A Fault Diagnosis Method for Flight Control Systems Combining Pose-Invariant Features and a Semi-Supervised RDC-GAN Model

ZHANG Jingsen; HOU Biao; LI Zhijie; BI Wenping; WU Zitong

doi:10.11999/JEIT250964

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2026 >

ZHANG Jingsen, HOU Biao, LI Zhijie, BI Wenping, WU Zitong. A Fault Diagnosis Method for Flight Control Systems Combining Pose-Invariant Features and a Semi-Supervised RDC-GAN Model[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250964

Citation:

ZHANG Jingsen, HOU Biao, LI Zhijie, BI Wenping, WU Zitong. A Fault Diagnosis Method for Flight Control Systems Combining Pose-Invariant Features and a Semi-Supervised RDC-GAN Model[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250964

Citation:

ZHANG Jingsen, HOU Biao, LI Zhijie, BI Wenping, WU Zitong. A Fault Diagnosis Method for Flight Control Systems Combining Pose-Invariant Features and a Semi-Supervised RDC-GAN Model[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT250964

PDF( 8312 KB)

A Fault Diagnosis Method for Flight Control Systems Combining Pose-Invariant Features and a Semi-Supervised RDC-GAN Model

doi: 10.11999/JEIT250964 cstr: 32379.14.JEIT250964

ZHANG Jingsen^{1, 2},
HOU Biao^{1, 2
,
,},
LI Zhijie³,
BI Wenping³,
WU Zitong^{1, 2}

1.
School of Artificial Intelligence, Xidian University, Xi’an 710071, China
2.
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xi’an 710071, China
3.
China Rongtong Artificial Intelligence Research Centre, Beijing 100020, China

Funds: The National Natural Science Foundation of China(62171347, 62101405, 62501450), China Postdoctoral Science Foundation (2024M762544)

Received Date: 2025-09-23
Accepted Date: 2025-12-12
Rev Recd Date: 2025-12-08

Available Online: 2025-12-18

Abstract

Abstract

Objective In recent years, China has actively promoted the development of the low-altitude economy, leading to the increasingly widespread application of drones across multiple industries. As highly complex aerial systems, Unmanned Aerial Vehicles (UAVs) are susceptible to various failures during operation. The flight control system, which serves as the core of UAV flight operations, may develop faults that are less evident than physical damage to components such as motors or propellers. However, such faults can directly cause flight instability or complete loss of control. Fault diagnosis of UAV flight control systems faces two major challenges. First, as an emerging aerial platform, UAVs have far fewer effectively accumulated training samples than traditional diagnostic targets such as bearings, resulting in data scarcity. Second, owing to strong maneuverability, UAVs exhibit substantial variations in data distribution under different flight attitudes, which limits the diagnostic accuracy of most existing models under rapidly changing operating conditions. Therefore, the development of an effective fault diagnosis method for UAV flight control systems is of both academic interest and practical engineering value. Methods A fault diagnosis method for flight control systems based on pose-invariant features and a semi-supervised Reloaded Dense Generative Adversarial Classification Network (RDC-GAN) is proposed. The overall framework is illustrated in Fig. 1. Flight logs collected from the UAV are used as raw diagnostic data. After data cleaning, a differential flatness-based data selection method is applied to separate the flight data into pose-dependent data and pose-independent data. For pose-dependent data, Empirical Mode Decomposition-Squeeze Excitation Network (EMD-SENet) is adopted to extract pose-invariant features, as shown in Fig. 3. An adaptive feature fusion module is then used to perform weighted fusion of pose-independent data, pose-invariant features, and pose-dependent data, as illustrated in Fig. 4. The fused features are subsequently input into a semi-supervised RDC-GAN diagnostic model, whose architecture is presented in Fig. 4. Model training is conducted in two stages. In the first stage, unsupervised training is performed to initialize the network parameters using a large set of unlabeled samples. In the second stage, supervised training is carried out with a small number of labeled samples, enabling accurate fault diagnosis under limited labeling conditions. Results and Discussions The proposed method is first validated on the publicly available RflyMad dataset, which contains magnetometer fault, accelerometer fault, gyroscope fault, Global Navigation Satellite System (GNSS) fault, and no-fault data under five flight attitude modes. Fig. 5 and Fig. 6 illustrate the pose-invariant features extracted by EMD-SENet and the synthetic samples generated by the RDC-GAN generator, respectively. Diagnostic performance is evaluated using Overall Accuracy (OA), Average Accuracy (AA), and the Kappa coefficient, in addition to class-wise accuracy for each fault category. The results on the RflyMad dataset are summarized in Table 3. The proposed method achieves 95.71% OA, 95.32% AA, and a Kappa coefficient of 95.41%, exceeding the second-best comparative method by 2.17%, 2.42%, and 2.40%, respectively. For real-flight experiments, a fault injection approach based on a redundant positioning system is designed. A motion capture system and an Ultra-WideBand (UWB) four-base-station positioning system are employed to ensure experimental reliability and operational safety. The experimental setup is shown in Fig. 12. Online real-flight diagnostic results are presented in Fig. 13, with an OA of 92.78%. Fault diagnosis time is reported in Table 5, and false alarm statistics are provided in Table 6. Conclusions A fault diagnosis method for flight control systems that integrates pose-invariant features with a semi-supervised RDC-GAN model is presented to address data scarcity and flight attitude-induced distribution variation in UAV diagnostics. Differential flatness-based data selection is used to distinguish pose-dependent data from pose-independent data, and pose-invariant features are extracted using EMD-SENet. An adaptive feature fusion strategy is applied to balance heterogeneous features, and phased semi-supervised training of the RDC-GAN model enables high diagnostic accuracy with a limited number of labeled samples. Experimental validation on the RflyMad dataset and real UAV flight scenarios confirms the effectiveness of the proposed method.
- Unmanned Aerial Vehicle (UAV),
- Fault diagnosis,
- Flight control system,
- Pose-invariant feature,
- Generative Adversarial Network (GAN)

