|本期目录/Table of Contents|

[1]张洪海,周锦伦,于文娟,等.基于HMM和DT的无人机异常检测方法*[J].中国安全生产科学技术,2022,18(3):193-198.[doi:10.11731/j.issn.1673-193x.2022.03.029]
　ZHANG Honghai,ZHOU Jinlun,YU Wenjuan,et al.Anomaly detection method of UAV based on hidden Markov model and decision tree[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):193-198.[doi:10.11731/j.issn.1673-193x.2022.03.029]
点击复制

基于HMM和DT的无人机异常检测方法*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
18
期数:
2022年3期
页码:
193-198
栏目:
职业安全卫生管理与技术
出版日期:
2022-03-31

文章信息/Info

Title:
Anomaly detection method of UAV based on hidden Markov model and decision tree
文章编号:
1673-193X(2022)-03-0193-06
作者:
张洪海; 周锦伦; 于文娟; 刘皞; 钟罡
(南京航空航天大学 民航学院，江苏 南京 211106)
Author(s):
ZHANG Honghai;  ZHOU Jinlun;  YU Wenjuan;  LIU Hao;  ZHONG Gang
(College of Civil Aviation,Nanjing University of Aeronautics & Astronautics,Nanjing Jiangsu 211106,China)
关键词:
无人机; 异常检测; 隐马尔可夫模型; 监督学习; 决策树
Keywords:
unmanned aerial vehicle (UAV);  anomaly detection;  hidden Markov model (HMM);  supervised learning;  decision tree (DT)
分类号:
X949
DOI:
10.11731/j.issn.1673-193x.2022.03.029
文献标志码:
A
摘要:
为了实时检测无人机异常状态，提出基于隐马尔可夫模型(Hidden Markov Model,HMM)和决策树(Decision Tree,DT)的无人机异常检测方法(HMMDT)。首先根据异常致因将无人机异常分为干扰异常和硬件异常；然后结合HMM和DT建立无人机异常检测模型，定义无人机异常度衡量异常状态的严重程度，确定其阈值作为异常分类标准；最后用经纬600pro型无人机进行实操验证，该方法异常检测召回率达92.9%，准确率达97.2%;对硬件异常的识别准确率达88.2%。结果表明：与传统异常检测方法相比,该方法在可以满足无人机实时异常检测需要的同时，具有较高的检测准确率和较小的时间复杂度。
Abstract:
In order to detect the UAV anomaly in real time,a UAV anomaly detection method (HMMDT) based on the hidden Markov model (HMM) and decision tree (DT) was proposed.Firstly,the UAV anomaly was divided into interference anomaly and hardware anomaly according to the anomaly causes.Secondly,the UAV anomaly detection model was established by combining HMM and DT,Then the UAV anomaly degree was defined to measure the severity of anomaly state,and its threshold was determined as the anomaly classification standard.Finally,the Jingwei 600Pro UAV was used to verify the method.The recall rate and precision of anomaly detection by the method reached 92.9% and 97.2% respectively,and the recognition accuracy of hardware anomaly reached 88.2%.The results showed that compared with the traditional anomaly detection methods,this method could meet the needs of UAV anomaly detection in real time with higher detection accuracy and smaller time complexity.

参考文献/References:

［1］SCHUMANNJ,ROZIER K Y,REINBACHER T,et al.Towards real-time,onboard,hardware supported sensor and software health management for unmanned aerial systems［J］.International Journal of Prognostics and Health Management,2015,6(21):1-27.
［2］何永福,王少军,王文娟,等.基于过采样投影近似基追踪的无人机异常检测［J］.仪器仪表学报,2016,37(7):1468-1476.HE Yongfu,WANG Shaojun,WANG Wenjuan,et al.Anomaly detection of UAV based on oversampled projection approximate basis tracking ［J］.Chinese Journal of Scientific Instrument,2016,37(7):1468-1476.
［3］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.
［4］韩鹏,王梦琦,赵嶷飞.基于贝叶斯网络的物流无人机失效风险评估［J］.中国安全生产科学技术,2020,16(11):178-183.HAN Peng,WANG Mengqi,ZHAO Yifei.Failure risk assessment of logistics UAV based on bayesian network ［J］.Journal of Safety Science and Technology,2020,16(11):178-183.
［5］刘连胜,张哲彦,王志亮,等.四旋翼无人机姿态异常感知数据生成方法［J］.仪器仪表学报,2020,41(4):58-67.LIU Liansheng,ZHANG Zheyan,WANG Zhiliang,et al.Generation method of attitude abnormal sensing data for quadrotor UAV ［J］.Chinese Journal of Scientific Instrument,2020,41(4):58-67.
［6］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.LI Chen,WANG Buhong,TIAN Jiwei,et al.Anomaly detection of sensor data of UAV based on LSTM-OCSVM ［J］.System of Small and Micro Computers,2021,42(4):700-705.
［7］SARAHG,MEDIA O.Introduction to machine learning with python［M］.Beijing:Posts & Telecom Press,2018.
［8］彭宇,何永福,王少军,等.飞行数据异常检测技术综述［J］.仪器仪表学报,2019,40(3):1-13.PENG Yu,HE Yongfu,WANG Shaojun,et al.Review of anomaly detection techniques in flight data ［J］.Chinese Journal of Scientific Instrument,2019,40(3):1-13.
［9］MK WES.Python for data analysis:data wrangling with pandas,numpy,and ipython［M］.Beijing:China Machine Press,2018.
［10］MANSOUR R F,ESCORCIA G J,GAMARRA M,et al.Intelligent video anomaly detection and classification using faster RCNN with deep reinforcement learning model［J］.Image and Vision Computing,2021,112,104229.
［11］BENJAMIN L,BENJAMIN M,NADA S,et al.A survey on anomaly detection for technical systems using LSTM networks［J］.Computers in Industry,2021,131,10498.
［12］ALBON C.Machine learning with python cookbook［M］.Beijing:Publishing House of Electrons Industry,2019.
［13］LI H,CHEN J,WANG F,et al.Ground-vehicle and unmanned-aerial-vehicle routing problems from two-echelon scheme perspective:a review［J］.European Journal of Operational Research,2021,294(3)：1078-1095.
［14］周志华.机器学习［M］.北京：清华大学出版社,2016:147-169.
［15］司守奎.Python数学实验与建模［M］.北京：科学出版社,2020:519-524.

