Dual-Channel Graph Ranking Contrastive Learning for Dissolved Gas Analysis

Dissolved Gas Analysis (DGA) is a widely used diagnostic technique specifically designed to identify potential defects or irregularities in power transformers. Despite recent advancements, the fine-grained correlation modeling between samples is still insufficient. This limitation results in less contextualized feature representations, ultimately impacting the accuracy of diagnosis. To this end, we propose an effective graph deep learning model called DGRCL (Dual-channel Graph Ranking Contrastive Learning) for DGA. In our model, we construct two types of graphs: similar $K$-Nearest Neighbors (KNN) ($G_{S}$) and dissimilar KNN ($G_{\text{DS}}$), where nodes represent individual records of dissolved gases and the edges, namely similar-homophilic and dissimilar-heterophilic, capture the relationships between nodes. To better generate node representations, we design a dual-channel graph encoding component, with each channel playing a crucial role in capturing the corresponding edge type view. Furthermore, in order to better distinguish the feature differences among various fault categories, we employ ranking contrastive loss to refine the node representations. Experimental results demonstrate that our model achieves high accuracy and robustness in predicting fault types.