Fault diagnosis method for four-quadrant pulse rectifiers based on convolutional neural network and Gramian angular difference field
To fully exert the advantages of the convolutional neural network(CNN)in image recognition and classification,a fault diagnosis method for four-quadrant pulse rectifiers based on CNN and Gramian angular difference field(GADF)is proposed.GADF is utilized to transform the one-dimensional time series of rectifier current into a two-dimensional feature map,preserving the temporal dependency of the data and identifying the temporal correlations of the signal over different time intervals.The CNN then extracts and classifies the features of open circuit faults in the rectifier from the generated feature maps.This method is compared with other common fault diagnosis methods.Simulation analysis results indicate that this proposed method achieves higher diagnostic accuracy compared to other fault diagnosis methods.
万方数据
维普
