基于信号分析技术和人工智能算法的电力线路故障定位研究

针对基于行波分析的故障定位方法存在的部署成本高，且在串补电路中精度不足的问题，提出一种基于信号处理技术和人工智能算法相结合的低成本故障定位方法。使用双曲S变换对故障电流进行时频转换以提取故障特征，使用能量谱分析技术对故障特征进行降维处理，并将所得到的故障特征输入反向传递人工神经网络（BP-ANN）模型，实现对电力线路故障距离的识别。仿真实验表明，在不同故障类型、不同过渡电阻的条件下，该方法均能够实现准确的故障定位。

Research on power line fault location based on signal analysis technology and artificial intelligence algorithm

Aiming at the problems of high deployment cost and insufficient accuracy in series compensation circuit of fault location method based on traveling wave analysis,a low-cost fault location method based on the combination of signal processing technology and artificial intelligence algorithm was proposed.The hyperbolic S transform was used to convert the fault current into time frequency to extract fault features,the energy spectrum analysis technology was used to reduce the dimension of fault features,and the obtained fault features were input into the back propagation artificial neural network (BP ANN) model to identify the fault distance of power lines.Simulation results showed that this method could achieve accurate fault location under the conditions of different fault types and different transition resistances.