Power Quality Disturbance Signal Classification Based on MTF and AlexNet
Considering the shortcomings of the traditional power quality disturbances(PQDs)classification meth-od,such as low classification accuracy and slow classification speed,in this study,a novel PQDs classification method combining Markov transition field and convolutional neural network AlexNet is proposed.Firstly,the MTF method was used to visualize the feature vectors of 7 single disturbances and 6 composite disturbances.The one-dimensional dis-turbance signal time series was converted into a two-dimensional feature image with temporal correlation.Then,the feature image was used as the input of the AlexNet network for automatic feature extraction.Finally,the classification of different types of PQDs signals was achieved.Experimental results show that the proposed method can accurately classify single and compound PQDs signals,and the effectiveness of the proposed method is verified by comparing dif-ferent classification methods.
Power qualityDisturbance classificationMarkov transition fieldConvolutional neural networkDeep learning