Enhanced LORAN signals generating based on cycle-consistent adversarial networks
In signal generation algorithms,a large number of labeled signal samples are needed for network training,but it is usually difficult to obtain signals carrying message information markers in bulk. To address this problem,this paper proposes a method based on CycleGAN and transfer learning,which realizes the generation of Enhanced LORAN signals without the need for a large number of signals and the corresponding messages as markers and uses migration learning to generate them quickly with a small number of measured signals. The structure of the CycleGAN includes two generators and two discriminators,using the Enhanced LORAN signals and message data sets that do not need to be one-to-one correspondence,so that the generator learns the interconversion relationship between the two data sets,and realises that the input message data can generate the Enhanced LORAN signals corresponding to it,for the characteristics of the Enhanced LORAN signal,the network model is improved using a one-dimensional convolution,residual network,and self-attention mechanism. Experimentally confirmed,it is confirmed that the mean square error of the signal generated by this paper with the measured data is 0.0153,the average Pearson correlation coefficient is 0.9843,and the accuracy of the contained message information is 99.02％. To verify the universality of the algorithm,this paper validates the algorithm on PSK,ASK,and FSK datasets,and the experimental results show that the generated signals satisfy the expectations and provide a new idea for signal modulation and demodulation with unknown parameters.
signal generationCycleGANtransfer learningenhanced LORAN signal
万方数据
维普
