基于PSO-SVM的小电流接地故障选线方法

Fault line selection in small current grounding power system based on PSO-SVM

针对小电流接地系统,现有故障选线方法的精度不高,为此提出基于粒子群优化向量机(PSO-SVM)的选线方案。在搭建小电流接地系统仿真模型的基础上,采用Matlab进行PSO优化算法仿真实验,根据不同的接地情况获得故障时各线路零序电流,利用小波包变换(WPT)与傅里叶变换(FFT)从零序电流中提取暂态分量、谐波分量、五次谐波分量作为PSO-SVM输入特征进行训练,用训练好的SVM对测试样本行检测,得到选线结果。仿真结果表明,该方法使学习训练速度加快、自适应能力增强、选线精度提高进,且其不受接地电阻、故障距离等因素影响。

In the small current grounding system,for the problem that using the existing fault line selection method can not obtain high accuracy,a solution of fault line selection based on PSO-SVM（support vector machine optimized by particle swarm optimization）was proposed.The software of Matlab was used to conduct a PSO（particle swarm optimization）algorithm simulation based on the simulation model of the small current grounding system.According to different ground conditions,each line zero sequence current was obtained,and then the methods of WPT（wavelet packet transform）and FFT（Fourier transform）were used to extract the steady-state fundamental component,steady-state fifth harmonic component,and transient energy component from the zero sequence currents,these features were taken as PSO-SVM input features for training,the SVM（support vector machine）were trained on the test samples to get selected line results.The simulation results show that the information fusion for fault line selection is reliable,effective and accurate,and it is not affected by factors such as grounding resistance and fault distance.