Application of kernel principal component analysis in autonomous fault diagnosis for spacecraft flywheel
-
摘要:
针对在轨航天器执行机构故障诊断研究相对较少、姿态控制系统背景建模相对简单、算法自主性不强等问题,提出一种基于核主元分析(KPCA)的飞轮自主故障诊断方法。建立使用飞轮组的刚体航天器三轴稳定姿态控制系统;在力矩模式和转速模式下分别建立飞轮伺服系统,并给出飞轮常见故障及其模型;在上述模式下分别采集飞轮组输入输出的差值数据,进行同源扩维,通过改进特征向量归一化准则,优化了KPCA统计量法,并建立一种综合指标,通过比对该指标是否超限判断有无故障,减少对单一指标的主观侧重;在经典的贡献图法基础上进行溯源合并,计算综合贡献率,以此定位故障飞轮。仿真结果表明:所提方法能够实现航天器飞轮自主故障诊断,2种模式下,正确率较传统方法分别平均提高约40.94%、22.23%,适用于单点故障、多点故障、轻微故障等多种情况。
Abstract:Aiming at the problems of relatively few studies on actuator fault diagnosis of on orbit spacecraft, relatively simple background modeling for attitude control system and weak algorithm autonomy, an autonomous fault diagnosis method for spacecraft flywheel based on kernel principal component analysis (KPCA) is proposed. Firstly, the three-axis stable attitude control system of rigid spacecraft using flywheel group is established. Secondly, the flywheel servo system is established in torque mode and speed mode, and the common faults and models of flywheel are given. Then, in the above mode, the input and output differential data of flywheel group are collected for homologous dimension expansion. By improving the normalization criterion of eigenvector, the classical KPCA statistical method is optimized, and a comprehensive index is established. By comparing whether the index exceeds the limit to judge whether there is a fault, the subjective focus on a single index is reduced. Finally, based on the classical contribution graph method, the fault flywheels are located by tracing source and merging fault comprehensive contribution rate. Simulation results show that this method can realize autonomous fault diagnosis of spacecraft flywheel, and the accuracy of the two modes increases by an average of about 40.94% and 22.23% compared to traditional methods. It is suitable for single point fault, multi-point fault, and minor fault.
-
表 1 飞轮常见故障及模型
Table 1. Common faults and models of flywheel
序号 ew fw 故障特征 故障类型 1 0 0 转速不变或渐趋0 空转 2 0 0 转速迅速归0 卡死 3 1 $ \ne 0 $ 输入输出存在偏差 偏差故障 4 $ (0,1) $ 0 输入输出按比减小 增益故障 5 不定 不定 无固定特征 混合故障 表 2 飞轮基本参数
Table 2. Basic parameters of flywheel
转动惯量/
(kg·m2)电枢
电阻/$ \Omega $转矩系数/
(N·m·A−1)反电动势系数/
(V·s·rad−1)0.0077 2 0.029 0.029 表 3 飞轮故障参数
Table 3. Fault parameters of flywheels
故障时间/s 故障类型 ew fw/(N·m) 故障部位 550~600 空转 0 0 飞轮1 450~500 偏差故障 1 −0.0003 飞轮2 350~400 增益故障 0.15 0 飞轮3 350~500 偏差故障 1 −0.0003 飞轮3 表 4 力矩模式下时滞参数为2时不同指标性能对比
Table 4. Performance comparison of different indexes when number of delay parameter is 2 in torque mode
% 判定准则 误报率 漏报率 正确率 T2超限 1.50 11.55 91.80 SPE超限 2.60 74.00 49.80 T2、SPE同时超限 0.20 74.50 50.27 综合指标超限 4.60 11.25 90.97 表 5 转速模式下时滞参数为2时不同指标性能对比
Table 5. Performance comparison of different indexes when number of delay parameter is 2 in speed mode
% 判定准则 误报率 漏报率 正确率 T2超限 6.40 0.10 97.80 SPE量超限 6.10 37.90 72.70 T2、SPE同时超限 0.70 37.90 74.50 综合指标超限 12.30 0.10 95.83 -
