基于AF-BiTCN的弹道中段目标HRRP识别  

HRRP recognition of midcourse ballistic targets based on AF-BiTCN

作　　者：王晓丹[1] 王鹏[1] 宋亚飞[1] 向前 李京泰 WANG Xiaodan;WANG Peng;SONG Yafei;XIANG Qian;LI Jingtai(Air and Missile Defense College,Air Force Engineering University,Xi’an 710051,China)

机构地区：[1]空军工程大学防空反导学院,西安710051

出　　处：《北京航空航天大学学报》2025年第2期349-359,共11页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(61876189,61703426,61273275);陕西省高校科协青年人才托举计划(20190108);陕西省创新人才推进计划(2020KJXX-065)。

摘　　要：针对弹道中段目标高分辨距离像(HRRP)的时序特征提取和识别问题,为充分利用弹道中段目标HRRP的双向时序信息,进一步提高识别性能,提出一种基于加性融合双向时间卷积神经网络(AF-BiTCN)的识别方法。对HRRP数据采用双向时序滑窗法处理为双向序列;构建BiTCN逐层提取HRRP的双向深层时序特征,并将双向时序特征采用加性策略融合;利用更加稳健的融合特征实现对弹道中段目标的识别,并使用Adam算法优化AF-BiTCN的收敛速度和稳定性。实验结果表明:所提的基于AF-BiTCN的弹道中段目标HRRP识别方法较堆叠选择长短期记忆网络(SLSTM)、堆叠门控循环单元(SGRU)等6种时序方法具有更高的准确率和更快的识别速度,在测试集上达到了96.60%的准确率,并且在噪声数据集上表现出更好的鲁棒性。To address the problem of temporal feature extraction and recognition of high-resolution range profiles(HRRP)of midcourse ballistic targets,a recognition method based on bidirectional temporal convolutional networks with additive fusion(AF-BiTCN)was proposed,which could make full use of the bidirectional temporal information of HRRP of midcourse ballistic targets and further improve the recognition performance.Firstly,the HRRP data was processed into a bidirectional sequence by the bidirectional sliding window algorithm.Then,the BiTCN was constructed to extract bidirectional deep temporal features of HRRP in each layer,and the bidirectional features were fused by an additive strategy.Finally,more robust fusion features were utilized to recognize ballistic targets,and the Adam algorithm was used to optimize the convergence speed and stability of AF-BiTCN.The experimental results show that the proposed HRRP recognition method of midcourse ballistic targets based on AFBiTCN in this paper has higher accuracy and faster recognition speed compared with six methods such as stack long short-term memory(SLSTM),stack gate recurrent unit(SGRU)and so on,and it achieves an accuracy of 96.60%on the test set.Moreover,the proposed method indicates better robustness on noise datasets.

关 键 词：双向时间卷积神经网络 弹道目标识别 特征融合 高分辨距离像 滑窗算法 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.4[自动化与计算机技术—控制科学与工程]