基于NARX神经网络的火箭炮发火回路状态预测研究  

State Forecasting Research of Rocket Launcher Firing Circuit Based on NARX Neural Network

作　　者：王小召 张建新 张震 李永保 李锋 谢立中 WANG Xiaozhao;ZHANG Jianxin;ZHANG Zhen;LI Yongbao;LI Feng;XIE Lizhong(Hubei Jiangshan Heavy Industry Co.,Ltd.,Hubei Xiangyang 441005,China)

机构地区：[1]湖北江山重工有限责任公司,湖北襄阳441005

出　　处：《弹箭与制导学报》2021年第3期21-24,30,共5页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：装备预研兵器工业联合基金(6141B012102)资助。

摘　　要：由于服役环境变化剧烈和影响因素复杂,火箭炮状态变化具有非平稳、非线性的特点,为更准确对其进行预测,提出将模糊综合评判法和NARX神经网络相结合的方法,以某型火箭炮发火回路为例进行状态预测实验。结果表明,经过对影响因素进行模糊综合评分,NARX神经网络的规模减小且收敛速度提高,对火箭炮状态变化趋势的预测也更加精确。The state change of the rocket launcher is non-stationary and non-linear.In order to predict the state of rocket launchers more accurately,this paper proposes a prediction method combining fuzzy comprehensive evaluation method and NARX neural network.Taking the firing circuit of a certain type rocket launcher as an example,the prediction experiment shows that after fuzzy comprehensive evaluation of the influencing factors,the NARX neural network converges faster during training and predicts the state change trend of the rocket launcher more accurately.

关 键 词：火箭炮 状态预测 NARX 神经网络 模糊综合评判 发火回路 

分 类 号：TJ393[兵器科学与技术—火炮、自动武器与弹药工程] TJ713