




















This paper has been withdrawn by Yang Hu
No PDF available, click to view other formats
Abstract:BACKGROUND: General aviation fleet expansion demands intelligent health monitoring under computational constraints. Real-world aircraft health diagnosis requires balancing accuracy with computational constraints under extreme class imbalance and environmental uncertainty. Existing end-to-end approaches suffer from the receptive field paradox: global attention introduces excessive operational heterogeneity noise for fine-grained fault classification, while localized constraints sacrifice critical cross-temporal context essential for anomaly detection. METHODS: This paper presents an AI-driven heterogeneous cascading architecture for general aviation health management. The proposed Long-Micro Scale Diagnostician (LMSD) explicitly decouples global anomaly detection (full-sequence attention) from micro-scale fault classification (restricted receptive fields), resolving the receptive field paradox while minimizing training overhead. A knowledge distillation-based interpretability module provides physically traceable explanations for safety-critical validation. RESULTS: Experiments on the public National General Aviation Flight Information Database (NGAFID) dataset (28,935 flights, 36 categories) demonstrate 4--8% improvement in safety-critical metrics (MCWPM) with 4.2 times training acceleration and 46% model compression compared to end-to-end baselines. CONCLUSIONS: The AI-driven heterogeneous architecture offers deployable solutions for aviation equipment health management, with potential for digital twin integration in future work. The proposed framework substantiates deployability in resource-constrained aviation environments while maintaining stringent safety requirements.
| Comments: | Significant methodological flaws have been identified in the experimental validation and metric computation procedures that undermine the reliability of the reported results. A comprehensive revision is underway |
| Subjects: | Machine Learning (cs.LG) |
| ACM classes: | J.2; I.2.6 |
| Cite as: | arXiv:2603.22885 [cs.LG] |
| (or arXiv:2603.22885v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.22885 arXiv-issued DOI via DataCite |
From: Yang Hu [view email]
[v1]
Tue, 24 Mar 2026 07:35:23 UTC (3,548 KB)
[v2]
Thu, 26 Mar 2026 14:53:32 UTC (5,005 KB)
[v3]
Fri, 27 Mar 2026 14:03:50 UTC (5,004 KB)
[v4]
Tue, 21 Apr 2026 14:46:38 UTC (1 KB) (withdrawn)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。