在四轴冗余配置的惯导系统陀螺组件中，为了解决基于等价空间原理的诊断算法无法分离故障器件的问题，保证惯导系统陀螺组件的容错性能，提出一种基于支持向量机辅助的两级故障诊断方法.首先，以奇偶残差构建卡方检测量，采用广义似然比法对四轴陀螺组件进行实时的故障检测；然后，构建基于小波包变换与支持向量机的故障分类器，分析陀螺器件输出信号的能量特征，对传感器的运行状态进行判定；最后，结合广义似然比法的检测结果与故障分类器的输出，对四轴陀螺组件的故障进行判别，诊断系统故障源.仿真结果表明：所提方法能够快速准确地识别故障器件；在最小冗余配置条件下，保证了惯性系统陀螺组件一次故障正常工作的容错能力.
Aiming at the problem that the traditional parity space method cannot identify fault component in a gyro-quadruplet of the inertial navigation system, a two-level fault diagnosis method assisted by a support vector machine is proposed to ensure fault tolerance of the gyro module. The generalized likelihood ratio method, whose chi-square volume is constructed by parity residuals, is used for real-time fault detection of the four-axis gyro module. Then, a fault classifier composed of a wavelet packet transform and a support vector machine is constructed to analyze the energy characteristics of gyro output and determinate the operating state of gyro component. Finally, combining the detection results of the generalized likelihood ratio method with the output of the fault classifier, the fault source in the gyro module is detected and isolated. The simulation results show that the proposed method can quickly and accurately identify the faulty device, and thus ensure the performance of the gyro module under a minimum redundancy configuration.
［1］LI S N, MEI J S, QU Q, et al. Research on SINS/GPS/CNS fault-tolerant integrated navigation system with air data system assistance［C］∥2016 IEEE Chinese Guidance, Navigation and Control Conference. Nanjing, China: IEEE, 2016: 2366-2370.
［2］吴有龙, 王晓鸣, 曹鹏, 等. 一种改进的故障检测算法在组合导航中的应用［J］. 北京理工大学学报, 2015, 35(5): 494-499.
WU Youlong, WANG Xiaoming, CAO Peng, et al. A novel fault detection algorithm for integrated navigation system［J］. Transactions of Beijing Institute of Technology, 2015, 35(5): 494-499.
［3］陈帅, 蒋长辉, 付梦印, 等. 一种GNSS/SINS容错深组合导航系统设计［J］. 中国惯性技术学报, 2017, 25(1): 77-80.
CHEN Shuai, JIANG Changhui, FU Mengyin, et al. Design of fault-tolerant GNSS/SINS deep-integration system［J］. Journal of Chinese Inertial Technology, 2017, 25(1): 77-80.
［4］CALL C, IBIS M, MCDONALD J, et al. Performance of honeywell’s inertial/GPS hybrid (HIGH) for RNP operations［C］∥2006 IEEE/ION Position, Location, and Navigation Symposium. Coronado, CA, USA: IEEE, 2006: 244-255.
［5］张闯, 赵修斌, 庞春雷, 等. GNSS/SINS紧组合导航故障检测与系统重构新方法［J］. 电光与控制, 2017, 24(2): 100-104.
ZHANG Chuang, ZHAO Xiubin, PANG Chunlei, et al. A fault detection and system reconstruction method for GNSS/SINS tightly-coupled system［J］. Electronics Optics & Control, 2017, 24(2): 100-104.
［6］耿峰, 祝小平, 周洲. 一种有效的组合导航容错滤波技术研究［J］. 西北工业大学学报, 2016, 34(3): 449-455.
GENG Feng, ZHU Xiaoping, ZHOU Zhou. Research on an effective integrated navigation failure-tolerance filtering technology［J］. Journal of Northwestern Polytechnical University, 2016, 34(3): 449-455.
［7］武唯强, 任子君, 张通, 等. 改进的四陀螺冗余捷联惯组故障诊断与隔离方法［J］. 指挥控制与仿真, 2015, 37(1): 128-131.
WU Weiqiang, REN Zijun, ZHANG Tong, et al. Improved FDI method for a gyro-quadruplet［J］. Command Control & Simulation, 2015, 37(1): 128-131.
［8］CHENG J H, SUN X Y, CHEN D D, et al. Multi-fault detection and isolation for redundant strapdown inertial navigation system［C］∥2018 IEEE/ION Position, Location and Navigation Symposium. Monterey, CA, USA: IEEE, 2018: 17823365.
［9］WIDODO A, YANG B S. Support vector machine in machine condition monitoring and fault diagnosis［J］. Mechanical Systems and Signal Processing, 2007, 21(6): 2560-2574.
［10］WEI C H, TANG W H, WU Q H. A hybrid least-square support vector machine approach to incipient fault detection for oil-immersed power transformer［J］. Electric Power Components and Systems, 2014, 42(5): 453-463.
［11］柳敏, 赖际舟, 刘建业, 等. 基于SVR的惯性/卫星组合导航系统故障诊断方法［J］. 控制与决策, 2016, 31(10): 1889-1893.
LIU Min, LAI Jizhou, LIU Jianye, et al. Fault diagnosis method of integrated GPS/Inertial navigation system based on support vector regression［J］. Control and Decision, 2016, 31(10): 1889-1893.
［12］ZHONG L N, LIU J Y, LI R B, et al. Approach for detecting soft faults in GPS/INS integrated navigation based on LS-SVM and AIME［J］. Journal of Navigation, 2017, 70(3): 561-579.
［13］XIAO X, SHI C, YANG Y, et al. An adaptive INS/GPS/VPS federal Kalman filter for UAV based on SVM［C］∥2017 13th IEEE Conference on Automation Science and Engineering. Xi’an, China: IEEE, 2017: 1651-1656.
［14］李勇. 基于增量式模糊支持向量机的陀螺仪故障诊断［D］. 南京: 南京航空航天大学, 2015.
LI Yong. Fault diagnosis for gyroscope based on incremental fuzzy support vector machine［D］. Nanjing: Nanjing University of Aeronautics and Astronautics, 2015.
