摘要
为拓展雷达网效能评估的内容、改进评估方法和提高评估效率,重构了雷达网效能评估指标体系,给出了各指标的量化模型和方法;针对BP神经网络收敛速度慢、局部极小化问题,提出了利用遗传算法(GA)优化BP神经网络的方法,并采用GA+BP神经网络模型对雷达网部署方案进行了评估优选.仿真结果表明,运用GA算法改进的BP神经网络具有更快的收敛速度和更高的预测精度,可作为雷达网效能量化评估的有效手段,为雷达兵作战筹划提供科学决策依据.
In order to expand the content of radar network effectiveness evaluation and improve the evaluation methods and efficiency, this paper restructures the index system of radar network effectiveness evaluation, and provides the quantitative models and methods of each index. And then the paper proposes that BP neural network is optimized by using genetic algorithm (GA) method to solve BP neural network’s slow convergence speed and local optimum. Finally the paper adopts GA+BP neural network model to evaluate and optimize the deployment scheme of radar network. The simulation results show that the BP neural network improved by GA algorithm has faster convergence speed and higher prediction accuracy, and can be used as an effective means to evaluate the effectiveness of radar network, thus providing a scientific decision-making basis for the operational planning of radar troops.
作者
郑国杰
任吉
李泽鹏
ZHENG Guojie;REN Ji;LI Zepeng(Air Force EarlyWarning Academy,Wuhan 430019, China;No.95786 Unit, the PLA, Chengdu 621000, China;No.93498 Unit, the PLA, Shijiazhuang 051000, China)
出处
《空军预警学院学报》
2019年第2期116-120,共5页
Journal of Air Force Early Warning Academy
关键词
BP神经网络
遗传算法
雷达网
效能评估
BP neural network
genetic algorithm (GA)
radar network
effectiveness evaluation
