统基于高频量衰减特性的特高压直流输电线路双端测距方法的测距精度依赖于线路衰减常数的准确求取,但准确计算线路衰减常数是一个难题。人工神经网络具有很强的非线性逼近拟合能力,利用人工神经网络方法,将不必准确计算线路衰减常数也能准确实现故障定位。选取不同频带内整流侧和逆变侧测距装置处检测到的故障电压行波线模分量高频部分首波头幅值比作为BP神经网络的输入样本集,故障距离作为输出样本集,对神经网络进行训练、测试,形成直流输电线路故障测距神经网络模型,将反映故障位置的特征数据输入训练后的网络模型即可实现故障测距。大量仿真结果表明:该基于高频量衰减特性的特高压直流输电线路神经网络双端故障测距方法精度较高,而且耐受过渡电阻能力强。

A novel two terminal fault location method used ANN for UHVDC transmission line based on the attenuation characteristic of signals with high frequency is proposed. The precision of traditional fault location method for UHVDC transmission line based on the attenuation characteristic of signals with high frequency depends on the accuracy of attenuation constant of transmission line, but it is difficult to compute that accurately, ANN that is a good tool for non-linear data modeling and non-linear function curve-fitting is selected to solve the aforementioned problems. The ratios of amplitude of initial traveling wave head of the aerial mode component of voltage traveling wave with high frequency in rectifier side to which in the inverter side of each wavelet level are chosen as the inputs and fault distance as the outputs for training and testing the neural network for fault location in the UHVDC transmission line, and fault distance can be obtained when input fault characteristic data to the trained model. A variety of transmission line fault situation are simulated based on the PSCAD, and this proposed two terminal fault location method used ANN for UHVDC transmission line based on the attenuation characteristic of signals with high frequency shows satisfactory performance.