Fault Diagnosis of Modular Multilevel Converter with FA-SVM Algorithm

Aiming at the open failure of sub-module(SM) for modular multilevel converter (MMC), this paper proposes a fault diagnosis method with firefly algorithm optimized support vector machine (FA-SVM). Without changing the topology of MMC circuit, the fault signal is preprocessed by employing Fast Fourier transform. Furthermore, principal component analysis is used to extract the fault characteristics and reduce the dimension. Especially, FA-SVM is adopted to classify and identify the fault with high efficiency and accuracy. By building a 31-level MMC platform based on MATLAB/Simulink, the simulation results show that the proposed method can not only effectively identify the open fault of the MMC sub-module, but also reduce the diagnosis time greatly.