基于SVM的超高压直流输电系统故障诊断模型研究

针对非线性、高度可控的超高压直流输电（HVDC）系统,提出将支持向量机（SVM）用于系统的故障诊断研究中。首先利用电磁暂态仿真软件EMTDC/PSCAD建立系统模型,对常见故障进行仿真研究。为有效提取故障特征,对直流电压波形进行S变换。变换后的特征量作为SVM的输入,建立系统故障诊断模型,并比较了不同参数下的SVM模型性能。仿真结果表明SVM用于HVDC系统故障诊断是合理、有效的。

Research on SVM-Based Fault Diagnosis Models of HVDC System

Aiming at a nonlinear and high-controllable High Voltage Direct Current(HVDC)system,a new fault diagnosis approach based on Support Vector Machine(SVM)was proposed.An electro-magnetic transient state simulation software named EMTDC/PSCAD was used to set up a simulation model of HVDC system to investigate the typical power system faults.DC voltage signals which could reflect fault features were selected to be S transformed and fault samples composed of effective features were extracted.On this basis,SVM fault diagnosis models were established,and the performance of different models was compared.Simulation results show that SVM using in HVDC fault diagnosis is valid and effective.