CAJ | 학술논문

对于带自回归滑动平均(ARMA)有色观测噪声的多传感器广义离散随机线性系统,应用奇异值分解,提出了广义系统多传感器信息融合状态平滑问题.基_丁:Kalman滤波方法,在线性最小方差信息融合准则下,给出了按矩阵加权融合降阶稳态广义Kalman平滑器.为了计算最优加权,提出了局部平滑误差协方差阵的计算公式.一个Monte Carlo仿真例子说明了所提方法的有效性.
대우대자회귀활동평균(ARMA)유색관측조성적다전감기엄의리산수궤선성계통,응용기이치분해,제출료엄의계통다전감기신식융합상태평활문제.기_정:Kalman려파방법,재선성최소방차신식융합준칙하,급출료안구진가권융합강계은태엄의Kalman평활기.위료계산최우가권,제출료국부평활오차협방차진적계산공식.일개Monte Carlo방진례자설명료소제방법적유효성.
For multisensor descriptor discrete-time stochastic linear systems with autore-gressive moving average(ARMA) colored observation noises, by using the singular value decomposition, the problem of multi-sensor information fusion state smooth is presented. Based on Kalman filtering method, a reduced order steady-state descriptor Kalman smoother weighted by matrices is proposed under the linear minimum variance information fusion criterion. In order to compute the optimal weights, the formulae of computing the covariance matrices among local smoothing errors are presented. A Monte Carlo simulation example shows the proposed method's effectiveness.