A novel federated deep learning framework for diagnosis of partial discharge in gas-insulated switchgear

Abstract

In recent years, many different deep learning methods have been developed to ensure the safe and stable operation of gas-insulated switchgear (GIS). However, the use of these methods to achieve excellent results depends on obtaining as much training data as possible, which is difficult to accomplish because of conflicts of interest among different clients and privacy concerns. To address this issue, this paper proposes a novel federated deep learning (FDL) for the diagnosis of partial discharge (PD) in GIS. A federated learning (FL) based on an improved federated averaging algorithm is proposed, which allows different clients to collaboratively participate in model training and preserves data privacy. In addition, a novel subtractive attention Siamese network is introduced for feature extraction and classification, which achieves the high-precision classification of unbalanced data. Experimental results showed that the diagnostic accuracy of the proposed FDL reached 95.61%, which was significantly higher than that achieved by other methods. The proposed FDL can also achieve excellent performance in the case of unbalanced samples and small samples. As a distributed learning, FL does not require clients to share data, and clients can collaboratively develop an effective global diagnostic model, which provides a novel solution for GIS PD diagnosis.