A Sequence-to-Sequence Deep Learning Architecture Based on Bidirectional GRU for Type Recognition and Time Location of Combined Power Quality Disturbance

Abstract

In this paper, a sequence-to-sequence deep learning architecture based on the bidirectional gated recurrent unit (Bi-GRU) for type recognition and time location of combined power quality disturbance is proposed. Especially, the proposed methodology can determine the type of each element in input sequence, which is different from existing sequence-to-sequence model employing encoder–decoder network. First, the input sequence is normalized and batched. Second, deep features are extracted from input sequence by constructing Bi-GRU recurrent neural network, where multiple Bi-GRU layers are stacked together in both forward direction and backward direction. Third, according to aforementioned extracted features, fully connected layer and Softmax are employed to calculate the corresponding probability indicating the category that each element in input sequence is classified to. Fourth, Argmax or Top_K operation is further integrated to determine the type of each element in input sequence by selecting the maximal probability. Finally, the type is recognized, and meanwhile, starting–ending times of disturbances are also located just at the moment when the type is changed. The proposed model is further validated and tested by synthetic signals and practical field signals, respectively. Experimental results demonstrate that the accuracy of type recognition is over 98% for 96 kinds of disturbances including single and combined disturbances with signal-to-noise ration being 20 dB. Besides, the starting–ending times are also located with the absolute error less than six sampling points when sampling frequency is 256 points per cycle with noisy environment.