Fault Diagnosis Strategy of Four-Switch Buck-Boost Converter Based on Support Vector Machines

The four-switch Buck-Boost (FSBB) converter, with advantages such as bidirectional power transmission and low switch stress, has been widely applied in various fields including photovoltaic power generation and energy storage. This paper addresses the problem of the complex working mode of the FSBB converter and the small sample size of fault samples by using the support vector machines (SVM) model for fault diagnosis. By selecting signal acquisition nodes and using Fast Fourier Transform (FFT) to extract fault features, the improved grid search method is used to find the optimal parameters of the SVM model. Finally, the SVM model is used for multi-class recognition to achieve effective diagnosis of single-switch open circuit faults and double-switch open circuit faults of the FSBB converter under different modes. Simulation results show that this method has a high diagnostic accuracy and strong extrapolation ability.