| 摘要: |
| 随着民航飞机数量的增多，接收到的广播式自动相关监视（Automatic Dependent Surveillance-Broadcast，ADS-B）信号可能出现多条报文交织的情况，这将导致解码失败。针对单天线ADS-B二重交织信号，提出了一种投影算法与卷积神经网络（Convolutional Neural Networks，CNN）相结合的分离方法。首先将单天线ADS-B信号重构为虚拟阵列信号，接着利用投影算法对其进行分离，最后将分离信号通过CNN模型进行幅值修正。实验结果表明，通过该方法分离出的信号其解码成功率得到了提高。 |
| 关键词: 广播式自动相关监视 信号解交织 单天线 投影算法 卷积神经网络(CNN) |
| DOI： |
|
| 基金项目: |
|
| A single antenna ADS-B interleaved signal separation algorithm |
| BIE Fangyu,GAO Yong |
| (School of Electronics and Information Engineering，Sichuan University，Chengdu 610065，China) |
| Abstract: |
| With the increase in the number of civil aircraft,the received Automatic Dependent Surveillance-Broadcast(ADS-B) signals may have multiple messages interleaved,which will cause decoding failure.For single-antenna ADS-B double-interleaved signals,a separation method combining project algorithm and convolutional neural network(CNN) is proposed.Firstly,the single-antenna ADS-B signal is reconstructed into a virtual array signal,and then it is separated by project algorithm.Finally,the amplitude of the separated signal is modified by CNN model.The experimental results show that the decoding success rate of the signal separated by this method has been improved. |
| Key words: ADS-B signal separation single antenna project algorithm convolutional neural network(CNN) |
《电讯技术》编辑部 