基于RBF神经网络的中压配电网接地故障特性研究

Research on Grounding Fault Characteristics of Medium Voltage Distribution Network Based on RBF Neural Network

接地故障是中压配电网中常见故障之一,快速定位故障对于提高供电经济型、安全性、可靠性具有重要意义。提出了一种结合行波法与RBF神经网络的故障定位方法,首先通过行波法确定故障点与电源出口间的距离,其次利用RBF神经网络对故障点所在线路支路进行精确定位,最后以实际电网作为算例进行仿真模拟,验证了所提方法的合理性和有效性。

Grounding fault is one of the common faults in 10 kV distribution lines. Fast fault location is of great significance to improve the economy, safety and reliability of power supply. A fault location method combining traveling wave method with RBF neural network is proposed in this paper. Firstly, the distance between fault point and power outlet is determined by traveling wave method. Secondly, the line branch where the fault point is located is accurately positioned by RBF neural network. Finally, Chongming power grid is taken as an example to simulate, and the rationality and effectiveness of the proposed method are verified.