一种UAV-USV-UUV跨域协同时钟同步算法

Clock Synchronization Algorithm of UAV-USV-UUV Cross-Domain Cooperation

随着海洋科学技术的发展,水下任务更加强调跨平台系统的协作,然而不同应用场景对时钟同步的要求不同,由于水下通信的弱通信与高延迟,对涉及多场景的异构系统,需要新的同步方法。针对随机时延影响下的全网时钟同步问题,文中提出了基于神经网络的无人机(UAV)-无人水面艇(USV)-无人水下航行器(UUV)跨域协同的时钟同步算法。首先,考虑随机时延影响,将USV时钟作为基准时钟;其次,通过递推滤波和神经网络对UAV时钟偏差进行校正;最后,USV辅助UUV估计水下的长时延,设计了神经网络算法估计时钟漂移和时钟偏移。通过仿真验证了上述算法的有效性。

With the development of marine science and technology,underwater missions have placed greater emphasis on the collaboration of cross-platform systems.However,different application scenarios have varying requirements for clock synchronization.Due to the weak communication and high time delay of underwater communication,a new synchronization method is required for heterogeneous systems involving multiple scenarios.With regard to the problem of global time synchronization under the influence of random time delay,a neural network-based time synchronization algorithm for crossdomain cooperation of unmanned aerial vehicles(UAVs),unmanned surface vessels(USVs),and unmanned undersea vehicles(UUVs)was proposed.First,the impact of random time delay was considered,and the clock of USVs was used as the reference clock.The clock offset of UAVs was corrected through recursive filtering and a neural network.Finally,with the assistance of USVs,the underwater long time delay was estimated by UUVs,and a neural network algorithm was designed to estimate clock drift and clock skew.The effectiveness of the proposed algorithm was verified through simulation.