[1] 闻新, 张兴旺, 朱亚萍, 等. 智能故障诊断技术: MATLAB应用[M]. 北京: 北京航空航天大学出版社, 2015: 10-18.WEN X, ZHANG X W, ZHU Y P, et al. Intelligent fault diagnosis technology: Application of MATLAB[M]. Beijing: Beihang University Press, 2015: 10-18(in Chinese). [2] HWANG I, KIM S, KIM Y, et al. A survey of fault detection, isolation, and reconfiguration methods[J]. IEEE Transactions on Control Systems Technology, 2010, 18(3): 636-653. doi: 10.1109/TCST.2009.2026285 [3] FRANK P M. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy[J]. Automatica, 1990, 26(3): 459-474. doi: 10.1016/0005-1098(90)90018-D [4] 沈毅, 李利亮, 王振华. 航天器故障诊断与容错控制技术研究综述[J]. 宇航学报, 2020, 41(6): 647-656. doi: 10.3873/j.issn.1000-1328.2020.06.002SHEN Y, LI L L, WANG Z H. A review of fault diagnosis and fault-tolerant control techniques for spacecraft[J]. Journal of Astronautics, 2020, 41(6): 647-656(in Chinese). doi: 10.3873/j.issn.1000-1328.2020.06.002 [5] JACKSON J E, MUDHOLKAR G S. Control procedures for residuals associated with principal component analysis[J]. Technometrics, 1979, 21(3): 341-349. doi: 10.1080/00401706.1979.10489779 [6] NOMIKOS P, MACGREGOR J F. Multivariate SPC charts for monitoring batch processes[J]. Technometrics, 1995, 37(1): 41-59. doi: 10.1080/00401706.1995.10485888 [7] DUNIA R, JOE QIN S. Subspace approach to multidimensional fault identification and reconstruction[J]. AIChE Journal, 1998, 44(8): 1813-1831. doi: 10.1002/aic.690440812 [8] 李楠, 张云燕, 李言俊. 一种自旋稳定卫星姿态传感器数据异常的诊断方法[J]. 宇航学报, 2011, 32(6): 1327-1332. doi: 10.3873/j.issn.1000-1328.2011.06.019LI N, ZHANG Y Y, LI Y J. A diagnosis algorithm for abnormal data of spin-stabilized satellite attitude sensors[J]. Journal of Astronautics, 2011, 32(6): 1327-1332(in Chinese). doi: 10.3873/j.issn.1000-1328.2011.06.019 [9] LI Z Z, LIU G H, ZHANG R, et al. Fault detection, identification and reconstruction for gyroscope in satellite based on independent component analysis[J]. Acta Astronautica, 2011, 68(7-8): 1015-1023. doi: 10.1016/j.actaastro.2010.09.010 [10] 龚学兵, 王日新, 徐敏强. 飞轮传感器的高斯混合模型故障检测方法[J]. 宇航学报, 2015, 36(6): 699-705.GONG X B, WANG R X, XU M Q. Gaussian mixed model-based fault detection method for flywheel sensor[J]. Journal of Astronautics, 2015, 36(6): 699-705(in Chinese). [11] 龚学兵. 基于数据驱动方法的飞轮系统早期故障检测[D]. 哈尔滨 : 哈尔滨工业大学, 2017 : 42-28.GONG X B. Early fault detection of flywheel system based on data driven method[D]. Harbin : Harbin Institute of Technology, 2017 : 42-48(in Chinese). [12] INUI M, KAWAHARA Y, GOTO K, et al. Adaptive limit checking for spacecraft telemetry data using kernel principal component analysis[J]. Transactions of the Japan Society for Aeronautical and Space Sciences, Space Technology Japan, 2009, 7(26): 11-16. [13] FUJIMAKI R, YAIRI T, MACHIDA K. An approach to spacecraft anomaly detection problem using kernel feature space[C]//Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining. New York: ACM, 2005: 401-410. [14] YAIRI T, TAKEISHI N, ODA T, et al. A data-driven health monitoring method for satellite housekeeping data based on probabilistic clustering and dimensionality reduction[J]. IEEE Transactions on Aerospace and Electronic Systems, 2017, 53(3): 1384-1401. doi: 10.1109/TAES.2017.2671247 [15] 王大轶, 屠园园, 符方舟, 等. 