SVM Theory and Its Application in Fault Diagnosis of HVDC System

Support vector machine (SVM), which based on statistical learning theory, is a universal machine learning method. The fault diagnosis of nonlinear and high-controllable high voltage direct current (HVDC) system based on SVM method is proposed, which can take full advantage of effective ability and superiority of SVM in dealing with small samples, and solve many familiar problems in fault diagnosis of HVDC system. A simulation model of HVDC system is set up, and performance of SVM models under different parameters using polynomial kernel function and RBF kernel function respectively are compared. Results show the superiority of SVM method, also the validity and feasibility of the proposed method.