CLGNN: UAV Fault Diagnosis via Causal Learning and Graph Neural Network

To build an efficient unmanned aerial vehicle (UAV) fault diagnosis system, accurately modeling the relationship between sensor signals is a challenge. A common thought is to use a graph structure for modeling (Graph Neural Network), i.e., sensors as nodes and relationships between sensors are represented by edges. However, the Graph Neural Network (GNN) models, following the "Learning to Attend" principle, aim to maximize the mutual information between features and labels while minimizing training loss, without distinguishing the causal relationships between features and labels. The model's lack of causal inference capability can lead to instability in model predictions, which ultimately shows up as a degradation in the model's generalization performance on the test dataset. To address these issues, this paper proposes a GNN with causal learning to implement efficient UAV fault diagnosis, the model is called CLGNN. Specifically, the model first utilizes a GNN to model the sensor signals represented by the graph structure. Then, by intervening at the level of feature extraction, the non-causal components in the features are weakened to improve the model's generalization performance in fault diagnosis. Extensive experimental results demonstrate that our method can robustly and accurately capture the anomalous signals of UAVs. In addition, we conduct a detailed analysis of the learned graphical representation of the sensor signals, exploring the decision-making basis of the model, which helps to boost the interpretability and reliability of the model.