基于神经网络的认知雷达目标优先级综合评价方法  

A cognitive radar target priority comprehensive evaluation method based on neural network

作　　者：冯伟业 廖可非 欧阳缮[1] 牛耀 FENG Weiye;LIAO Kefei;OUYANG Shan;NIU Yao(School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《现代电子技术》2020年第9期62-66,70,共6页Modern Electronics Technique

基　　金：国家自然科学基金资助项目(61631019);国家自然科学基金资助项目(61701128);国家自然科学基金资助项目(61871425);广西自然科学基金资助项目(2017GXNSFBA198032);中国博士后科学基金资助项目(2017M623298XB)。

摘　　要：为了解决认知雷达资源自适应调度中评价指标和评价方法单一而导致主、客观评价不一致的问题,根据空中目标威胁度以及目标图像质量,提出一种基于神经网络的认知雷达目标优先级综合评价方法,为认知雷达资源调度系统提供准确的调度依据。该方法首先建立目标的威胁度和成像质量的评价指标体系,然后采用BP神经网络和自组织特征映射(SOFM)神经网络对目标的优先级进行综合评价。仿真结果表明,该方法能够对多个目标的优先级进行客观、准确的评价。In order to solve the problems of inconsistent subjective and objective evaluation due to single evaluation index and evaluation method in the adaptive scheduling of cognitive radar resource,a cognitive radar target priority comprehensive evaluation method based on neural networks is proposed according to threat degree and image quality of aerial targets,which provides accurate scheduling basis for the cognitive radar resource scheduling system. In this method,an evaluation index system of target threat degree and imaging quality is established firstly,and then the target priority is comprehensively evaluated with BP(Back Propagation) neural network and SOFM(Self Organizing Feature Map) neural network. The simulation results show that the priority sequence of multiple targets can be objectively and accurately evaluated with this method.

关 键 词：优先级综合评价 认知雷达目标 资源调度系统 评价模型建立 评价方法 目标成像图分析 

分 类 号：TN956-34[电子电信—信号与信息处理]