论文:2020,Vol:38,Issue(3):619-626
引用本文:
梁少军, 张世荣, 郑幸, 林冬生. 基于DKPCA的固定翼无人机多工况在线故障诊断[J]. 西北工业大学学报
LIANG Shaojun, ZHANG Shirong, ZHENG Xing, LIN Dongsheng. Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered[J]. Northwestern polytechnical university

基于DKPCA的固定翼无人机多工况在线故障诊断
梁少军1, 张世荣2, 郑幸1, 林冬生1
1. 陆军工程大学 军械士官学校, 湖北 武汉 430075;
2. 武汉大学 电气与自动化学院, 湖北 武汉 430072
摘要:
固定翼无人机(UAV)执行任务过程包含多个阶段,体现出多工况特征,且UAV参数具有动态性和非线性,导致UAV在线故障诊断复杂化。本文选取UAV横向、纵向和速度控制回路的9个核心参数来表征无人机实时状态,通过动态预处理构建增广矩阵以描述UAV的动态特征;采用改进k-mediods*算法对UAV扩维数据进行工况聚类,并采用神经网络完成在线工况匹配。针对UAV非线性特征,采用了DKPCA算法进行故障诊断,基于SPE和T2构建合成指标FAI用于故障监测,并提出了分离算法从高维数据定位故障变量;为了应对测量误差带来的故障误报,还对DKPCA合成指标FAI进行了小波去噪处理。最后,以某UAV的实飞数据为对象,呈现以上算法的结果,验证了工况聚类、工况匹配、故障诊断及小波去噪等算法的有效性。
关键词:    固定翼无人机    动态核主元分析    聚类    多工况    故障诊断   
Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered
LIANG Shaojun1, ZHANG Shirong2, ZHENG Xing1, LIN Dongsheng1
1. School of Ordnance Sergeant, Army Engineering University, Wuhan 430075, China;
2. School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
Abstract:
The mission execution process of a fixed-wing UAV has multiple phases and multiple operation conditions. Its parameters are nonlinear and dynamic. These characteristics make its online fault detection rather complicated. To carry out the fault detection, this paper selects nine key parameters of the transverse, longitudinal and velocity control loops of the UAV to characterize its real-time conditions. The core parameters are dynamically preprocessed to construct an augmented matrix so as to describe the dynamic characteristics of the UAV. Then, the improved k-mediods* algorithm is used to cluster the operation conditions of the UAVs by means of augmented dimensions. Neural networks are used to achieve the online matching of operation conditions. To overcome the nonlinearity of the UAV, the fault detection is performed by using the DKPCA algorithm; the fault monitoring is conducted through constructing the compound indexes of SPE and T2, notated as FAI. Furthermore, the fault separation algorithm is proposed to specify the variables of fault from the augmented high-dimensional data set. In order to deal with the erroneous reporting of faults due to measurement errors, the paper conducts the wavelet denoising of FAI, the compound indexes of the DKPCA algorithm. Finally, the data set collected from a real UAV flight is used to verify the effectiveness of the DKPCA algorithm for operation condition clustering and matching, fault detection and wavelet denoising.
