摘要
针对传统空中目标意图估计方法大多依赖专家经验,仅考虑单时刻目标属性,导致意图估计结果不可靠、准确度较差的问题,提出基于改进灰色神经网络(IFOA-GNNM)的空中目标意图估计模型。该模型采用改进后的果蝇算法优化灰色神经网络挖掘空中目标多时刻属性的变化趋势与意图之间的隐含规则实现对空中目标的意图估计。仿真实验结果表明,该模型在对空中目标的意图的估计中有着更强的可靠性和更高的准确性。
Traditional air targets intention estimation methods mostly rely on expert knowledge or experience,and only consider the attribute of single time target,which makes the result of intention estimation unreliable and inaccurate.To solve the above problems,an air target intention estimation model based on improved grey neural network(IFOAGNNM)was proposed.In this model,the improved fruit fly algorithm was used to optimize the grey neural network to mine the implicit rules between the changing trend of multi time attributes and intention of air targets,so as to realize the intention estimation of air targets.Simulation results showed that the model had stronger reliability and higher accuracy in the estimation of air target intention.
作者
于果
王肖霞
吉琳娜
杨风暴
YU Guo;WANG Xiaoxia;JI Linna;YANG Fengbao(School of Information and Communication Engineering, The North University of China, Taiyuan 030051, China)
出处
《探测与控制学报》
CSCD
北大核心
2021年第5期106-112,共7页
Journal of Detection & Control