基于自注意力层的神经网络弹道落点预测方法  

Neural Network Ballistic Landing Point Prediction Method Based on Self-attention Layer

作　　者：马月红 曹彦敏 李超旺 赵辰 周辉 赵慧亮 王晓成 李乾 MA Yuehong;CAO Yanmin;LI Chaowang;ZHAO Chen;ZHOU Hui;ZHAO Huiliang;WANG Xiaocheng;LI Qian(Hebei Provincial Collaborative Innovation Center of Transportation Power Grid Intelligent Integration Technology and Equipment,Shijiazhuang Tiedao University,Shijiazhuang 050043,Hebei,China;School of Electrical and Electronic Engineering,Shijiazhuang Tiedao University,Shijiazhuang 050043,Hebei,China;Shijiazhuang Campus,Army Engineering University,Shijiazhuang 050005,Hebei,China;Shijiazhuang Power Supply Branch of State Grid Hebei Electric Power Co.,Ltd.,Shijiazhuang 050051,Hebei,China)

机构地区：[1]石家庄铁道大学河北省交通电力网智能融合技术与装备协同创新中心,河北石家庄050043 [2]石家庄铁道大学电气与电子工程学院,河北石家庄050043 [3]陆军工程大学石家庄校区,河北石家庄050005 [4]国网河北省电力有限公司石家庄供电分公司,河北石家庄050051

出　　处：《弹箭与制导学报》2025年第1期53-61,共9页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：河北省重点研发计划项目(21350701D)。

摘　　要：针对现有的弹道落点预测方法误差大和气象变化适应不足的问题,建立了包含气象条件的弹道数据集,并提出了一种基于自注意力层的CNN-BiLSTM-BiGRU弹道落点预测方法。在所构建的组合模型中引入自注意力层和残差连接,加强模型在处理输入序列时动态关注不同时刻信息的能力,缓解网络中的梯度爆炸问题。采用多维时间序列数据的输入表示方法,结合历史弹道轨迹数据和目标特征等信息,减小弹道落点预测误差。仿真结果表明,基于自注意力层的CNN-BiLSTM-BiGRU网络模型的预测效果优于其他模型,射程预测的最大误差占真实值的0.156%,横偏预测的最大误差占真实值的5.904%。文中研究为弹道落点预测领域提供了重要的参考依据。Aiming at the problems of large errors and insufficient adaptation to meteorological changes in existing ballistic drop prediction methods,a ballistic dataset containing meteorological conditions is established and a CNN-BiLSTM-BiGRU ballistic drop prediction method based on a self-attention layer is proposed in this paper.The self-attention layer and residual connection are introduced into the constructed combined model to strengthen the model′s ability to dynamically focus on the information at different moments when processing the input sequences,and to alleviate problems such as gradient explosion in the network.It also uses the input representation of multi-dimensional time series data to reduce the ballistic drop prediction error by combining multiple information such as historical ballistic trajectory data and target characteristics.The simulation results show that the prediction effect of the CNN-BiLSTM-BiGRU network model based on the self-attention layer is better than the other models,and the maximum error of the range prediction accounts for 0.156%of the true value,and the maximum error of the lateral deviation prediction accounts for 5.904%as of the true value.The method provides an important reference for the field of ballistic drop prediction.

关 键 词：弹道落点预测 深度学习 弹道模型 自注意力层 卷积神经网络 长短期记忆网络 门控循环神经网络 

分 类 号：TJ012.3[兵器科学与技术—兵器发射理论与技术]