摘要
海洋环境大动态变化特性导致水声信道复杂的时-空-频变,传统水声通信技术难以有效地与之自适应匹配。目前仍无法研制出一种能在各类海洋环境下均满足水声业务指标的水声通信机,更难以在全天候条件下实现大规模、稳健可靠的水声通信组网应用。近年来,人工智能和大数据的迅速发展,为突破传统水声通信技术瓶颈、建设海洋物联网带来新思路。本文对国内外利用人工智能技术解决水声通信难题的研究状况进行了概述,结合水声信道特性梳理了水声通信领域应用人工智能技术的主要思路,围绕人工智能技术从水声通信物理层和网络层两方面进行归纳,最后对未来的人工智能与水声通信交叉研究进行总结展望。
Significant changes in the dynamics of the marine environment lead to complex time-space-frequency variations in underwater acoustic(UWA)channels.As yet,no UWA communication set has been developed that can meet UWA business metrics in various marine environments.It is even more difficult to realize large-scale,robust,and reliable UWA networking applications that can operate in all weather conditions.In recent years,the rapid development of artificial intelligence(AI)and big data has inspired new strategies for breaking through the bottleneck of traditional UWA communication technology by building an Internet of underwater things.In this paper,progress in AI research with respect to UWA communications in China and around the world is summarized.The characteristics of UWA channels are described and the main strategies for applying AI in the UWA communication field are clarified.The application of AI in UWA communications is summarized with respect to both the physical and network layers.Finally,the future intersection of AI and UWA communications research and its future prospects are summarized.
作者
陈友淦
许肖梅
CHEN Yougan;XU Xiaomei(Key Laboratory of Underwater Acoustic Communication and Marine Information Technology(Xiamen University),Ministry of Education,Xiamen 361005,China;College of Ocean and Earth Sciences,Xiamen University,Xiamen 361102,China;Shenzhen Research Institute of Xiamen University,Shenzhen 518000,China)
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
北大核心
2020年第10期1536-1544,共9页
Journal of Harbin Engineering University
基金
国家自然科学基金项目(41976178,41676024,41476026)
深圳市科技计划基础研究面上项目(JCYJ20190809161805508).
关键词
水声
声通信
水声通信
人工智能
水下通信
机器学习
深度学习
海洋物联网
underwater acoustics
acoustic communications
underwater acoustic communications
artificial intelligence
underwater communications
machine learning
deep learning
internet of underwater things(IoUT)
