Support Vector Machine for Classification and its Application to the Small Current Grounding Fault Line Detection in Peterson-Coil-Grounding System

In Peterson-coil-grounding system(PCGS), the electric parameters in grounding fault have different electric characteristics, and the working situation of PCGS can be recognized by electric parameters of system. In this paper, support vector machines for classification(SVMC)are used to recognize the working situation of PCGS and to detect the fault line or bus. Simulation results show that the method is effective, accurate and can effectively improve the accuracy of fault lines, has some practical value.