Elman-Adaboost集成人工神经网络高压交流输电线路单相接地初始电压行波模量幅值比单端故障测距

Elman-Adaboost Integrated Artificial Neural Network for High Voltage AC Transmission Line Single-phase Grounding Initial Voltage Traveling Wave Modulus Amplitude Ratio of Single-end Fault Location

针对现有单端行波故障测距方法对高阻接地故障不灵敏、反射波波头识别不准等问题,提出了一种Elman-Adaboost集成人工神经网络高压交流输电线路单相接地初始电压行波模量幅值比单端故障测距的方法。首先,基于行波衰减原理,通过推导高压交流输电线路故障距离与线路首端初始暂态电压行波线模分量与零模分量幅值比之间的计算公式,发现两者存在与过渡电阻无关的非线性关系;其次,利用Elman-Adaboost集成人工神经网络拟合初始暂态电压行波线模分量与零模分量小波能量比和故障距离之间的关系,构建集成人工神经网络故障定位模型,通过该模型可直接得到高压交流输电线路故障位置。实验结果表明,方法精度不受过渡电阻影响,测距精度较高。

The existing single-ended traveling wave fault location methods have some problems,such as insensitive grounding fault and inaccurate reflection wave head identification.In this paper,a single-ended fault location method based on Elman-Adaboost integrated artificial neural network for high voltage AC transmission line single-phase grounding initial voltage travelling wave modulus amplitude ratio is proposed.Firstly,based on the principle of traveling wave attenuation,the calculation formula between the fault distance of high voltage alternating current(HVAC)transmission line and the amplitude ratio of the line mode component to the zero mode component of the initial transient voltage at the head end of the line is derived, which shows that there is a nonlinear relationship between the two and the transition resistance. Secondly, the Elman-Adaboost integrated artificial neural network is used to fit the relationship between the wavelet energy ratio and the fault distance of the initial transient voltage traveling wave mode component and the zero-mode component, and the integrated artificial neural network fault location model is constructed, through which the fault location of the high voltage AC transmission line can be directly obtained. The experimental results show that the accuracy of this method is not affected by the transition resistance, and the ranging accuracy is high.