摘要
主要对不确定性环境下的空中目标威胁评估问题进行研究。首先通过模糊神经网络处理信息不确定问题,在获取威胁目标信息较少的环境下,使用小波神经网络增强网络自学习能力,并分析威胁因素,创建不确定性环境下的模糊小波神经网络(FWNN),实现对目标威胁的评估;然后针对初始参数的不确定性问题,采用粒子群优化算法和BP算法更新每个模糊规则后件部分的参数,以达到提高评估效果的目的。仿真结果表明,与模糊小波神经网络相比,该算法提高系统的稳定性,加快收敛速度,增强预测精度。
This paper focuses on threat assessment of aerial target under uncertain environment. First, the problem of uncertain information is solved by using fuzzy neural networks. In the environment with less threat target information, the wavelet neural network is used to enhance the self-learning ability of the network and the threat factors are analyzed. The Fuzzy Wavelet Neural Network( FWNN) in the uncertain environment is established to achieve the target threat evaluation. For the uncertainty of the initial parameters, the consequent parameters of each fuzzy rule are updated by using the particle swarm optimization algorithm and the BP algorithm to achieve the purpose of improving the evaluation effect. The simulation results show that:Compared with the fuzzy wavelet neural network, the stability of the system is improved, the convergence speed is accelerated, and the prediction accuracy is enhanced.
作者
陈侠
刘子龙
CHEN Xia;LIU Zi-long(Shenyang University of Aerospace,Shenyang 110136,China)
出处
《电光与控制》
CSCD
北大核心
2019年第3期30-34,111,共6页
Electronics Optics & Control
基金
国家自然科学基金(61074159)
航空科学基金(2016ZC54011)
辽宁省自然科学基金(2015020063)
关键词
目标威胁评估
粒子群算法
小波神经网络
模糊小波神经网络
BP算法
target threat assessment
particle swarm algorithm
wavelet neural network
fuzzy wavelet neural network
back-propagation algorithm
