摘要
为了提升雷达的跟踪性能,针对雷达多目标跟踪时传统跟踪任务优先级设计方法无法保证对重要目标跟踪的问题,提出了一种基于BP神经网络的跟踪任务优先级设计方法。方法利用目标参数以及雷达性能参数直接对目标的跟踪任务优先级进行综合评判,并采用BP神经网络对参数和跟踪任务优先级之间进行函数关系逼近,实现对优先级的快速实时设计。最后将该方法与基于模糊逻辑的跟踪任务优先级设计方法进行对比仿真,仿真结果证明了上述方法的有效性和优越性。
In order to improve the tracking performance of radar, aim at the problem that the traditional method of tracking task priority designing cannot ensure that radar always tracks important targets under multi -target tracking, a method based on the BP neural network model is given in the paper. The method used the target parameters and the performance parameter of radar to comprehensively judge the priority of the target tracking task directly, and adopted BP neural network to realize the function approximate between the parameters and tracking task priority, and to real- ize rapid real - time design of tracking task priority. Finally, compared with the method based on the fuzzy logic, the method in this paper was simulated. The analysis resuh proves the effectiveness and superiority of the method.
出处
《计算机仿真》
北大核心
2017年第8期27-32,共6页
Computer Simulation
基金
国家自然科学基金(61601499)