基于小波变换与BP神经网络相结合的配电网单相接地故障定位方法

提出一种基于小波变换与BP神经网络相结合的方法来实现小电流接地系统单相接地故障定位。由于利用暂态故障电流和暂态母线电压的模极大值的实部和虚部作为BP神经网络的输入,提高了识别故障能力和可靠性,通过对BP神经网络的特别处理,大大地减小过渡电阻对故障定位的影响。仿真结果表明,该故障定位方法准确可靠。

Fault location for single-phase-to-earth fault using the combination of wavelet transform and BP neural network

In this paper, the method based on the combination of wavelet transform and BP neural network is presented to realize fault location for the single-phase-to-earth fault in non-direct-ground systems. Because of taking the moudal maxima of real and imaginary part of the transient fault current and transient bus voltage as the input of BP neural network, the ability of the fault detection and the reliability are enhanced. The effect of transient resistance on fault location is reduced greatly through special processing of BP neural network. Simulation results show that the proposed method is of precision and reliability.