摘要
针对地面防空作战中目标威胁度难以准确评估的问题,提出了基于改进Elman神经网络的目标威胁度动态预测评估方法。该方法利用量子粒子群智能优化(QPSO)算法对Elman神经网络进行了改进,提出了QPSO-Elman神经网络,并基于优化的QPSO-Elman神经网络构建了目标威胁度的动态预测评估模型。仿真分析表明,该方法有效解决了目标威胁度的动态评估问题,预测结果更加准确且实用性强,增强了防空系统的作战能力。
Aiming at the problem that target threat is hard to assess in ground air defense operation, a method of target threat assessment was proposed based on the improved Elman neural network The Elman neural net-work was improved based on the quantum particle swarm optimization （QPSQ） , and the QPSO-Elman neural network was proposed. Besides,a assessment model was proposed based on QPSO-Elman neural network The simulation results showed that this method could effectively solved the problem, the prediction results were more accurate and practicable, and it could enhance the operational capability of the air defense system.
出处
《探测与控制学报》
CSCD
北大核心
2017年第3期101-106,共6页
Journal of Detection & Control
基金
军内科研基金重点项目资助(ZS2015070132A12009)
关键词
目标威胁度
ELMAN神经网络
量子粒子群优化算法
防空作战
target threat assessment
Elman neural network
quantum particle swarm optimization
air defense operation
