数据关联的神经—模糊融合方法

Neural-Fuzzy Fusion Solution to the Data Association Problem

本文提出了基于神经—模糊融合网络的数据关联新方法，解决了杂波背景下多目标数据关联的实际问题。首先为分级实现数据关联和降低关联模糊度，在文献［１］的基础上构造了多目标快速数据关联的系统结构。然后应用神经—模糊融合技术和改进的模糊基函数网络学习算法完成相关值的计算。该方法在地波超视距达站应用结果表明，这种方法提高了数据关联的性能和快速性，并为强海杂波背景下多目标跟踪提供了一种新的方法。

In this paper,we propose a new data association algorithm based on neural-fuzzy fusion networks,to solve the problems in the practical application of multitarget data association in clutter. Firstly,we present a system structure for the fast multi target data association ,which results in realizing the data association in series and reducing the fuzziness of association.Secondly,we apply the neural-fuzzy fusion technology and the modified fuzzy basic function networks in the computing of correlation.Finally,the results of its application in the Ground Wave Over-The-Horizon Radar prove that this fast algorithm,have improved the performances of the multitarget data association in the rough sea clutter.