A novel semi-supervised method for classification of power quality disturbance using generative adversarial network

Abstract

The existing methods for classification of power quality disturbance signals (PQDs) have the problems that the process of signal feature selection is tedious and imprecise, the accuracy of classification has no guiding significance for feature extraction, and lack of adequate labelled training data. To solve these problems, this paper proposes a new semi-supervised method for classification of PQDs based on generative adversarial network (GAN). Firstly, a GAN model is designed which we call it PQDGAN. After the unsupervised pre-training with unlabeled training data, the trained discriminator is extracted alone and conduct supervised training with a small amount of labelled training data. Finally, the discriminator became a classifier with high accuracy. This model can achieve the step of feature extraction and selection efficiently. In addition, only a small amount of labelled training data is used, which greatly reduces the dependence of classification model on labelled data. Experiments show that this method has high classification accuracy, less computations and strong robustness. It is a new semi-supervised method for classification of PQDs.