《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1833-1841.DOI: 10.11772/j.issn.1001-9081.2022060808
        
                    
            祁超帅1, 何文思2, 焦毅3, 马英红1( ), 蔡伟4, 任素萍4
), 蔡伟4, 任素萍4
                  
        
        
        
        
    
收稿日期:2022-06-06
									
				
											修回日期:2022-11-09
									
				
											接受日期:2022-11-09
									
				
											发布日期:2023-06-08
									
				
											出版日期:2023-06-10
									
				
			通讯作者:
					马英红
							作者简介:祁超帅(1998—),男,河南开封人,硕士研究生,主要研究方向:机器学习、数据挖掘基金资助:
        
                                                                                                                                                            Chaoshuai QI1, Wensi HE2, Yi JIAO3, Yinghong MA1( ), Wei CAI4, Suping REN4
), Wei CAI4, Suping REN4
			  
			
			
			
                
        
    
Received:2022-06-06
									
				
											Revised:2022-11-09
									
				
											Accepted:2022-11-09
									
				
											Online:2023-06-08
									
				
											Published:2023-06-10
									
			Contact:
					Yinghong MA   
							About author:QI Chaoshuai, born in 1998, M. S. candidate. His research interests include machine learning, data mining.Supported by:摘要:
针对无人机(UAV)机载健康状态监测领域的UAV飞行数据异常检测问题,首先阐述了UAV飞行数据的特点、常见的飞行数据异常类型及对异常检测算法的要求;然后梳理了UAV飞行数据异常检测算法的研究现状,并归为3大类:基于先验知识的定性异常检测算法、基于模型的定量异常检测算法和基于数据驱动的异常检测算法,同时分析了各类算法的应用场景和优缺点;最后总结了UAV飞行数据异常检测算法目前存在的问题和挑战,展望了未来UAV飞行数据异常检测领域的重点发展方向,为新的研究提供了参考思路。
中图分类号:
祁超帅, 何文思, 焦毅, 马英红, 蔡伟, 任素萍. 无人机飞行数据异常检测算法综述[J]. 计算机应用, 2023, 43(6): 1833-1841.
Chaoshuai QI, Wensi HE, Yi JIAO, Yinghong MA, Wei CAI, Suping REN. Survey on anomaly detection algorithms for unmanned aerial vehicle flight data[J]. Journal of Computer Applications, 2023, 43(6): 1833-1841.
| 类型 | 优点 | 缺点 | 
|---|---|---|
| 基于先验知识的定性算法 | 无需严格的数据定量分析,实现简单 | 先验知识少,异常种类难以完全把握 | 
| 基于模型的定量算法 | 模型准确度较高 | 模型建立困难,移植性差 | 
| 基于数据驱动的算法 | 通用性强,先验知识需求小 | 大多数算法复杂度高,依赖数据的质量 | 
表1 异常检测算法优劣对比
Tab. 1 Comparison of pros and cons of anomaly detection algorithms
| 类型 | 优点 | 缺点 | 
|---|---|---|
| 基于先验知识的定性算法 | 无需严格的数据定量分析,实现简单 | 先验知识少,异常种类难以完全把握 | 
| 基于模型的定量算法 | 模型准确度较高 | 模型建立困难,移植性差 | 
| 基于数据驱动的算法 | 通用性强,先验知识需求小 | 大多数算法复杂度高,依赖数据的质量 | 
| 算法类型 | 基本思想 | 优点 | 缺点 | 
|---|---|---|---|
| 基于统计 | 异常点分布在低概率区域 | 数据处理速度快,能有效识别单维数据的离群点 | 很难确定概率分布假设,不适用于高维数据 | 
| 基于分类 | 训练决策边界分离异常数据 | 适用于高维且标签明确的场景 | 过于依赖数据标签 | 
| 基于相似性 | 根据数据间的相似度识别异常数据 | 检测准确度高 | 大多相似性算法计算复杂度高 | 
| 基于预测 | 通过数据与预测值的残差判断异常 | 可较好地拟合数据的趋势性 | 对噪声数据敏感 | 
表2 各基于数据驱动算法的特点
Tab. 2 Characteristics of different data-driven algorithms
| 算法类型 | 基本思想 | 优点 | 缺点 | 
|---|---|---|---|
| 基于统计 | 异常点分布在低概率区域 | 数据处理速度快,能有效识别单维数据的离群点 | 很难确定概率分布假设,不适用于高维数据 | 
| 基于分类 | 训练决策边界分离异常数据 | 适用于高维且标签明确的场景 | 过于依赖数据标签 | 
| 基于相似性 | 根据数据间的相似度识别异常数据 | 检测准确度高 | 大多相似性算法计算复杂度高 | 
| 基于预测 | 通过数据与预测值的残差判断异常 | 可较好地拟合数据的趋势性 | 对噪声数据敏感 | 
| 1 | 祁圣君,井立,王亚龙. 无人机系统及发展趋势综述[J]. 飞航导弹, 2018(4):17-21. 10.21884/ijmter.2017.4120.y54mr | 
| QI S J, JING L, WANG Y L. Overview of unmanned aerial vehicle systems and development trends[J]. Aerodynamic Missile Journal, 2018(4): 17-21. 10.21884/ijmter.2017.4120.y54mr | |
| 2 | 李磊,王彤,蒋琪. 从美军2042年无人系统路线图看无人系统关键技术发展动向[J]. 无人系统技术, 2018, 1(4):79-84. | 