FullText(HTML)

References(20)

References

[1]	SINGH P K and SHARMA A. An intelligent WSN-UAV-based IoT framework for precision agriculture application[J]. Computers and Electrical Engineering, 2022, 100: 107912. doi: 10.1016/j.compeleceng.2022.107912.
[2]	林清, 王英勋, 蔡志浩, 等. 国外几型无人机事故统计及分析[C]. 2014(第五届)中国无人机大会论文集, 北京, 2014: 798–805. LIN Qing, WANG Yingxun, CAI Zhihao, et al. Several types of foreign UAV accident statistics and analysis[C]. 2014 (5^th) China UAV Conference, Beijing, China, 2014: 798–805.
[3]	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. doi: 10.3778/j.issn.1002-8331.2305-0137. AN Xue, LI Shaobo, ZHANG Yizong, et al. Review of fault diagnosis techniques for UAV flight control systems[J]. Computer Engineering and Applications, 2023, 59(24): 1–15. doi: 10.3778/j.issn.1002-8331.2305-0137.
[4]	熊鹏伟, 李志农, 刘晨宇, 等. 基于自适应边际损失的小样本故障诊断方法[J]. 兵器装备工程学报, 2024, 45(9): 253–260. doi: 10.11809/bqzbgcxb2024.09.032. XIONG Pengwei, LI Zhinong, LIU Chenyu, et al. Fault diagnosis method for small sample based on adaptive margin loss[J]. Journal of Ordnance Equipment Engineering, 2024, 45(9): 253–260. doi: 10.11809/bqzbgcxb2024.09.032.
[5]	刘金富, 黄頔, 王文林. 无人机故障诊断研究进展[J]. 控制工程, 2022, 29(3): 428–434. doi: 10.14107/j.cnki.kzgc.20210260. LIU Jinfu, HUANG Di, and WANG Wenlin. Research progress of unmanned aerial vehicle fault diagnosis[J]. Control Engineering of China, 2022, 29(3): 428–434. doi: 10.14107/j.cnki.kzgc.20210260.
[6]	AVRAM R, ZHANG Xiaodong, and MUSE J. Quadrotor accelerometer and gyroscope sensor fault diagnosis using nonlinear adaptive estimation methods[J]. International Journal of Prognostics and Health Management, 2016, 7(1): 2328–2338. doi: 10.36001/ijphm.2016.v7i1.2328.
[7]	LI Yang, LIU Zhenbao, JIA Zhen, et al. Fault diagnosis strategy for flight control rudder circuit based on SHAP interpretable analysis optimization transformer with attention mechanism[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 3534214. doi: 10.1109/TIM.2024.3470041.
[8]	SONG Xiaofei, ZHENG Zewei, GUAN Zhiyuan, et al. Deep learning fault diagnosis in flight control system of carrier-based aircraft[C]. 2022 IEEE 17th International Conference on Control & Automation, Naples, Italy, 2022: 492–497. doi: 10.1109/ICCA54724.2022.9831899.
[9]	MELLINGER D and KUMAR V. Minimum snap trajectory generation and control for quadrotors[C]. 2011 IEEE International Conference on Robotics and Automation. Shanghai, China, 2011: 2520–2525. doi: 10.1109/ICRA.2011.5980409.
[10]	KIM D, HEO B, and HAN D. DenseNets reloaded: Paradigm shift beyond ResNets and ViTs[C]. 18th European Conference on Computer Vision. Milan, Italy, 2024: 395–415. doi: 10.1007/978-3-031-72646-0_23.
