遗传算法和神经网络在低空声目标识别中的应用研究

英文篇名：The Study on the Application of Genetic Algorithm and Neural Network in Low Altitude Acoustic Target Identification
中文刊名：弹箭与制导学报
英文刊名：Journal of Projectiles ; Rockets ; Missiles and Guidance
作者：刘辉 ; 杨俊安 ; 许学忠
英文作者：LIU Hui1 ; 2 ; YANG Junan1 ; 2 ; XU Xuezhong3(1 Anhui Electronic Engineering Institute of PLA ; Hefei 230037 ; China ; 2 Anhui Key Laboratory of Electronic Restriction ; Hefei 230037 ; China ; 3 Northwest Institute of Nuclear Technology ; Xi'an 710613 ; China)
中文关键词：神经网络 ; BP算法 ; 遗传算法 ; 声目标识别
英文关键词：neural network ; BP algorithm ; genetic algorithm ; acoustic target recognition
出版日期：2008-10-15
机构：解放军电子工程学院;安徽省电子制约技术重点实验室;西北核技术研究所;
年：2008
期：05
出版单位：弹箭与制导学报

摘要

将神经网络应用于战场声目标分类,针对BP算法易陷入局部极小、收敛速度慢的缺点,利用遗传算法具有全局寻优的特点,将二者结合起来,提出一种训练神经网络的混合算法GA-BP算法,并将其应用于低空飞行目标的声识别。仿真结果表明该算法具有较高的识别概率和较好的鲁棒性。
When the neural network is applied to low altitude passive acoustic target identification,BP algorithm has a low speed of convergence and is usually plunged into local optimum easily.According to the advantage of the globe searching property of genetic algorithm,a novel algorithm combining BP algorithm and genetic algorithm was proposed in this paper.The simulation results show that the proposed algorithm can be used in low altitude passive acoustic target identification effectively and reliably.

引文

[1]吕国云,许学忠,赵锐.战场目标被动噪声识别技术[J].探测与控制学报,2001,23(4):22-25.
    [2]陈国良,王煦法,庄镇泉.遗传算法及其应用[M].北京:人民邮电出版社,2001.
    [3]郭晓婷,朱岩.基于遗传算法的进化神经网络[J].清华大学学报,2000,40(10):116-119.
    [4]Skow Ronski M D,Harris J G.Increased MFCCfilter bandwidth for noise robust phoneme recogni-tion[C]//IEEE International Conference on A-coustics,Speech,and Signal Processing,2002,:801-804.
    [5]刘辉,杨俊安,许学忠.基于MFCC参数和HMM的低空目标声识别方法研究[J].弹箭与制导学报,2007,25(5):229-232.
    [6]段俊峰,李科杰,张中民,等.基于神经网络的战场被动声/地震动目标识别方法[J].探测与控制学报,2001,23(3):25-27.