Short Circuit Fault Type Identification of Low Voltage AC System Based on Black Hole Particle Swarm and Multi-level SVM

The fast and accurate identification of the type of short circuit fault in low voltage AC system is helpful for post fault analysis and treatment research, and is of great significance for fast restoration of power supply. A method of short circuit fault type identification for low voltage AC system based on black hole particle swarm optimization (BHPSO) and Multi-level SVM is proposed. Wavelet transform is used to decompose the three-phase current and zero sequence voltage from 1ms pre-fault to 1ms post-fault, fault feature vector is constructed based on mathematical statistics method; black hole particle swarm algorithm is used to optimize the parameters of multi-level SVM classifier to improve the accuracy of fault type identification. The fault simulation experiment data of typical low voltage AC system are used to test. The results show that the proposed method not only has a high accuracy of short circuit fault type identification, but also has good adaptability in the case of noise interference, asynchronous sampling, load current change and so on.