| LI L, WANG T, JIANG Q. Key technology develop trends of unmanned systems viewed from unmanned systems integrated roadmap 2017-2042 [J]. Unmanned Systems Technology, 2018, 1(4): 79-84. | |
| 3 | CHANDOLA V, BANERJEE A, KUMAR V. Anomaly detection: a survey [J]. ACM Computing Surveys, 2009, 41(3): No.15. 10.1145/1541880.1541882 | 
| 4 | 陈亚锋. 无人机飞行数据实时异常检测系统研制[D]. 哈尔滨:哈尔滨工业大学, 2017:3-3. 10.1109/phm.2017.8079160 | 
| CHEN Y F. Real-time anomaly detection system for unmanned aerial vehicle flight data[D]. Harbin: Harbin Institute of Technology, 2017: 3-3. 10.1109/phm.2017.8079160 | |
| 5 | 彭喜元,庞景月,彭宇,等. 航天器遥测数据异常检测综述[J]. 仪器仪表学报, 2016, 37(9):1929-1945. 10.3969/j.issn.0254-3087.2016.09.003 | 
| PENG X Y, PANG J Y, PENG Y, et al. Review on anomaly detection of spacecraft telemetry data [J]. Chinese Journal of Scientific Instrument, 2016, 37(9): 1929-1945. 10.3969/j.issn.0254-3087.2016.09.003 | |
| 6 | LU H M, LI Y J, MU S L, et al. Motor anomaly detection for unmanned aerial vehicles using reinforcement learning [J]. IEEE Internet of Things Journal, 2018, 5(4): 2315-2322. 10.1109/jiot.2017.2737479 | 
| 7 | 黄可鸣. 专家系统导论[M]. 南京:东南大学出版社, 1988: 217-229. | 
| HUANG K M. An Introduction to Expert Systems[M]. Nanjing: Southeast University Press, 1988: 217-229. | |
| 8 | 孙学初. 无人机飞控系统故障诊断专家系统设计[D]. 成都:电子科技大学, 2012:14-24. 10.3969/j.issn.1672-545X.2012.02.023 | 
| SUN X C. Design of UAV flight control system fault diagnosis expert system[D]. Chengdu: University of Electronic Science and Technology of China, 2012:14-24. 10.3969/j.issn.1672-545X.2012.02.023 | |
| 9 | 刘瀚泽. 基于机器学习的无人机飞控故障智能诊断系统研究[D]. 成都:电子科技大学, 2019:20-25. | 
| LIU H Z. Research on intelligent diagnosis system of UAV flight control fault based on machine learning [D]. Chengdu: University of Electronic Science and Technology of China, 2019: 20-25. | |
| 10 | 卿立勇. 基于飞行数据的飞机故障预测与故障诊断系统研究[D]. 南京:南京航空航天大学, 2007:30-50. 10.7666/d.d037712 | 
| QING L Y. Research on airplane fault prognosis and diagnosis system based on flight data [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2007: 30-50. 10.7666/d.d037712 | |
| 11 | 北京航空航天大学. 一种概率耦合关系下无人机系统多层级风险评估方法: 202010410327.1[P]. 2020-09-18. | 
| Beihang University. A multi-level risk assessment method for unmanned aerial vehicle system under probabilistic coupling relationship: 202010410327.1 [P]. 2020-09-18. | |
| 12 | GAO Z W, CECATI C, DING S X. A survey of fault diagnosis and fault-tolerant techniques — Part I: fault diagnosis with model-based and signal-based approaches[J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3757-3767. 10.1109/tie.2015.2417501 | 
| 13 | CHEN M J, PAN Z, CHI C Z, et al. Research on UAV wing structure health monitoring technology based on finite element simulation analysis[C]// Proceedings of the 11th International Conference on Prognostics and System Health Management. Piscataway: IEEE, 2020: 86-90. 10.1109/phm-jinan48558.2020.00022 | 
| 14 | BEARD R V. Failure accommodation in linear systems through self-reorganization [R/OL]. [2022-03-21].. | 
| 15 | 谈娟. 基于解析模型的飞控系统故障诊断技术研究[D]. 南京:南京航空航天大学, 2020:12-15. | 
| TAN J. Research on fault diagnosis technology of flight control system based on analytical model[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2020: 12-15. | |
