基于神经网络的高压输电线路单端测距方法

针对单端行波故障测距第二个行波波头性质辨识问题，提出一种将小波模极大值方法和神经网络算法相结合的测距方法。采集故障波头时间差和极性等信息作为样本，利用神经网络的非线性拟合能力对样本进行训练、测试，从而建立相应的故障测距神经网络模型。将故障信息代入神经网络模型得到初步测距结果，根据初测结果和波头极性、时间差等性质的关系，对第二个行波波头进行正确辨识，从而得到优化的测距结果。经Matlab/Simulink仿真验证，该方法有较高的可靠性和精确性。

Single Terminal Fault Location Method for High Voltage Transmission Line Based on ANN

Aming at the question that the second traveling wave head for the single terminal fault location is difficult to be identified,a new fault location method combined with wavelet modulus maxima and artificial neutral network(ANN) is put forward.The time lag of the first three wave heads and their polarity are selected as the characteristic of ANN to establish fault diagnosis model by using the nonlinear fitting ability of neural network to train and test samples.Make the fault information into the ANN model to get the initial result.According to the intial result and the polarity , time lag of the wave heads,identify the second traveling wave head and obtained the accurate fault distance.Matlab/Simulink simulation results show that the presented method is efficient in fault location and the accuracy is high.