结合注意力机制与元学习的固定翼无人机故障诊断方法

doi:10.3778/j.issn.1002-8331.2409-0051

摘要/Abstract

摘要： 随着无人机在各领域应用的日益广泛，故障诊断成为保障其安全运行的关键。然而，传统基于深度学习的故障诊断方法往往依赖大量标记数据，在样本量较小和复杂飞行环境下易出现泛化性能差、对关键特征的提取不够显著、过拟合等问题。针对这些挑战，提出了一种元学习和有效通道注意力（meta-learning and effective channel attention，MLECA）的故障诊断方法，旨在利用元学习提高固定翼无人机故障诊断的准确性和鲁棒性。对原始传感器数据预处理并构建元任务；为了有效捕捉和突出重要特征，建立卷积神经网络和有效通道注意力（efficient channel attention，ECA）结合的特征编码器；将其作为基模型，通过模型无关的元学习方法训练优化初始化参数来获取先验表征知识，并利用所学知识实现未知环境下固定翼无人机故障诊断。实验结果表明，MLECA整体展现出较好的诊断性能，且拥有更强的泛化能力。

关键词: 固定翼无人机, 故障诊断, 元学习, 注意力机制

Abstract: With the increasing application of UAVs in various fields, fault diagnosis has become crucial for ensuring their safe operation. However, traditional deep learning-based fault diagnosis methods often rely on large amounts of labeled data, leading to issues such as poor generalization performance, insufficient extraction of key features, and overfitting, especially in scenarios with small sample sizes and complex flight environments. To address these challenges, a meta-learning and effective channel attention(MLECA) fault diagnosis method is proposed. This method aims to improve the accuracy and robustness of fault diagnosis through meta-learning. Firstly, the original sensor data are preprocessed, and meta-tasks are constructed. Secondly, to effectively capture and emphasize important features, a feature encoder combining convolutional neural networks and efficient channel attention (ECA) is established. Finally, it is used as the base model, and model-agnostic meta-learning is applied to train and optimize the initialization parameters to acquire prior representational knowledge, which is then used for fixed-wing UAV fault diagnosis in unknown environments. Experimental results demonstrate that the MLECA method exhibits better overall diagnostic performance and stronger generalization capability.

Key words: fixed-wing UAV, fault diagnosis, meta-learning, attention mechanism

董虔利, 张安思, 武杰, 赵凯君. 结合注意力机制与元学习的固定翼无人机故障诊断方法[J]. 计算机工程与应用, 2025, 61(23): 360-367.

DONG Qianli, ZHANG Ansi+, WU Jie, ZHAO Kaijun. Fault Diagnosis Method for Fixed-Wing UAVs Integrating Attention Mechanism and Meta-Learning[J]. Computer Engineering and Applications, 2025, 61(23): 360-367.

参考文献

[1] GUO D F, ZHONG M Y, JI H Q, et al. A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors[J]. Neurocomputing, 2018, 319: 155-163.
[2] ZHU X N. Analysis of military application of UAV swarm technology[C]//Proceedings of the 3rd International Conference on Unmanned Systems. Piscataway: IEEE, 2020: 1200-1204.
[3] XIANG H T, TIAN L. Development of a low-cost agricultural remote sensing system based on an autonomous unmanned aerial vehicle (UAV)[J]. Biosystems Engineering, 2011, 108(2): 174-190.
[4] GUPTA L, JAIN R, VASZKUN G. Survey of important issues in UAV communication networks[J]. IEEE Communications Surveys & Tutorials, 2016, 18(2): 1123-1152.
[5] DENG L, HE Y H, LIU Q Y. Research on application of fire uumanned aerial vehicles in emergency rescue[C]//Proceedings of the 9th International Conference on Fire Science and Fire Protection Engineering. Piscataway: IEEE, 2019: 1-5.
[6] TAN X, ZHANG G. Research on surface defect detection technology of wind turbine blade based on UAV image[J].Instrumentation, 2022(1): 41-48.
[7] DING S X. Model-based fault diagnosis techniques: design schemes, algorithms, and tools[M]. Cham: Springer , 2008.
[8] 安雪, 李少波, 张仪宗, 等. 无人机飞控系统故障诊断技术研究综述[J]. 计算机工程与应用, 2023, 59(24): 1-15.
AN X, LI S B, ZHANG Y Z, et al. Review of fault diagnosis techniques for UAV flight control systems[J]. Computer Engineering and Applications, 2023, 59(24): 1-15.
[9] ZUO L F, YAO L N, KANG Y F. UIO based sensor fault diagnosis and compensation for quadrotor UAV[C]//Proceedings of the Chinese Control and Decision Conference. Piscataway: IEEE, 2020: 4052-4057.
[10] GAO J X, ZHANG Q, CHEN J Y. EKF-based actuator fault detection and diagnosis method for tilt-rotor unmanned aerial vehicles[J]. Mathematical Problems in Engineering, 2020, 2020: 8019017.
[11] SKRIVER M, HELCK J, HASAN A. Adaptive extended Kalman filter for actuator fault diagnosis[C]//Proceedings of the 4th International Conference on System Reliability and Safety. Piscataway: IEEE, 2019: 339-344.
[12] WANG X M, ROY S, FARì S, et al. The problem of reliable design of vector-field path following in the presence of uncertain course dynamics[J]. IFAC-Papers OnLine, 2020, 53(2): 9399-9404.
[13] KLADIS G P, ECONOMOU J T, KNOWLES K, et al. Digraph matrix reliability analysis for fault assessment for a UAV platform application.a fault-tree analysis approach[C]//Proceedings of the IEEE Vehicle Power and Propulsion Conference. Piscataway: IEEE, 2008: 1-6.
[14] XIAO L Z, SUN D X, LIU Y W, et al. A combined method based on expert system and BP neural network for UAV systems fault diagnosis[C]//Proceedings of the International Conference on Artificial Intelligence and Computational Intelligence. Piscataway: IEEE, 2010: 3-6.
[15] BU J, SUN R, BAI H Y, et al. Integrated method for the UAV navigation sensor anomaly detection[J]. IET Radar, Sonar & Navigation, 2017, 11(5): 847-853.
[16] CHEN X M, WU C X, WU Y, et al. Design and analysis for early warning of rotor UAV based on data-driven DBN[J]. Electronics, 2019, 8(11): 1350.
[17] CUI A Y, ZHANG Y, ZHANG P Y, et al. Intelligent health management of fixed-wing UAVs: a deep-learning-based approach[C]//Proceedings of the 16th International Conference on Control, Automation, Robotics and Vision. Piscataway: IEEE, 2020: 1055-1060.
[18] AHMAD M W, AKRAM M U, AHMAD R, et al. Intelligent framework for automated failure prediction, detection, and classification of mission critical autonomous flights[J].ISA Transactions, 2022, 129: 355-371.
[19] CAI G W, LUM K Y, CHEN B M, et al. A brief overview on miniature fixed-wing unmanned aerial vehicles[C]//Proceedings of the IEEE International Conference on Control and Automation?. Piscataway: IEEE, 2010: 285-290.
[20] DUCARD G. Actuator fault detection in UAVs[M].Dordrecht: Springer Netherlands, 2015.
[21] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the International Conference on Machine Learning, 2017: 1126-1135.
[22] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 7132-7141.
[23] WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11531-11539.
[24] BRONZ M, BASKAYA E, DELAHAYE D, et al. Real-time fault detection on small fixed-wing UAVs using machine learning[C]//Proceedings of the AIAA/IEEE 39th Digital Avionics Systems Conference. Piscataway: IEEE, 2020: 1-10.