中国物理B ›› 2023, Vol. 32 ›› Issue (4): 44208-044208.doi: 10.1088/1674-1056/ac935e

• • 上一篇    下一篇

Diffraction deep neural network based orbital angular momentum mode recognition scheme in oceanic turbulence

Hai-Chao Zhan(詹海潮)1, Bing Chen(陈兵)1, Yi-Xiang Peng(彭怡翔)1, Le Wang(王乐)1, Wen-Nai Wang(王文鼐)2, and Sheng-Mei Zhao(赵生妹)1,2,†   

  1. 1 Institute of Signal Processing and Transmission, Nanjing University of Posts and Telecommunications(NUPT), Nanjing 210003, China;
    2 Key Laboratory of Broadband Wireless Communication and Sensor Network Technology(Ministry of Education), Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • 收稿日期:2022-07-09 修回日期:2022-09-13 接受日期:2022-09-21 出版日期:2023-03-10 发布日期:2023-03-17
  • 通讯作者: Sheng-Mei Zhao E-mail:zhaosm@njupt.edu.cn
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61871234 and 62001249), and the Postgraduate Research and Practice Innovation Program of Jiangsu Province, China (Grant No. KYCX200718).

Diffraction deep neural network based orbital angular momentum mode recognition scheme in oceanic turbulence

Hai-Chao Zhan(詹海潮)1, Bing Chen(陈兵)1, Yi-Xiang Peng(彭怡翔)1, Le Wang(王乐)1, Wen-Nai Wang(王文鼐)2, and Sheng-Mei Zhao(赵生妹)1,2,†   

  1. 1 Institute of Signal Processing and Transmission, Nanjing University of Posts and Telecommunications(NUPT), Nanjing 210003, China;
    2 Key Laboratory of Broadband Wireless Communication and Sensor Network Technology(Ministry of Education), Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • Received:2022-07-09 Revised:2022-09-13 Accepted:2022-09-21 Online:2023-03-10 Published:2023-03-17
  • Contact: Sheng-Mei Zhao E-mail:zhaosm@njupt.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 61871234 and 62001249), and the Postgraduate Research and Practice Innovation Program of Jiangsu Province, China (Grant No. KYCX200718).

摘要: Orbital angular momentum (OAM) has the characteristics of mutual orthogonality between modes, and has been applied to underwater wireless optical communication (UWOC) systems to increase the channel capacity. In this work, we propose a diffractive deep neural network (DDNN) based OAM mode recognition scheme, where the DDNN is trained to capture the features of the intensity distribution of the OAM modes and output the corresponding azimuthal indices and radial indices. The results show that the proposed scheme can recognize the azimuthal indices and radial indices of the OAM modes accurately and quickly. In addition, the proposed scheme can resist weak oceanic turbulence (OT), and exhibit excellent ability to recognize OAM modes in a strong OT environment. The DDNN-based OAM mode recognition scheme has potential applications in UWOC systems.

关键词: orbital angular momentum, diffractive deep neural network, mode recognition, oceanic turbulence

Abstract: Orbital angular momentum (OAM) has the characteristics of mutual orthogonality between modes, and has been applied to underwater wireless optical communication (UWOC) systems to increase the channel capacity. In this work, we propose a diffractive deep neural network (DDNN) based OAM mode recognition scheme, where the DDNN is trained to capture the features of the intensity distribution of the OAM modes and output the corresponding azimuthal indices and radial indices. The results show that the proposed scheme can recognize the azimuthal indices and radial indices of the OAM modes accurately and quickly. In addition, the proposed scheme can resist weak oceanic turbulence (OT), and exhibit excellent ability to recognize OAM modes in a strong OT environment. The DDNN-based OAM mode recognition scheme has potential applications in UWOC systems.

Key words: orbital angular momentum, diffractive deep neural network, mode recognition, oceanic turbulence

中图分类号:  (Pattern recognition)

  • 42.30.Sy
42.68.-w (Atmospheric and ocean optics) 42.79.Ta (Optical computers, logic elements, interconnects, switches; neural networks) 84.35.+i (Neural networks)