基于数据驱动的无人机集群故障检测与诊断

李润泽; 姜斌; 余自权; 陆宁云

doi:10.13700/j.bh.1001-5965.2022.0441

基于数据驱动的无人机集群故障检测与诊断

doi: 10.13700/j.bh.1001-5965.2022.0441

南京航空航天大学自动化学院，南京 211100

基金项目: 国家自然科学基金 (62020106003,61663008)；直升机动力学全国重点实验室开放基金(2024-ZSJ-LB-02-04)

详细信息

通讯作者:
E-mail：binjiang@nuaa.edu.cn

中图分类号: V279；V241
计量
- 文章访问数: 659
- HTML全文浏览量: 148
- PDF下载量: 33
- 被引次数: 0
出版历程
- 收稿日期: 2022-05-31
- 录用日期: 2022-06-17
- 网络出版日期: 2022-11-19
- 整期出版日期: 2024-05-29

Data-driven fault detection and diagnosis for UAV swarms

College of Automation Engineering，Nanjing University of Aeronautics and Astronautics，Nanjing 211100，China

Funds: National Natural Science Foundation of China (62020106003,61663008); Open fund of the National Key Laboratory of Helicopter Aeromechanics (2024-ZSJ-LB-02-04)

More Information

Corresponding author: E-mail：binjiang@nuaa.edu.cn

摘要

摘要:
无人机集群系统对安全性和稳定性要求极高,实时的故障检测与诊断技术是保证安全可靠运行的有力手段。提出一种基于统计模型和改进宽度学习(BLS)模型的故障诊断方法。所提方法通过多元数据统计分析表征无人机集群系统在正常与不同故障模式下的行为特征，采用改进的BLS模型实现准确、快速的故障诊断。在此基础上，开发无人机集群系统的高逼真可视化仿真验证平台对所提方法的合理性与有效性进行验证。实验结果表明，所提方法与目前主流方法相比具有明显的诊断优势。
- 无人机集群 /
- 故障诊断 /
- 统计模型 /
- 宽度学习 /
- 仿真验证
Abstract:
The security requirements of the unmanned aerial vehicle (UAV) swarm system are extremely strict, and real-time fault detection and diagnosis is one of its important supporting technologies. This paper presents a fault diagnosis method based on statistical model and improved broad learning system (BLS) model. Firstly, the behavior characteristics of UAV swarm system under normal and different fault modes are characterized by multivariate data statistical analysis, and then the improved BLS model is used to achieve accurate and rapid fault diagnosis. On this basis, a high fidelity simulation verification platform is developed to verify the rationality and effectiveness of the proposed method. The experimental results show that the proposed method has obvious diagnostic advantages compared with the current mainstream methods.
- UAV swarm /
- fault diagnosis /
- statistical model /
- broad learning system /
- simulation verification

HTML全文

图 1 本文提出的故障检测与诊断框架流程

Figure 1. Illustration of fault detection and diagnosis scheme of this paper

下载: 全尺寸图片幻灯片

图 2 BLS网络架构

Figure 2. Architecture of broad learning system

下载: 全尺寸图片幻灯片

图 3 多旋翼无人机非线性故障注入模型^[20]

Figure 3. Nonlinear fault injection model of multi-rotor UAV^[20]

下载: 全尺寸图片幻灯片

图 4 故障注入仿真

Figure 4. Fault injection simulation

下载: 全尺寸图片幻灯片

图 5 软件在环仿真平台的故障检测结果

Figure 5. Fault detection results of software-in-the-loop simulation platform

下载: 全尺寸图片幻灯片

图 6 传统BLS和改进BLS参数确定

Figure 6. Parameters determination of original BLS method and improved BLS method

下载: 全尺寸图片幻灯片

图 7 4种情况下使用传统BLS和改进BLS的诊断结果

Figure 7. Fault diagnosis result of original BLS method and improved BLS method in four conditions

