Fusion reasoning algorithm for airborne correlated fault diagnosis based on meta-model
Source abstract
Abstract
Fault diagnosis is a critical component of the maintenance and support system for complex airborne systems. Traditional diagnostic methods relying on fault transmission relationships have limitations such as monitoring blind spots and insufficient reasoning for cross-linking faults. This paper proposes a meta-model-based fusion reasoning algorithm for airborne correlated fault diagnosis, which captures system topological features via graph convolutional neural network,depictsthe fault evolution mechanisms through the meta-model, and and integrates structure features-explicit diagnostic rules-neural network reasoning by embedding association rules. Comparative tests on a typical airborne communication system show that the framework significantly improves fault isolation accuracy with strong adaptability. The research provides a new technical approach for airborne complex system fault diagnosis and supports the development of operation and maintenance technologies for similar equipment.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Engineering and Test Systems · AI-based Problem Solving and Planning · Rough Sets and Fuzzy Logic
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Northwestern Polytechnical University
References (32)
Show source-provided references
1. 10.1007/s42417-025-02122-y10.1007/s42417-025-02122-y ↗
2. 10.1109/TIE.2016.258272910.1109/TIE.2016.2582729 ↗
3. Zhao H, Yang J. A novel health status assessment method for rolling bearings based on multi-band anomaly detection. Measurement. 2025;256:118427.10.1016/j.measurement.2025.118427 ↗
4. 10.1016/j.neucom.2018.05.02410.1016/j.neucom.2018.05.024 ↗
5. Xu D, Shang J, Miao J, et al. An adaptive spatiotemporal graph convolutional network for aero-engine remaining useful life prediction. Comput Integr Manuf Syst. 2025;6:2165–2177.
6. Ding SS, Chen RW, Liu F. Rolling bearing fault diagnosis algorithm based on convolutional graph neural network. Appl Single-Chip Microcomput Embedded Syst. 2022;4:22–27.
7. 10.1109/TNN.2008.200560510.1109/TNN.2008.2005605 ↗
8. Liao W, Yang D, Wang Y. Fault diagnosis of power transformers using graph convolutional network. CSEE J Power Energy Syst. 2021;7(2):123–130.
9. Liu M. Comprehensive processing and performance evaluation of large passenger aircraft navigation information based on RNP requirements [master’s thesis]. Nanjing China: Nanjing University of Aeronautics and Astronautics; 2020.
10. Kang WW. Research and implementation of rocket fault diagnosis technology based on directed graph and fuzzy set [master’s thesis]. Lanzhou China: Lanzhou University; 2020.
11. Zhang XN, Guo QL, Liu SY. Analysis and prospect of deep learning technology and its application in fault diagnosis. J Xi’an Jiaotong Univ. 2020;54:7–19.
12. 10.1016/j.measurement.2025.11941910.1016/j.measurement.2025.119419 ↗
13. 10.1051/jnwpu/2020386121010.1051/jnwpu/20203861210 ↗
14. Ying Rex, He Ruining, Chen Kaifeng. Graph convolutional neural networks for web-scale recommender systems. In: Proceedings of the 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining London, United Kingdom. Association for Computing Machinery; 2018. p. 974–983.
15. 10.13675/j.cnki.tjjs.240103610.13675/j.cnki.tjjs.2401036 ↗
16. 10.1109/TII.2024.348456910.1109/TII.2024.3484569 ↗
17. 10.3390/s2401027210.3390/s24010272 ↗
18. Smith J, Johnson L, Williams K. Comparing gcn, graphsage, and gat for industrial fault diagnosis. J Mach Learn Eng. 2024;5(2):145–162.
19. Wang Y, Li Z, Zhang J. Revisiting, benchmarking, and refining heterogeneous graph neural networks. IEEE Trans Knowl Data Eng. 2023;35(12):11890–11902.
20. Chen Rong, Jiang Yao, Wang Xuan, et al. Multi-expert collaboration based information graph learning for anomaly diagnosis in smart grids. Computers, Materials & Continua. 2025;75(3):4567–4589.
21. Zhang L, Wang H, Chen S. Graph convolutional neural network-based modeling of ultra-scale MIMO channels in 6G networks. Appl Math Nonlinear Sci. 2025;10(1):123–145.
22. 10.1016/j.measurement.2019.10722710.1016/j.measurement.2019.107227 ↗
23. Tan XY, Pei SW. Research on heterogeneous graph neural network based on higher-order neighbors. J Chin Comput Syst. 2023;44:1954–1960.
24. Liu J, Zhao F, Smith AL. SuperGLUE facilitates an explainable training framework for multi-modal data analysis. Cell Rep Methods. 2025;5(3):100045.
25. 10.1007/s10845-021-01884-y10.1007/s10845-021-01884-y ↗
26. 10.1109/TPAMI.2025.357361510.1109/TPAMI.2025.3573615 ↗
27. Velickovic Petar, Cucurull Guillem, Casanova Arantxa, et al. Graph attention networks. In: International Conference on Learning Representations (ICLR) 2018 Canada; 2018 Yoshua Bengio Yann LeCun (OpenReview.net). https://openreview.net/forum?id=rJXMpikCZ.
28. Chen L, Wang Z, Li X. Aligning local features from multi-view data via contextual distillation and global representation learning. Knowl-Based Syst. 2025;295:114671.
29. 10.1109/TCYB.2021.305900210.1109/TCYB.2021.3059002 ↗
30. Li T, Zhao Z, Sun C. Multi-receptive field graph convolutional networks for machine fault diagnosis. IEEE Trans Ind Electron. 2020;67(7):5993–6002.
31. 10.1016/j.eswa.2025.12902310.1016/j.eswa.2025.129023 ↗
32. 10.1016/j.ress.2025.11097810.1016/j.ress.2025.110978 ↗