| 摘要: |
| 针对低信噪比场景下多飞行目标波达方向（Direction of Arrival,DOA）估计精度不高，导致基于智能天线的民航地空通信抗干扰性能较差的问题，提出了一种基于航向训练模式和动态径向基神经网络（Radial Basis Function Neural Network,RBFNN）的多飞行目标追踪方法。首先融合二次雷达信息，建立民航飞行目标DOA变换关系；然后通过航向训练模式，粗估下一时刻各飞行目标DOA，并作为RBFNN的输入；最后构建隐含层中心动态调整的RBFNN，快速准确追踪各飞行目标DOA。实验表明，该方法可以大幅提高空中同时存在的多飞行目标DOA估计精度；结合波束形成技术，可以大幅提高民航地空通信系统的抗干扰能力，提升民航飞行安全水平；在5 dB信噪比条件下，相对基于常规智能天线的民航地空通信系统，抗干扰能力可以提升16 dB。 |
| 关键词: 地空通信 多飞行目标追踪 波达方向估计 径向基神经网络 抗干扰能力 |
| DOI：10.20079/j.issn.1001-893x.231214001 |
|
| 基金项目:教育部第二批新工科研究与实践项目（E-XTYR20200661）；四川省科技成果转移转化示范项目（2020ZHZY0010） |
|
| A Multi-flight Target Tracking Method for Civil Aviation Ground-to-Air Communication Anti-interference |
| YAO Yuanfei,CHEN Xinpeng,ZHANG Xiaozhou,CAI Fangkai,LI Xiaoyu |
| (1.School of Network ＆ Communication Engineering，Chengdu Technological University，Chengdu 611730，China;2.Chengdu Spaceon Technology Co.，Ltd.，Chengdu 611731，China) |
| Abstract: |
| In view of the problem that the estimation accuracy of the direction of arrival(DOA) of multi-flight targets is not high in the scene with low signal-to-noise ratio(SNR),which leads to the poor anti-interference performance of civil aviation ground-to-air communication based on smart antenna,a multi-flight target tracking method based on course training model and dynamic radial basis function neural network(RBFNN) is proposed.Firstly,the secondary radar information is fused to establish the DOA transformation relationship of civil aviation flight targets.Then,through the course training mode,the DOA of each flying target at the next moment is estimated and used as the input for RBFNN.Finally,the RBFNN with dynamic adjustment of the hidden layer center is constructed to quickly and accurately track the DOA of each flying target.Experiments show that this method can significantly improve the accuracy of DOA estimation for multiple flying targets simultaneously in the air,and if combined with beamforming technology,it can greatly enhance the anti-interference ability of civil aviation ground-to-air communication systems and enhance the level of civil aviation flight safety.Under the condition of 5 dB SNR,the anti-interference ability can be improved by 16 dB compared with that of civil aviation ground-to-air communication systems based on conventional smart antennas. |
| Key words: ground-to-air communication multi-flight target tracking DOA estimation radial basis function neural network anti-interference ability |