下载: 全尺寸图片幻灯片

表 1 4种情况下不同方法的诊断结果对比

Table 1. Diagnosis comparison of different methods under four conditions

方法诊断准确率/%

SAE 76.8

SVM 93.8

BLS 96.8

本文方法 99.2

下载: 导出CSV

参考文献(28)

[1]	NAWAZ H, ALI H M, ALI LAGHARI A. UAV communication networks issues: A review[J]. Archives of Computational Methods in Engineering, 2021, 28(3): 1349-1369. doi: 10.1007/s11831-020-09418-0
[2]	YU Z Q, QU Y H, ZHANG Y M. Distributed fault-tolerant cooperative control for multi-UAVs under actuator fault and input saturation[J]. IEEE Transactions on Control Systems Technology, 2019, 27(6): 2417-2429. doi: 10.1109/TCST.2018.2868038
[3]	王莉娜, 刘贞报, 院金彪, 等. 四旋翼无人机的自适应故障诊断与估计[J]. 北京航空航天大学学报, 2023, 49(9): 2395-2405. WANG L N, LIU Z B, YUAN J B, et al. Adaptive fault diagnosis and estimation for quadrotor UAV[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(9): 2395-2405(in Chinese).
[4]	PARSINIA M, EL KHAMLICHI B, PENG Q D, et al. A distributed mode reassignment scheme for mobile multihop wireless network of FDD nodes[J]. IEEE Transactions on Aerospace and Electronic Systems, 2020, 56(5): 3599-3612. doi: 10.1109/TAES.2020.2979035
[5]	SAIED M, LUSSIER B, FANTONI I, et al. Active versus passive fault-tolerant control of a redundant multirotor UAV[J]. The Aeronautical Journal, 2020, 124(1273): 385-408. doi: 10.1017/aer.2019.149
[6]	YU Z Q, ZHANG Y M, JIANG B, et al. A review on fault-tolerant cooperative control of multiple unmanned aerial vehicles[J]. Chinese Journal of Aeronautics, 2022, 35(1): 1-18. doi: 10.1016/j.cja.2021.04.022
[7]	JUNG W, BANG H. Fault and failure tolerant model predictive control of quadrotor UAV[J]. International Journal of Aeronautical and Space Sciences, 2021, 22(3): 663-675. doi: 10.1007/s42405-020-00331-1
[8]	YU Z Q, ZHANG Y M, JIANG B, et al. Composite adaptive disturbance observer-based decentralized fractional-order fault-tolerant control of networked UAVs[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2022, 52(2): 799-813.
[9]	YU Z Q, ZHANG Y M, JIANG B. PID-type fault-tolerant prescribed performance control of fixed-wing UAV[J]. Journal of Systems Engineering and Electronics, 2021, 32(5): 1053-1061. doi: 10.23919/JSEE.2021.000090
[10]	陆宁云, 孟宪锋, 姜斌, 等. 基于多信号模型和盲源分离的复合故障诊断方法[J]. 控制与决策, 2016, 31(11): 1945-1952. LU N Y, MENG X F, JIANG B, et al. Compound fault diagnosis method based on multi-signal model and blind source separation[J]. Control and Decision, 2016, 31(11): 1945-1952(in Chinese).
[11]	HUANG J, LI M N, ZHANG Y M, et al. Fault detection and classification for sensor faults of UAV by deep learning and time-frequency analysis[C]//Proceedings of the 40th Chinese Control Conference. Piscataway: IEEE Press, 2021: 4420-4424.
[12]	GUO L, LI R Z, JIANG B. A cascade broad neural network for concrete structural crack damage automated classification[J]. IEEE Transactions on Industrial Informatics, 2021, 17(4): 2737-2742. doi: 10.1109/TII.2020.3010799
[13]	CHEN H T, JIANG B, CHEN W, et al. Data-driven detection and diagnosis of incipient faults in electrical drives of high-speed trains[J]. IEEE Transactions on Industrial Electronics, 2019, 66(6): 4716-4725. doi: 10.1109/TIE.2018.2863191