[11]	LE Xiangli, JIN Bo, CUI Gen, et al. RflyMAD: A dataset for multicopter fault detection and health assessment[J]. The International Journal of Robotics Research, 2025, 44(7): 1081–1092. doi: 10.1177/02783649241305153.
[12]	沈延安, 杨克泉, 陈强. 基于PSO优化小波神经网络的无人机动力系统故障诊断模型[J]. 兵器装备工程学报, 2024, 45(4): 168–175. doi: 10.11809/bqzbgcxb2024.04.021. SHEN Yanan, YANG Kequan, and CHEN Qiang. UAV power based on PSO optimized wavelet neural network system fault diagnosis model[J]. Journal of Ordnance Equipment Engineering, 2024, 45(4): 168–175. doi: 10.11809/bqzbgcxb2024.04.021.
[13]	孙菱, 张振宇, 郭健, 等. 基于RF-LSTM模型的无人机执行器故障诊断算法[J]. 南京理工大学学报, 2024, 48(5): 661–668. doi: 10.14177/j.cnki.32-1397n.2024.48.05.014. SUN Ling, ZHANG Zhenyu, GUO Jian, et al. Fault diagnosis algorithm for UAV actuator based on RF-LSTM model[J]. Journal of Nanjing University of Science and Technology, 2024, 48(5): 661–668. doi: 10.14177/j.cnki.32-1397n.2024.48.05.014.
[14]	XIONG Pengwei, LI Zhinong, LI Yunlong, et al. Fault diagnosis of UAV based on adaptive Siamese network with limited data[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 3531711. doi: 10.1109/TIM.2023.3301898.
[15]	LI Yang, JIA Zhen, LIU Zhenbao, et al. Interpretable intelligent fault diagnosis strategy for fixed-wing UAV elevator fault diagnosis based on improved cross entropy loss[J]. Measurement Science and Technology, 2024, 35(7): 076110. doi: 10.1088/1361-6501/ad3666.
[16]	LUO Qinyuan, CHEN Jinglong, ZI Yangyang, et al. A synchronization-induced cross-modal contrastive learning strategy for fault diagnosis of electromechanical systems under semi-supervised learning with current signal[J]. Expert Systems with Applications, 2024, 249: 123801. doi: 10.1016/j.eswa.2024.123801.
[17]	CHEN Xin, CHEN Zaigang, GUO Liang, et al. Pseudo-label assisted semi-supervised adversarial enhancement learning for fault diagnosis of gearbox degradation with limited data[J]. Mechanical Systems and Signal Processing, 2025, 224: 112108. doi: 10.1016/j.ymssp.2024.112108.
[18]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. The 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 770–778. doi: 10.1109/CVPR.2016.90.
[19]	HUANG Gao, LIU Zhuang, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]. The 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 2261–2269. doi: 10.1109/CVPR.2017.243.
[20]	LIU Zhuang, MAO Hanzi, WU Chaoyuan, et al. A ConvNet for the 2020s[C]. The 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans, USA, 2022: 11966–11976. doi: 10.1109/CVPR52688.2022.01167.