航天器控制系统的自主诊断重构技术[J]. 控制理论与应用, 2019, 36(12): 1966-1978.WANG D Y, TU Y Y, FU F Z, et al. Autonomous diagnosis and reconfiguration technology of spacecraft control system[J]. Control Theory & Applications, 2019, 36(12): 1966-1978. [16] 屠善澄, 陈义庆, 严拱添, 等. 卫星姿态动力学与控制[M]. 北京: 中国宇航出版社, 1999: 192-193.TU S C, CHEN Y Q, YANG G T, et al. Satellite attitude dynamics and control[M]. Beijing: China Astronautic Publishing House, 1999: 192-193(in Chinese). [17] 马星宇. 基于反作用飞轮和磁力矩器的卫星姿态控制系统研究[D]. 哈尔滨: 哈尔滨工业大学, 2013: 23-25.MA X Y. Study on the attitude control system of satellite with reaction wheels and magnetotors[D]. Harbin: Harbin Institute of Technology, 2013: 23-25(in Chinese). [18] BIALKE B. High fidelity mathematical modeling of reaction wheel performance[J]. Advances in the Astronautical Science, 1998(98): 483-496. [19] 金磊, 徐世杰. 基于扩张状态观测器的飞轮故障检测与恢复[J]. 北京航空航天大学学报, 2008, 34(11): 1272-1275. doi: 10.13700/j.bh.1001-5965.2008.11.013JIN L, XU S J. Extended state observer-based fault detection and recovery for flywheels[J]. Journal of Beijing University of Aeronautics and Astronautics, 2008, 34(11): 1272-1275(in Chinese). doi: 10.13700/j.bh.1001-5965.2008.11.013 [20] 谭春林, 胡太彬, 王大鹏, 等. 国外航天器在轨故障统计与分析[J]. 航天器工程, 2011, 20(4): 130-136. doi: 10.3969/j.issn.1673-8748.2011.04.029TAN C L, HU T B, WANG D P, et al. Analysis on foreign spacecraft in-orbit failures[J]. Spacecraft Engineering, 2011, 20(4): 130-136(in Chinese). doi: 10.3969/j.issn.1673-8748.2011.04.029 [21] KU W F, STORER R H, GEORGAKIS C. Disturbance detection and isolation by dynamic principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1995, 30(1): 179-196. doi: 10.1016/0169-7439(95)00076-3 [22] YUE H H, QIN S J. Reconstruction-based fault identification using a combined index[J]. Industrial & Engineering Chemistry Research, 2001, 40(20): 4403-4414. [23] FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2005, 27(8): 861-874. [24] RAKOTOMAMONJY A. Variable selection using SVM-based criteria[J]. Journal of Machine Learning Research, 2003, 3: 1357-1370. [25] 李智. 基于主元分析的故障诊断方法研究及应用[D]. 沈阳: 东北大学, 2012 : 44-46.LI Z. Research of fault diagnosis method based on principle component analysis and application[D]. Shenyang: Northeastern Univerisity, 2012 : 44-46(in Chinese). [26] 袁泉, 何英姿, 邢琰, 等. 基于线性最小均方差估计的星敏感器故障诊断[J]. 空间控制技术与应用, 2013, 39(2): 30-35. doi: 10.3969/j.issn.1674-1579.2013.02.006YUAN Q, HE Y Z, XING Y, et al. Fault diagnosis for sensors based on linear minimum mean square filter[J]. Aerospace Control and Application, 2013, 39(2): 30-35(in Chinese). doi: 10.3969/j.issn.1674-1579.2013.02.006 [27] KALMAN R E. A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering, 1960, 82(1): 35-45. doi: 10.1115/1.3662552