GAN and CNN for imbalanced partial discharge pattern recognition in GIS

The convolutional neural network (CNN) achieves excellent performance in pattern recognition owing to its powerful automatic feature extraction capability and outstanding classification performance. However, the actual samples obtained are unbalanced, and accurate diagnoses are difficult for the existing methods. A classification method for partial discharge (PD) pattern recognition in gas-insulated switchgear (GIS) that uses a generative adversarial network (GAN) and CNN on unbalanced samples is proposed. First, a novel Wasserstein dual discriminator GAN is used to generate data to equalise the unbalanced samples. Second, a decomposed hierarchical search space is used to automatically construct an optimal diagnostic CNN. Finally, PD pattern recognition classification in GIS of the unbalanced samples is realised by the GAN and CNN. The experimental results show that the GAN and CNN methods proposed in this study have a pattern recognition accuracy of 99.15% on unbalanced samples, which is significantly higher than that obtained by other methods. Therefore, the method proposed in this study is more suitable for industrial applications.