Aircraft sensors are crucial for ensuring the safe and efficient operation of aircraft. However, these sensors are vulnerable to external factors that can lead to malfunctions, making fault diagnosis essential. Traditional deep learning-based fault diagnosis methods often face challenges, such as limited data representation and insufficient feature extraction. To address these problems, this paper proposes an enhanced GraphSage-based fault diagnosis method that incorporates attention mechanisms. First, signal data representing the coupling characteristics of various sensors are constructed through data stacking. These signals are then transformed into graph data with a specific topology reflecting the overall sensor status of the aircraft using K-nearest neighbor and Radius classification algorithms. This approach helps fully leverage the correlations between data points. Next, node and neighbor information is aggregated through graph sampling and attention-based aggregation methods, strengthening the extraction of fault features. Finally, fault diagnosis is performed using multi-layer aggregation and transformation within fully connected layers. Experiments demonstrate that the proposed method outperforms baseline approaches, achieving better detection performance and faster computational speed. The method has been validated on both simulated and real-flight data.