This paper proposes a fault detection and isolation strategy that integrates robust observers and support vector ma-chines (SVM) to address the problem of multiple faults in spacecraft attitude control systems in complex space environ-ments. Firstly, a robust observer constructed based on a physical model is compared with system dynamics to generate residuals. A trained neural network is used to design dynamic thresholds and compare them with residuals for fault detec-tion. Then, combining the residual signals generated by the observer with the system's input and output, SVM is used to classify and detect multiple fault types from the data. Through the dual drive strategy of physical model and data fusion, typical single faults, dual faults, and triple faults can be classified and identified, improving the accuracy of fault detection and classification in spacecraft attitude control systems. The dynamic threshold has universality for different fault modes and can effectively improve detection performance. By comparing the static threshold and the dynamic threshold trained by neural networks through simulation, it is shown that the dynamic threshold method has improved the fault response speed and accuracy compared to the traditional static threshold method. By comparing the fault classification results of random forest and SVM, the experiment shows that the SVM classification accuracy reaches 99.26%, which is better than random forest (98.52%) and neural network (97.04%), demonstrating high performance. The conclusion shows that the proposed method effectively solves the problem of detecting and isolating high coupling faults through the fusion of observer and SVM, significantly improving system reliability.
[1] YUAN Z, SONG N, PAN X, et al. Fault detection, isolation, and reconstruction for satellite attitude sensors using an adaptive hybrid method [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-12.
[2] 袁利, 王淑一. 航天器控制系统智能健康管理技术发展综述 [J] . 航空学报,2021,42(4):116-130.
YUAN L, WANG S Y. A review on development of intelligent health management technology for spacecraft control systems [J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4):116-130.
[3] 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]. 2020,41(6):647-656.
SHEN 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..
[4] YANG R, ZHONG M. Machine learning-based fault diagnosis for industrial engineering systems [M]. CRC Press, 2022.
[5] LI A, DUAN G, LIU M, et al. Fault-tolerant quantized sliding mode observers design for a class of Takagi-Sugeno fuzzy system with unmeasurable premise variable [J]. IEEE Transactions on Fuzzy Systems, 2021, 30(7): 2312-24.
[6] NASROLAHI S S, ABDOLLAHI F. Sensor fault detection and recovery in satellite attitude control [J]. Acta Astronautica, 2018, 145: 275-83.
[7] HENRY D, BORNSCHLEGL E, OLIVE X, et al. A model-based solution for fault diagnosis of thruster faults: Application to the rendezvous phase of the Mars Sample Return mission [J]. Progress in Flight Dynamics, Guidance, Navigation, Control, Fault Detection, and Avionics, 2013, 6: 423-42.
[8] DAIGLE M, BREGON A, ROYCHOUDHURY I. Qualitative event-based diagnosis with possible conflicts applied to spacecraft power distribution systems [J]. IFAC Proceedings Volumes, 2012, 45(20): 265-70.
[9] 金洋, 王日新, 徐敏强. 基于分离策略的航天器多故障模式诊断方法 [J]. 宇航学报, 2012, 33(6):698-704.
JIN Y, WANG R X, XI M Q. A Spacecraft Autonomous Failure Diagnosis Approach for Multiple Failure-Mode System Based on Qualitative Models [J]. Journal of Astronautics, 2012, 33(6): 698-704.
[10] CHENG Y, WANG R, XU M. A combined model-based and intelligent method for small fault detection and isolation of actuators [J]. IEEE Transactions on Industrial Electronics, 2015, 63(4): 2403-13.
[11] 王振华,航天器故障诊断中的动态阈值生成与快速故障估计方法研究.黑龙江省,哈尔滨工业大学,2018-03-20.
WANG Z H, Research on Dynamic Threshold Generation and Fast Fault Estimation Method in Spacecraft Fault Diagnosis. Harbin: Harbin Institute of Technology,2018-03-20.
[12] CHEN X, YANG R, XUE Y, et al. Deep transfer learning for bearing fault diagnosis: A systematic review since 2016 [J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-21.
[13] SHAKIBA F M, SHOJAEE M, AZIZI S M, et al. Real-time sensing and fault diagnosis for transmission lines [J]. International Journal of Network Dynamics and Intelligence, 2022: 36-47.
[14] YAIRI T, KAWAHARA Y, FUJIMAKI R, et al. Telemetry-mining: a machine learning approach to anomaly detection and fault diagnosis for space systems; proceedings of the 2nd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT'06), F, 2006 [C]. IEEE.
[15] 李维铮, 孟桥. 基于遥测数据动态特征的卫星异常检测方法 [J]. 空间科学学报, 2014, 34(2):201-207.
LI W Z, MENG Q. Fault Detection for in-orbit Satellites Using an Adaptive Prediction Model [J]. Chinese Journal of Space Science, 2014, 34(2):201-207.
[16] CHEN S, YANG R, ZHONG M. Graph-based semi-supervised random forest for rotating machinery gearbox fault diagnosis [J]. Control Engineering Practice, 2021, 117: 104952.
[17] 于牧野,初未萌,符方舟,等.基于SCSO-BP神经网络的卫星姿态控制系统故障预测[J].飞控与探测, 2024, 7(1):37-46.
YU M Y,CHU W M,FU F Z,et al. Satellite Attitude Control System Fault Prediction Based on SCSO-BP Neural Network [J]. Flight Control & Detection, 2024, 7(1):37-46.
[18] YIN S, DING S X, XIE X, et al. A review on basic data-driven approaches for industrial process monitoring [J]. IEEE Transactions on Industrial electronics, 2014, 61(11): 6418-28.
[19] LI Z, MA L, KHORASANI K. Fault diagnosis of an actuator in the attitude control subsystem of a satellite using neural networks; proceedings of the 2007 International Joint Conference on Neural Networks, F, 2007 [C]. IEEE.
[20] GUO D, ZHONG M, JI H, et al. A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors [J]. Neurocomputing, 2018, 319: 155-63.
[21] CHEN S, YANG R, ZHONG M, et al. A random forest and model-based hybrid method of fault diagnosis for satellite attitude control systems [J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-13.
[22] XIONG Y, JIANG Z, FANG H, et al. Research on health condition assessment method for spacecraft power control system based on SVM and cloud model; proceedings of the 2019 Prognostics and System Health Management Conference (PHM-Paris), F, 2019 [C]. IEEE.
[23] Xiong J, Cheong J W, Xiong Z, et al. Adaptive hybrid robust filter for multi-sensor relative navigation system[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(8): 11026-11040.
[24] Li T, Zhao Z, Sun C, et al. WaveletKernelNet: An interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(4): 2302-2312.
[25] Zhong M, Liu C, Zhou D, et al. Probability analysis of fault diagnosis performance for satellite attitude control systems[J]. IEEE Transactions on Industrial Informatics, 2019, 15(11): 5867-5876.
CJA