Abstract: The occurrence of faults will greatly affect the safety of the shipboard zonal distribution power system.In order to ensure the safe operation of ships,10 types of short-circuit faults in the shipboard zonal distribution power system are focused in this paper.MATLAB/Simulink is used to establish the power system simulation model of the shipboard zonal distribution power system,SMOTE oversampling is adopted to preprocess the fault data.Taking the feature vector extracted by principal component analysis(PCA) in fault data as input of multi-class support vector machine(MSVM) for fault diagnosis.In order to optimize the diagnosis results,a firework particle swarm optimization algorithm is presented to optimize the penalty factor C and the kernel function parameter γ of MSVM,which is compared with the results of MSVM fault classification optimized only by the particle swarm optimization algorithm.Simulation results show that the proposed algorithm has higher fault classification accuracy and precision.

Key words: Shipboard zonal distribution power system, Principal component analysis, Firework algorithm, Particle swarm optimization algorithm, Multi-class support vector machine, Fault diagnosis