Noise-aware dynamic graph recalibration for interpretable aero-engine anomaly detection

Early detection of anomalies in aero-engine is critical to flight safety. In practical operational environments, however, dynamic noise interference distorts the topological structure of sensor networks, undermining the reliability of feature propagation in graph neural networks. Existing models lack dynamic graph optimization capabilities under noisy conditions and offer limited interpretability, as they fail to explicitly model the relationship between noise intensity and graph structural evolution. To overcome these limitations, this paper introduces a noise-guided framework for dynamic graph threshold recalibration. Specifically, the framework incorporates a noise-aware graph recalibrator that statistically infers noise levels from feature dispersion to dynamically adjust connection thresholds, and a feature fidelity convolutional layer that gates neighborhood aggregation to prevent noise accumulation and mitigate feature degradation. Experiments on public datasets and real aero-engine operational data demonstrate that the proposed framework significantly outperforms state-of-the-art methods in detection accuracy and noise resilience. Quantitative and visualization analyses confirm its noise-aware characteristics, yielding interpretable edge selection and establishing a rigorous causal link between internal dynamic thresholds and external physical interference. Validation on real-world data further substantiates the framework's potential for practical engineering applications in early anomaly detection.