| 16 | 刘哲成,郭丽娟. 基于分层滤波算法的无人机控制系统故障检测技术[J]. 计算机测量与控制, 2020, 28(5):23-26, 30. | 
| LIU Z C, GUO L J. Fault detection technology for UAV control system based on hierarchical filtering algorithm[J]. Computer Measurement and Control, 2020, 28(5): 23-26, 30. | |
| 17 | 武宝军. 无人机飞行控制系统故障检测技术研究[D]. 西安:西北工业大学, 2007:21-31. | 
| WU B J. Research on fault detection technology of UAV flight control system [D]. Xi’an: Northwestern Polytechnical University, 2007: 21-31. | |
| 18 | 贾庆贤,张迎春,管宇,等. 基于解析模型的非线性系统故障诊断方法综述[J]. 信息与控制, 2012, 41(3):356-364. | 
| JIA Q X, ZHANG Y C, GUAN Y, et al. Fault diagnosis of nonlinear systems based on analytical models: a survey [J]. Information and Control, 2012, 41(3): 356-364. | |
| 19 | 刘剑慰. 基于模型的飞行控制系统故障诊断方法研究[D]. 南京:南京航空航天大学, 2014:23-78. | 
| LIU J W. Research of model based fault diagnosis for flight control systems[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2014:23-78. | |
| 20 | MELNYK I, MATTHEWS B, VALIZADEGAN H, et al. Vector autoregressive model-based anomaly detection in aviation systems[J]. Journal of Aerospace Information Systems, 2016, 13(4): 161-173. 10.2514/1.i010394 | 
| 21 | PASCHALIDIS I C, CHEN Y. Statistical anomaly detection with sensor networks[J]. ACM Transactions on Sensor Networks, 2010, 7(2): No.17. 10.1145/1824766.1824773 | 
| 22 | FREEMAN P, PANDITA R, SRIVASTAVA N, et al. Model-based and data-driven fault detection performance for a small UAV[J]. IEEE/ASME Transactions on Mechatronics, 2013, 18(4): 1300-1309. 10.1109/tmech.2013.2258678 | 
| 23 | MELNYK I, YADAV P, STEINBACH M, et al. Detection of precursors to aviation safety incidents due to human factors [C]// Proceedings of the IEEE 13th International Conference on Data Mining Workshops. Piscataway: IEEE, 2013: 407-412. 10.1109/icdmw.2013.55 | 
| 24 | CHOWDHARY G, SRINIVASAN S, JOHNSON E N. Frequency domain method for real-time detection of oscillations [J]. Journal of Aerospace Computing, Information, and Communication, 2011, 8(2): 42-52. 10.2514/1.52110 | 
| 25 | BRONZ M, BASKAYA E, DELAHAYE D, et al. Real-time fault detection on small fixed-wing UAVs using machine learning [C]// Proceedings of the IEEE/AIAA 39th Digital Avionics Systems Conference. Piscataway: IEEE, 2020: 1-10. 10.1109/dasc50938.2020.9256800 | 
| 26 | YAMAN O, YOL F, ALTINORS A. A fault detection method based on embedded feature extraction and SVM classification for UAV motors [J]. Microprocessors and Microsystems, 2022, 94: No.104683. 10.1016/j.micpro.2022.104683 | 
| 27 | DAS S, MATTHEWS B L, SRIVASTAVA A N, et al. Multiple kernel learning for heterogeneous anomaly detection: algorithm and aviation safety case study [C]// Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2010: 47-56. 10.1145/1835804.1835813 | 
| 28 | PURANIK T G, MAVRIS D N. Anomaly detection in general-aviation operations using energy metrics and flight-data records[J]. Journal of Aerospace Information Systems, 2018, 15(1): 22-36. 10.2514/1.i010582 | 
| 29 | PAN D W. Hybrid data-driven anomaly detection method to improve UAV operating reliability [C]// Proceedings of the 2017 Prognostics and System Health Management Conference. Piscataway: IEEE, 2017: 1-4. 10.1109/phm.2017.8079281 | 
