论述了带反馈分布式信息融合系统中传感器观测维数不同时的状态估计方法。
The method of state estimation is discussed, when radars have different observation dimension in one distributed data fusion system with feedback.
逐次正交化分布式卡尔曼滤波器是对大系统进行状态估计的一种新方法。
The Successive Orthogonalization Decentralized Kalman Filter (SODKF ) is a new method which is used for large system state estimation.
由于扩展卡尔曼滤波必须假定噪声服从高斯分布，若用于复杂非线性系统，其估计精度不甚理想。粒子滤波对噪声类型没有限制，正在成为非线性系统状态估计的有效近似方法。
Because EKF must assume that the noise is subject to Gaussian distribution, the estimate accuracy is not so good if it is used to estimate the state of complicated nonlinear system.
在算法的状态估计阶段，采用混合系统粒子滤波和二元估计算法同时估计对象系统故障演化模型混合状态和未知参数的后验分布。
For state estimation of hybrid system with unknown transition probabilities, an adaptive estimation algorithm is proposed based on Monte Carlo particle filtering.
在算法的状态估计阶段，采用混合系统粒子滤波和二元估计算法同时估计对象系统故障演化模型混合状态和未知参数的后验分布。
For state estimation of hybrid system with unknown transition probabilities, an adaptive estimation algorithm is proposed based on Monte Carlo particle filtering.
应用推荐