[14]	GUO L, LI R Z, JIANG B, et al. Automatic crack distress classification from concrete surface images using a novel deep-width network architecture[J]. Neurocomputing, 2020, 397: 383-392. doi: 10.1016/j.neucom.2019.08.107
[15]	GUO L, LI R Z, JIANG B. An ensemble broad learning scheme for semisupervised vehicle type classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(12): 5287-5297. doi: 10.1109/TNNLS.2021.3083508
[16]	WANG J, GUI G, OHTSUKI T, et al. Compressive sampled CSI feedback method based on deep learning for FDD massive MIMO systems[J]. IEEE Transactions on Communications, 2021, 69(9): 5873-5885. doi: 10.1109/TCOMM.2021.3086525
[17]	YANG Y W, GAO F F, ZHONG Z M, et al. Deep transfer learning-based downlink channel prediction for FDD massive MIMO systems[J]. IEEE Transactions on Communications, 2020, 68(12): 7485-7497.
[18]	姜斌, 陈宏田, 易辉, 等. 数据驱动高速列车动态牵引系统的故障诊断[J]. 中国科学(信息科学), 2020, 50(4): 496-510. doi: 10.1360/SSI-2019-0220 JIANG B, CHEN H T, YI H, et al. Data-driven fault diagnosis for dynamic traction systems in high-speed trains[J]. Scientia Sinica (Informationis), 2020, 50(4): 496-510(in Chinese). doi: 10.1360/SSI-2019-0220
[19]	CHEN C L P, LIU Z L. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(1): 10-24. doi: 10.1109/TNNLS.2017.2716952
[20]	AMIN M T, KHAN F, AHMED S, et al. A data-driven Bayesian network learning method for process fault diagnosis[J]. Process Safety and Environmental Protection, 2021, 150: 110-122. doi: 10.1016/j.psep.2021.04.004
[21]	CHEN H T, JIANG B, LU N Y, et al. Deep PCA based real-time incipient fault detection and diagnosis methodology for electrical drive in high-speed trains[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6): 4819-4830. doi: 10.1109/TVT.2018.2818538
[22]	WU D Y, ZHAO J S. Process topology convolutional network model for chemical process fault diagnosis[J]. Process Safety and Environmental Protection, 2021, 150: 93-109. doi: 10.1016/j.psep.2021.03.052
[23]	SHI S B, LI G N, CHEN H X, et al. An efficient VRF system fault diagnosis strategy for refrigerant charge amount based on PCA and dual neural network model[J]. Applied Thermal Engineering, 2018, 129: 1252-1262. doi: 10.1016/j.applthermaleng.2017.09.117
[24]	GUO L, LI R, JIANG B. Fault detection and diagnosis using statistic feature and improved broad learning for traction systems in high-speed trains[J]. IEEE Transactions on Artificial Intelligence, 2022.
[25]	李润泽, 郭黎, 李保平, 等. 基于模糊宽度学习模型的光伏发电预测方法[J]. 控制工程, 2020, 27(11): 2016-2022. LI R Z, GUO L, LI B P, et al. A photovoltaic power prediction method based on fuzzy broad learning system[J]. Control Engineering of China, 2020, 27(11): 2016-2022(in Chinese).
[26]	WANG S, DAI X H, KE C X, et al. RflySim: A rapid multicopter development platform for education and research based on pixhawk and MATLAB[C]//Proceedings of the International Conference on Unmanned Aircraft Systems. Piscataway: IEEE Press, 2021: 1587-1594.
[27]	ZHAO X Y, HE Z X, ZHANG S Y, et al. A sparse-representation-based robust inspection system for hidden defects classification in casting components[J]. Neurocomputing, 2015, 153: 1-10. doi: 10.1016/j.neucom.2014.11.057
[28]	CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.