引用本文:姚衍,武岩波,朱敏.基于自编码器的水声非相干恒重映射优化[J].控制理论与应用,2022,39(11):2019~2027.[点击复制]
YAO Yan,WU Yan-bo,ZHU Min.Optimization of non-coherent underwater acoustic constant weight mapping based on auto-encoder[J].Control Theory and Technology,2022,39(11):2019~2027.[点击复制]
基于自编码器的水声非相干恒重映射优化
Optimization of non-coherent underwater acoustic constant weight mapping based on auto-encoder
摘要点击 597  全文点击 182  投稿时间：2021-08-24  修订日期：2022-09-26
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2021.10784
  2022,39(11):2019-2027
中文关键词  水声通信  深度神经网络  Rice衰落信道  恒重码  自编码器
英文关键词  underwater acoustic communication  deep neural network  Rice fading channel  constant weight code  auto-encoder
基金项目  中国科学院战略性先导科技专项项目(XDA22030101), 国家自然科学基金项目(61971472, 61471351), 中国科学院声学研究所自由探索类项 目(ZYTS202003)资助.
作者单位E-mail
姚衍 中国科学院声学研究所 yaoyan@mail.ioa.ac.cn 
武岩波* 中国科学院声学研究所 wuyanbo@mail.ioa.ac.cn; 
朱敏 中国科学院声学研究所  
中文摘要
      针对水声多径衰落非相干信道, 提出一种灵活的恒重自编码方案以解决传统恒重映射(如Hadamard映射) 权重单一, 频谱利用率低的问题. 将水声多径信道建模为泛化性更高的Rice衰落, 利用深度神经网络(DNN)合理构 建自编码器(AE), 在多个衰落因子下进行输入到输出的端到端训练, 在发射平均功率不变的条件下, 得到权重分布 更优的映射集. 发射符号幅度不局限于‘0’和‘1’的分布集合, 但分组仍保持恒重. 接收端仍可采用能量检测, 不依赖 信道状态信息(CSI)、鲁棒性强. 为扩展到高阶情况, 提出一种低复杂度的网络输入模式使AE复杂度大大降低, 加速 训练收敛. 仿真证明, 在接收端CSI未知的情况下, 所提方案在标准衰落信道及Bellhop模拟水声信道上均取得相较 传统方案5–6 dB的性能增益. 最后, 采用通信带宽4 kHz, 通信距离2500 m, 海底深度1750 m的南海海试数据对结果 进行了验证.
英文摘要
      For underwater acoustic multipath-fading noncoherent channels, a flexible constant weight automatic coding scheme is proposed to solve the problems of limited weight-distribution and low spectral-efficiency of traditional constant weight mappings (e.g., Hadamard mappings). The underwater acoustic multipath channel is modeled as the Rice fading, which is more generalized than the Rayleigh one. The auto-encoder (AE) is constructed by using the deep neural networks (DNN) and the end-to-end input-to-output training is carried out under several fading factors. Under the fixed average transmission power, the mapping set with better weight-distribution is obtained. The transmitted symbol amplitude is not limited to the ‘0’ or ‘1’, but the groups still maintain constant weight. The energy detection can still be used at the receiver side, which is robust without the channel state information (CSI). To extend to the high-order cases, a low complexity network-input mode is proposed to reduce the complexity of the proposed AE and accelerate the training convergence. With unknown CSI on the receiver side, the simulation results show that the proposed scheme achieves a performance gain of 5–6 dB over the standard fading channels and the Bellhop simulated underwater acoustic channel. The results are also verified by sea trial data collected in the South China Sea with seafloor depth of 1750 m, the communication bandwidth is 4 kHz and the communication distance is 2500 m.