Research on Fault Detection Method of Converters
The influence of converter faults to the system is introduced and the fault detection method based on wavelet transform and neural network is proposed in this paper. The fault information can be decomposed by wavelet transform, then the fault eigenvectors can be extracted and put into neural network for training and testing. Finally the neural network outputs specific codes, and thus the fault location and fault components of converters are confirmed, which lays the foundation for the fault-tolerant operation control of converters. Simulation and experimental results show the correctness and effectiveness of the method.
W. Z. Ma et al., "Research on Fault Detection Method of Converters", Applied Mechanics and Materials, Vols. 229-231, pp. 1150-1153, 2012