基于多因素模糊判决的多模型机动目标跟踪

发布时间：2018-06-01 05:43

  本文选题：机动目标跟踪 + 变结构多模型方法　； 参考：《哈尔滨工程大学学报》2014年05期

【摘要】：为提高非线性复杂系统状态估计的效率与精度,提出一种基于多因素模糊综合评判的变结构多模型方法(MFIE_MM)。MFIE_MM首先确定模型全集并提取各个模型的公共因素,进而选择模糊综合鉴别函数构建模糊评价集合;其次单因素模糊评判矩阵和多因素模糊评判准则得到各个模型的相似度;最后选出当前时刻最佳模型并以此模型为区域中心实时生成参与状态估计的模型集合。仿真结果显示,由MFIE_MM处理得到的位置变量估计误差协方差从2.15 m降到2.05 m,单拍处理时间从0.002 7 s降到0.001 8 s。因此,MFIE_MM在显著提高算法精度的同时有效降低了算法运行时间和模型平均误差。
[Abstract]:In order to improve the efficiency and accuracy of state estimation for nonlinear complex systems, a variable structure multi-model method based on multi-factor fuzzy comprehensive evaluation is proposed. Firstly, MFIEMM. MFIEMM is used to determine the complete set of models and to extract the common factors of each model. Then the fuzzy comprehensive discriminant function is selected to construct the fuzzy evaluation set. Secondly, the similarity of each model is obtained by the single factor fuzzy evaluation matrix and the multi-factor fuzzy evaluation criterion. Finally, the optimal model of the current time is selected and the model is used as the center of the region to generate the model set of participating state estimation in real time. The simulation results show that the estimated error covariance of the position variables processed by MFIE_MM is reduced from 2.15m to 2.05m, and the time of single beat processing is reduced from 0.002 s to 0.001 8s. So MFIEMM can significantly improve the accuracy of the algorithm and reduce the running time of the algorithm and the average error of the model.
【作者单位】： 华北水利水电大学信息工程系;哈尔滨工程大学信息与通信工程学院;
【基金】：国家自然科学基金资助项目(61240007) 博士后科研启动基金资助项目(LBH-Q12122)
【分类号】：TN953

【参考文献】

中国期刊全文数据库 前5条

1 林长川;孙腾达;洪爰助;黄丽卿;东f ;;雷达与AIS目标航迹模糊关联算法与仿真[J];系统仿真学报;2006年S2期

2 刘三阳;杜U，

本文编号：1963059