| 30 | PAN D W, NIE L Q, KANG W X, et al. UAV anomaly detection using active learning and improved S3VM model [C]// Proceedings of the 2020 International Conference on Sensing, Measurement and Data Analytics in the era of Artificial Intelligence. Piscataway: IEEE, 2020: 253-258. 10.1109/icsmd50554.2020.9261709 | 
| 31 | MACK D L C, BISWAS G, KOUTSOUKOS X D, et al. Learning Bayesian network structures to augment aircraft diagnostic reference models[J]. IEEE Transactions on Automation Science and Engineering, 2017, 14(1): 358-369. 10.1109/tase.2016.2542186 | 
| 32 | LIU F T, TING K M, ZHOU Z H. Isolation-based anomaly detection[J]. ACM Transactions on Knowledge Discovery from Data, 2012, 6(1): No.3. 10.1145/2133360.2133363 | 
| 33 | YU L, DING W R. A KNNS based anomaly detection method applied for UAV flight data stream [C]// Proceedings of the 2015 Prognostics and System Health Management Conference. Piscataway: IEEE, 2015:1-8. 10.1109/phm.2015.7380051 | 
| 34 | LI L S, DAS S, HANSMAN R J, et al. Analysis of flight data using clustering techniques for detecting abnormal operations [J]. Journal of Aerospace Information Systems, 2015, 12(9): 587-598. 10.2514/1.i010329 | 
| 35 | KHAN S, LIEW C F, YAIRI T, et al. Unsupervised anomaly detection in unmanned aerial vehicles[J]. Applied Soft Computing, 2019, 83: No.105650. 10.1016/j.asoc.2019.105650 | 
| 36 | 陈圣楠,钱红燕,李伟. 基于角度方差的多层次高维数据异常检测算法[J]. 计算机应用研究, 2016, 33(11):3383-3386. | 
| CHEN S N, QIAN H Y, LI W. Hybrid outlier detection algorithm based on angle variance for high-dimensional data [J]. Application Research of Computers, 2016, 33(11): 3383-3386. | |
| 37 | KRIEGEL H P, SCHUBERT M, ZIMEK A. Angle-based outlier detection in high-dimensional data [C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2008: 444-452. 10.1145/1401890.1401946 | 
| 38 | 何永福. 基于子空间学习的无人机飞行数据瞬时异常检测研究[D]. 哈尔滨:哈尔滨工业大学, 2019:50-70. | 
| HE Y F. UAV flight data instantaneous anomalies detection based on subspace learning[D]. Harbin: Harbin Institute of Technology, 2019:50-70. | |
| 39 | WANG B K, LIU D T, PENG X Y, et al. Data-driven anomaly detection of UAV based on multimodal regression model[C]// Proceedings of the 2019 IEEE International Instrumentation and Measurement Technology Conference. Piscataway: IEEE, 2019: 1-6. 10.1109/i2mtc.2019.8827154 | 
| 40 | WANG B K, WANG Z Y, LIU L S, et al. Data-driven anomaly detection for UAV sensor data based on deep learning prediction model[C]// Proceedings of the 2019 Prognostics and System Health Management Conference. Piscataway: IEEE, 2019: 286-290. 10.1109/phm-paris.2019.00055 | 
| 41 | 王泽洋. 基于LSTM的无人机异常检测方法研究[D]. 哈尔滨:哈尔滨工业大学, 2018:15-44. | 
| WANG Z Y. Unmanned aerial vehicle anomaly detection based on long short term memory [D]. Harbin: Harbin Institute of Technology, 2018: 15-44. | |
| 42 | ALOS A, DAHROUJ Z. Using MLSTM and multioutput convolutional LSTM algorithms for detecting anomalous patterns in streamed data of unmanned aerial vehicles[J]. IEEE Aerospace and Electronic Systems Magazine, 2022, 37(6): 6-15. 10.1109/maes.2021.3053108 | 
| 43 | ZHONG J, ZHANG Y J, WANG J Y, et al. Unmanned aerial vehicle flight data anomaly detection and recovery prediction based on spatio-temporal correlation[J]. IEEE Transactions on Reliability, 2022, 71(1): 457-468. 10.1109/tr.2021.3134369 | 