Key words:    fixed-wing UAV    fault detection    DKPCA algorithm    operation condition clustering    multiple operation conditions   
收稿日期: 2019-08-02     修回日期:
DOI: 10.1051/jnwpu/20203830619
通讯作者: 张世荣(1975-),武汉大学副教授,主要从事机器学习及故障诊断研究。E-mail:srzhang@whu.edu.cn     Email:srzhang@whu.edu.cn
作者简介: 梁少军(1987-),陆军工程大学讲师,主要从事故障诊断及模式识别研究。
相关功能
PDF(2276KB) Free
打印本文
把本文推荐给朋友
作者相关文章
梁少军  在本刊中的所有文章
张世荣  在本刊中的所有文章
郑幸  在本刊中的所有文章
林冬生  在本刊中的所有文章

参考文献:
[1] ABBASPOUR A, ABOUTALEBI P, YEN K K, et al. Neural Adaptive Observer-Based Sensor and Actuator Fault Detection in Nonlinear Systems:Application in UAV[J]. ISA Transactions,2017,67:317-329
[2] LEE J, SHIN H, KIM T. Optimal Combination of Fault Detection and Isolation Methods of Integrated Navigation Algorithm for UAV[J]. International Journal of Aeronautical and Space Sciences,2018,19(3):694-710
[3] 邱宗江, 刘慧霞, 席庆彪, 等. 无人机PCA故障检测与诊断技术研究[J]. 计算机工程与应用,2013,49(4):262-266 QIU Zongjiang, LIU Huixia, XI Qingbiao, et al. UAV PCA Fault Detection and Diagnosis Techniques[J]. Computer Engineering and Applications, 2013,49(4):262-266(in Chinese)
[4] 薛婷, 钟麦英, 李钢. 基于小波变换与等价空间的无人机作动器故障检测[J]. 控制理论与应用,2016,33(9):1193-1199 XUE Ting, ZHONG Maiying, LI Gang. Wavelet Transform and Parity Space Based Actuator Fault Detection for Unmanned Aerial Vehicle[J]. Control Theory & Applications, 2016,33(9):1193-1199(in Chinese)
[5] 李明虎, 李钢, 钟麦英. 动态核主元分析在无人机故障诊断中的应用[J]. 山东大学学报,2017,47(5):215-222 LI Minghu, LI Gang, ZHONG Maiying. Application of Dynamic Kernel Principal Component Analysis in Unmanned Aerial Vehicle Fault Diagnosis[J]. Journal of Shandong University, 2017,47(5):215-222(in Chinese)
[6] MINJUAN Z. Finding Good XML Fragments Based on k-Medoid Cluster Number Optimization and Ranking Model for Feedback[C]//2013 International Conference on Information Technology and Applications, 2013:333-337
[7] GUO J, ZHAO Y, LI J. A Multi-Relational Hierarchical Clustering Algorithm Based on Shared Nearest Neighbor Similarity[C]//Sixth International Conference on Machine Learning and Cybernetics, 2007:3951-3955
[8] 唐东明. 聚类分析及其应用研究[D]. 成都:电子科技大学, 2010 TANG Dongming. Study on Clustering Algorithm and Its Applications[D]. Chengdu:University of Electronic Science and Technology of China, 2010(in Chinese)
[9] 张世荣, 程琴, 张芳芳. 基于感测线圈和KPCA的电机轴承故障检测[J]. 电机与控制应用,2018,45(4):98-104 ZHANG Shirong, CHENG Qin, ZHANG Fangfang. Fault Detection of Motor Bearings Based on Detection Coils and KPCA Algorithm[J]. Electic Machines & Control Application, 2018,45(4):98-104(in Chinese)
[10] GE Z, YANG C, SONG Z. Improved Kernel PCA-Based Monitoring Approach for Nonlinear Processes[J]. Chemical Engineering Science, 2009, 64(9):2245-2255
[11] JAFFEL I, TAOUALI O, HARKAT M F, et al. Moving Window KPCA with Reduced Complexity for Nonlinear Dynamic Process Monitoring[J]. ISA Transactions, 2016, 64:184-192
[12] HOFFMANN H. Kernel PCA for Novelty Detection[J]. Pattern Recognition,2007,40(3):863-874
[13] ZHANG Y, LI S, TENG Y. Dynamic Processes Monitoring Using Recursive Kernel Principal Component Analysis[J].Chemical Engineering Science,2012,72:78-86
[14] 邓晓刚, 田学民. 一种基于KPCA的非线性故障诊断方法[J].山东大学学报,2005,35(3):103-106 DENG Xiaogang, TIAN Xuemin. Nonlinear Process Fault Diagnosis Method Using Kernel Principal Component Analysis[J]. Journal of Shandong University, 2005,35(3):103-106(in Chinese)
[15] ZHANG S, TANG Q, LIN Y, et al. Fault Detection of Feed Water Treatment Process Using PCA-WD with Parameter Optimization[J]. ISA Transactions, 2017, 68:313-326
[16] 岑翼刚. 一类单(多)小波构造方法及小波信号处理[D]. 武汉:华中科技大学, 2006 CEN Yigang. The Construction of a Sort of the Scalar(Multi) Wavelet and Wavelet Signal Processing[D]. Wuhan:Huazhong University of Science and Technology, 2006(in Chinese)