Transformer Fault Diagnosis Method based on PSO-GMNN Model

Background: Oil-immersed distribution transformer is an important power transmission and distribution equipment in the power system. If it fails, it will cause huge economic losses and safety hazards. It is of great significance to identify and diagnose its faults, find potential faults in time, and restore normal operation. Objective: To detect transformer fault, a transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm (PSO-GMNN) is proposed. Methods: Five common dissolved gases in transformer oil are used to construct a 22-dimensional feature set to be selected, and then the similarity between each feature vector is calculated by using Mahalanobis Distance. The graph structure is constructed with feature vectors as vertices and similarities as edges. Finally, the Particle Swarm Optimization algorithm is used to optimize the initial weights of Graph Markov Neural Networks, and then transformer fault diagnosis is realized. Results: The experiments are performed in the environment of Python 3.7, PyTorch 1.6.0, and the validity of the proposed method is verified by a comparative analysis of the detection accuracy between the proposed method and existing mainstream methods. Conclusion: A transformer fault diagnosis method based on Graph Markov Neural Networks for Particle Swarm Optimization algorithm is proposed to detect transformer fault, and the experimental results demonstrate the effectiveness and advantage of the proposed method.