电子学报 ›› 2019, Vol. 47 ›› Issue (8): 1618-1625.DOI: 10.3969/j.issn.0372-2112.2019.08.003

• 学术论文 • 上一篇    下一篇

基于BP神经网络的高精度本地多基准时钟合成算法研究

张萌   

  1. 中国信息通信研究院技术与标准研究所, 北京 100191
  • 收稿日期:2018-09-05 修回日期:2018-11-29 出版日期:2019-08-25
    • 作者简介:
    • 张萌 男,1989年出生于北京.中国信息通信研究院技术与标准研究所工程师.研究方向为时钟同步、分组传送、量子信息.E-mail:zhangmeng@ritt.cn
    • 基金资助:
    • 国家自然科学基金 (No.61671159)

Research on High-Precision Local Multi Reference Clock Synthesis Algorithm Based on BP Neural Network

ZHANG Meng   

  1. Research Institute of Telecommunications Transmission(RITT), China Academy of Information Communications Technology(CAICT), MIIT, Beijing 100191, China
  • Received:2018-09-05 Revised:2018-11-29 Online:2019-08-25 Published:2019-08-25
    • Supported by:
    • National Natural Science Foundation of China (No.61671159)

摘要: 解决基于单个原子钟的系统频率准确度难以突破10-12量级,基于多基准时钟合成算法的系统无法同时显著改善时钟的长期稳定性和短期稳定性,难以满足未来诸多领域超高精度时钟同步需求的问题,本文将多基准时钟合成算法和神经网络算法相结合,提出一种基于误差逆传播算法神经网络(BP神经网络)的本地多基准时钟合成算法,可以同时改善时钟源的短期和长期稳定性.

关键词: BP神经网络, 机器学习, 多基准时钟合成, 高精度时钟

Abstract: The system frequency accuracy based on a single atomic clock is difficult to break through 10-12 level, and the system based on multi-reference clock synthesis algorithm can't significantly improve the long-term stability and short-term stability of the clock at the same time, which is difficult to meet the requirements of ultra-high precision clock synchronization in many fields in the future.  Combined with neural network algorithm, a local multi-reference clock synthesis algorithm based on back-propagation neural network (BP neural network) is proposed, which can improve the short-term and long-term stability of clock source at the same time.

Key words: BP neural network, machine learning, multi reference clock synthesis, high precision clock

中图分类号: