论文部分内容阅读
针对出现测量死区的离散系统,提出一种基于两阶段TKF的故障估计方法。引入2个Bernoulli随机向量描述输出死区,并设计了增广状态Tobit卡尔曼滤波器(augmented state Tobit Kalman filter,ASTKF)。通过两步U-V变换方法对ASTKF的协方差矩阵解耦,从而获得两阶段Tobit卡尔曼滤波器(two-stage Tobit Kalman filter,TSTKF),并且利用TSTKF解决了系统故障估计问题。对所提出方法进行仿真,并与标准卡尔曼滤波器、间歇观测下的卡尔曼滤波器进行比较,说明了该方法的可行性和准确性。
Aiming at the discrete system with measurement dead zone, a fault estimation method based on two-stage TKF is proposed. Two Bernoulli random vectors are introduced to describe the output dead zone and an augmented state Tobit Kalman filter (ASTKF) is designed. A two-stage Tobit Kalman filter (TSTKF) is obtained by decoupling the ASTKF covariance matrix by a two-step U-V transform method. The system fault estimation problem is solved by using TSTKF. The proposed method is simulated and compared with the standard Kalman filter and the Kalman filter under intermittent observation. The feasibility and accuracy of the proposed method are demonstrated.