基于正交性原理的组合导航系统故障检测

Fault Detection of Integrated Navigation System Based on Orthogonality Principle

针对传统故障检测算法对组合导航系统的缓变故障检测效率不高的问题,提出了一种基于正交性原理的故障检测算法。无故障时,卡尔曼滤波相邻残差满足正交关系,残差正交值为零均值的白噪声序列;有故障时,相邻残差高度相关,残差正交值不满足零均值条件。综上所述,以残差正交值为基础,构建卡方检验算法以实现对故障的检测。残差正交值的特殊结构使其对故障较敏感。实验结果表明,该算法对缓变故障的检测效果优于残差卡方检验算法和渐消序贯概率比检验(sequential probability ratio test,SPRT)算法,提高了组合导航系统的估计精度与可靠性。

To solve the problem that traditional fault detection algorithms are not efficient in detecting slowly changing faults in integrated navigation systems,a fault detection algorithm based on the orthogonality principle is proposed.When there is no fault,the adjacent residuals of the Kalman filter satisfy the orthogonal relationship,and the residual orthogonal value is a white noise sequence with zero mean.When there is a fault,the adjacent residuals are highly correlated,and the residual orthogonal value does not meet the zero mean condition.To sum up,based on the residual orthogonal value,a chi-square test algorithm is constructed to detect faults.The special structure of the residual orthogonal value makes it sensitive to faults.The experimental results show that the algorithm is better than the residual chi-square test algorithm and the fading sequential probability ratio test(SPRT)algorithm in detecting slowly changing faults,which improves the estimation accuracy and reliability of the integrated navigation system.