School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China.
School of Automation, Guangdong University of Petrochemical Technology, Maoming 525000, China.
Sensors (Basel). 2022 Feb 10;22(4):1343. doi: 10.3390/s22041343.
In order to improve the performance of the Kalman filter for nonlinear systems, this paper contains the advantages of UKF statistical sampling and EnKF random sampling, respectively, and establishes a new design method of sampling a driven Kalman filter in order to overcome the shortcomings of UKF and EnKF. Firstly, a new sampling mechanism is proposed. Based on sigma sampling with UKF statistical constraints, random sampling similar to EnKF is carried out around each sampling point, so as to obtain a large sample data ensemble that can better describe the characteristics of the system variables to be evaluated. Secondly, by analyzing the spatial distribution characteristics of the obtained large sample ensemble, a sample weight selection and assignment mechanism with the centroid of the data ensemble as the optimization goal are established. Thirdly, a new Kalman filter driven by large data sample ensemble is established. Finally, the effectiveness of the new filter is verified by computer numerical simulation experiments.
为了提高非线性系统卡尔曼滤波器的性能，本文分别结合了 UKF 的统计采样和 EnKF 的随机采样的优点，建立了一种新的驱动卡尔曼滤波器的采样设计方法，以克服 UKF 和 EnKF 的缺点。首先，提出了一种新的采样机制。基于 UKF 统计约束的 sigma 采样，在每个采样点周围进行类似于 EnKF 的随机采样，从而获得可以更好地描述待评估系统变量特征的大样本数据集。其次，通过分析所获得的大样本数据集的空间分布特征，建立了一种以数据集合的质心为优化目标的样本权重选择和分配机制。第三，建立了一种新的基于大数据样本集合的卡尔曼滤波器。最后，通过计算机数值模拟实验验证了新滤波器的有效性。
