Fault Diagnosis Strategy of Four-Switch Buck-Boost Converter Based on BP Neural Network Optimized by Particle Swarm Optimization

The four-switch Buck-Boost converter (FSBB) is widely used in the field of new energy power generation and electric vehicles, and the complexity of its operation mode brings difficulties to fault diagnosis. This paper designs a diagnostic framework that integrates the back propagation (BP) neural network and the particle swarm optimization algorithm (PSO), and realizes the diagnosis of the switches in different modes of the FSBB converter. Effective diagnosis of single-switch open circuit faults and double-switch open circuit faults. Simulation results show that the method has high diagnostic accuracy.