摘要
研究卫星GNSS/INS组合导航系统故障检测问题。针对目前GNSS/INS组合导航系统故障检测方法延时大,识别和隔离故障卫星不及时的缺陷,采用"主-次"故障检测结构,提出一种新的基于最小二乘支持向量机的层次故障检测方法。利用最小二乘支持向量机的预测新息为各层次故障检测构建检测统计量,不仅可以更快地检测到系统故障,还可以及时隔离故障卫星,并采用子系统信息维持导航工作。仿真结果表明,上述方法不仅提高了导航系统的容错能力,还提高了系统故障检测的速度。
According to the problem that traditional detect GNSS/INS integrated navigation system method costs large time delay and identify fauh satellites, a hierarchical fault detection method based on least squares support vec- tor machine （LS- SVM） was proposed on the basis of the structure of ＂primary and secondary＂ fault detection. Building test statistic in hierarchical fault detection by using LS - SVM feedback value of the forecast can detect faults quickly and use subsystem information to maintain navigation work after promptly isolate fault satellites. The simula- tion result shows that this method can improve not only the ability of the fault tolerant in navigation system, but also the fault detection speed.
出处
《计算机仿真》
CSCD
北大核心
2014年第2期140-143,共4页
Computer Simulation
