S-Transform-Based Classification of Converter Faults in HVDC System by Support Vector Machines
Based on Support Vector Machines (SVM) and S-transform, a novel approach to detect and classify various types of high voltage direct current (HVDC) converter faults is presented. An electro-magnetic transient state simulation software PSCAD/EMTDC was used to set up a simulation model of HVDC system to investigate the typical converter faults. For the good time-frequency characteristic of S-transform, S-transform is applied to obtain useful features of the non-stationary fault signals. Then fault types are identified through the pattern recognition classifier based on SVM classification tree. Numerical results show that the proposed classification method is an effective technique for building up a pattern recognition system for converter fault signals.