Fault diagnosis of VSC-HVDC transmission system based on PCA and LS-SVM

In this paper, an effective method for fault diagnosis of voltage source converter based high voltage direct current transmission system (VSC-HVDC) is proposed. Considering the influence of random noise on the measured results, Firstly, The wavelet threshold denoising method is used to filter the fault signal of VSC-HVDC system. And then the principal component analysis (PCA) method is used to construct a fault detection model, detecting the fault in real time. In addition, a fault classification model based on least square support vector machine (LS-SVM) is established to effectively identify and classify the VSC-HVDC system fault, so as to achieve the purpose of fault diagnosis. Finally, the system simulation model based on the electromagnetic transient simulation software PSCAD/EMTDC is established to simulate the common faults. The simulation results show that the fault detection is effective, and the different fault can be correctly classified and identified.