基于神经网络的配电线路综合故障定位方法

Composite Fault Location Method Based on PNN for Distribution Lines

针对配电网分支多、故障点信号弱的特点提出了一种利用C行波法和PNN神经网络的功能互补性来实现对带有分支的配电网故障线路的准确故障定位的方法。首先利用C行波法确定故障点到母线端的距离;由于到母线端同样距离的分支可能不止一个,故利用PNN神经网络的模式识别功能来进一步确定故障分支,从而可以实现精确故障定位。理论分析和仿真结果表明,该方法能够准确地确定带分支配电网单相接地故障位置。

In order to tackle the problems that the distribution network is with a vast number of branches and the signal is usually weak in fault location, an accurate fault location method is proposed for the distribution network with branch, and this method synthesis C-type of traveling wave and PS/N. Initially, this method calculates the fault distance via C-type of traveling wave. Subsequently, due to the fact that there may be more that one branch that would be with the same fault distance, the PNN＇s function of pattern recognition is utilized to determine the fault branch, thereby achieving precise fault location. Both the theoretical analysis and simulation indicate that this composite location method can be utilized to determine the single-phase-to-earth fault location accurately in the distribution network.