相似文献/References:

[1]马国超,王立娟,马松,等.基于激光扫描和无人机倾斜摄影的露天采场安全监测应用[J].中国安全生产科学技术,2017,13(5):73.[doi:10.11731/j.issn.1673-193x.2017.05.012]
　MA Guochao,WANG Lijuan,MA Song,et al.Application of safety monitoring in open pit based on laser scanning and UAV oblique photography[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(3):73.[doi:10.11731/j.issn.1673-193x.2017.05.012]
[2]王静虹,李晨阳,支有冉,等.一种改进的CSCA+PCA化工过程异常检测技术[J].中国安全生产科学技术,2017,13(7):144.[doi:10.11731/j.issn.1673-193x.2017.07.023]
　WANG Jinghong,LI Chenyang,ZHI Youran,et al.An improved CSCA+PCA anomaly detection method of chemical process[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(3):144.[doi:10.11731/j.issn.1673-193x.2017.07.023]
[3]陈利琼,杜博文,吴东容.无人机在山区河流溢油事故溢油寻踪中的应用[J].中国安全生产科学技术,2019,15(7):161.[doi:10.11731/j.issn.1673-193x.2019.07.026]
　CHEN Liqiong,DU Bowen,WU Dongrong.Application of UAV for oil spill pursuit of oil spill accidents in mountain river[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(3):161.[doi:10.11731/j.issn.1673-193x.2019.07.026]
[4]李乃梁,陆勇,李开伟.无人机操作主观心理负荷测评与心率数据比较[J].中国安全生产科学技术,2021,17(4):35.[doi:10.11731/j.issn.1673-193x.2021.04.006]
　LI Nailiang,LU Yong,LI Kaiwei.Comparison of subjective mental workload evaluation and heart rate data of UAV operation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(3):35.[doi:10.11731/j.issn.1673-193x.2021.04.006]
[5]杨超,杨鹏,吕文生,等.基于无人机摄影测量的尾矿坝边坡表面变形监测*[J].中国安全生产科学技术,2021,17(5):5.[doi:10.11731/j.issn.1673-193x.2021.05.001]
　YANG Chao,YANG Peng,LYU Wensheng,et al.Surface deformation monitoring of tailings dam slope based on UAV photogrammetry[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(3):5.[doi:10.11731/j.issn.1673-193x.2021.05.001]
[6]刘聪,谌哲宇,储天羽,等.悬停状态双旋翼气动干扰与安全间隔研究*[J].中国安全生产科学技术,2021,17(12):30.[doi:10.11731/j.issn.1673-193x.2021.12.005]
　LIU Cong,CHEN Zheyu,CHU Tianyu,et al.Research on aerodynamic interaction and safety separation of twin rotors under hovering state[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(3):30.[doi:10.11731/j.issn.1673-193x.2021.12.005]
[7]吕伟,师远,汪京辉,等.复杂建筑空间人员应急疏散的无人机引导模型研究*[J].中国安全生产科学技术,2022,18(11):32.[doi:10.11731/j.issn.1673-193x.2022.11.005]
　LYU Wei,SHI Yuan,WANG Jinghui,et al.Research on UAV guidance model for emergency evacuation of personnel in complex building space[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(3):32.[doi:10.11731/j.issn.1673-193x.2022.11.005]
[8]袁丁,王艳红,雒旭峰.基于自适应滤波的无人机视觉导航误差补偿方法研究*[J].中国安全生产科学技术,2023,19(6):193.[doi:10.11731/j.issn.1673-193x.2023.06.027]
　YUAN Ding,WANG Yanhong,LUO Xufeng.Study on error compensation method of UAV visual navigation based on adaptive filtering[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(3):193.[doi:10.11731/j.issn.1673-193x.2023.06.027]
[9]张健,罗鑫悦,黎宗孝,等.基于动态贝叶斯网络的无人机航迹模型研究*[J].中国安全生产科学技术,2023,19(11):188.[doi:10.11731/j.issn.1673-193x.2023.11.026]
　ZHANG Jian,LUO Xinyue,LI Zongxiao,et al.Research on UAV track model based on dynamic Bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(3):188.[doi:10.11731/j.issn.1673-193x.2023.11.026]

备注/Memo

备注/Memo:
收稿日期： 2021-06-18
* 基金项目： 国家自然科学基金项目(71971114);南京航空航天大学研究生创新基地（实验室）开放基金项目(kfjj20200716)
作者简介： 张洪海，博士，教授，主要研究方向为空中交通管理智能化，通航运行与无人机管控。
通信作者： 周锦伦，硕士研究生，主要研究方向为空中交通管理智能化，无人机运行异常检测与轨迹预测。
更新日期/Last Update: 2022-04-18