| 44 | DUDUKCU H V, TASKIRAN M, KAHRAMAN N. Unmanned Aerial Vehicles (UAVs) battery power anomaly detection using temporal convolutional network with simple moving average algorithm[C]// Proceedings of the 2022 International Conference on Innovations in Intelligent Systems and Applications. Piscataway: IEEE, 2022: 1-5. 10.1109/inista55318.2022.9894193 | 
| 45 | YOU J T, LIANG J, LIU D T. An adaptable UAV sensor data anomaly detection method based on TCN model transferring [C]// Proceedings of the 2022 Prognostics and Health Management Conference. Piscataway: IEEE, 2022:73-76. 10.1109/phm2022-london52454.2022.00021 | 
| 46 | CHEN Y F, WANG B K, LIU W, et al. On-line and non-invasive anomaly detection system for unmanned aerial vehicle[C]// Proceedings of 2017 Prognostics and System Health Management Conference. Piscataway: IEEE, 2017: 1-7. 10.1109/phm.2017.8079160 | 
| 47 | 李晨,王布宏,田继伟,等. 基于LSTM-OCSVM的无人机传感器数据异常检测[J]. 小型微型计算机系统, 2021, 42(4):700-705. 10.3969/j.issn.1000-1220.2021.04.005 | 
| LI C, WANG B H, TIAN J W, et al. Anomaly detection method for UAV sensor data based on LSTM-OCSVM [J]. Journal of Chinese Computer Systems, 2021, 42(4): 700-705. 10.3969/j.issn.1000-1220.2021.04.005 | |
| 48 | PANG G S, SHEN C H, CAO L B, et al. Deep learning for anomaly detection: a review [J]. ACM Computing Surveys, 2022, 54(2): No.38. 10.1145/3439950 | 
| [1] | 穆凌霞, 周政君, 王斑, 张友民, 薛向宏, 宁凯凯. 多无人机编队避障和编队重构方法[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2938-2946. | 
| [2] | 陈廷伟, 张嘉诚, 王俊陆. 面向联邦学习的随机验证区块链构建[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2770-2776. | 
| [3] | 陈虹, 齐兵, 金海波, 武聪, 张立昂. 融合1D-CNN与BiGRU的类不平衡流量异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2493-2499. | 
| [4] | 刘禹含, 吉根林, 张红苹. 基于骨架图与混合注意力的视频行人异常检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2551-2557. | 
| [5] | 李欢欢, 黄添强, 丁雪梅, 罗海峰, 黄丽清. 基于多尺度时空图卷积网络的交通出行需求预测[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2065-2072. | 
| [6] | 林欣蕊, 王晓菲, 朱焱. 基于局部扩展社区发现的学术异常引用群体检测[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1855-1861. | 
| [7] | 董瑶, 付怡雪, 董永峰, 史进, 陈晨. 不完整多视图聚类综述[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1673-1682. | 
| [8] | 黄天宇, 李远兴, 陈昊, 郭紫佳, 魏明军. 地空协同场景下加权模糊聚类用户簇划分方法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1555-1561. | 
| [9] | 孟凡, 杨群力, 霍静, 王新宽. 基于边缘异常候选集的迭代式主动多元时序异常检测算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1458-1463. | 
| [10] | 郑志强, 段海滨. 基于有限忍耐度鸽群优化的无人机近距空战机动决策[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1401-1407. | 
| [11] | 朱子蒙, 李志新, 郇战, 陈瑛, 梁久祯. 基于三元中心引导的弱监督视频异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1452-1457. | 
| [12] | 唐睿, 岳士博, 张睿智, 刘川, 庞川林. UAV协助下非正交多址接入使能的数据采集系统中能效优化机制[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1209-1218. | 
| [13] | 周景贤, 李希娜. 基于改进卷积神经网络和射频指纹的无人机检测与识别[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 876-882. | 
| [14] | 蔡美玉, 朱润哲, 吴飞, 张开昱, 李家乐. 基于注意力机制和多粒度特征融合的跨视角匹配模型[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 901-908. | 
| [15] | 杨克帅, 武优西, 耿萌, 刘靖宇, 李艳. 一次性条件下top-k高平均效用序列模式挖掘算法[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 477-484. | 
| 阅读次数 | ||||||
| 全文 |  | |||||
| 摘要 |  | |||||