Coherent beam combination based on Q-learning algorithm

被引：23

作者：

Zhang, Xi ^{[1
]}

Li, Pingxue ^{[1
]}

Zhu, Yunchen ^{[1
]}

Li, Chunyong ^{[2
]}

Yao, Chuanfei ^{[1
]}

Wang, Luo ^{[1
]}

Dong, Xueyan ^{[1
]}

Li, Shun ^{[1
]}

机构：

[1] Beijing Univ Technol, Fac Mat & Mfg, Inst Ultrashort Pulsed Laser & Applicat, Beijing 10024, Peoples R China

[2] Univ Durham, Dept Phys, South Rd, Durham DH1 3LE, England

来源：

OPTICS COMMUNICATIONS | 2021年 / 490卷

基金：

中国国家自然科学基金; 北京市自然科学基金;

关键词：

Coherent beam combination; Q-learning algorithm; Stochastic parallel gradient descent; optimization algorithm; FIBER LASERS;

D O I：

10.1016/j.optcom.2021.126930

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Coherent beam combination (CBC) is an effective method to break the limiting power of a single fiber laser. The Q-learning algorithm is one of the reinforcement learning algorithms. We use the Q-learning algorithm to do phase compensation in the field of CBC. The performance difference between the Q-learning algorithm and the stochastic parallel gradient descent optimization algorithm (SPGD) is analyzed by simulating time-domain coherent synthesis. The results show that the Q-learning algorithm is easier to debug and has better stability.

引用

页数：7

共 50 条

[41] A Novel Access Network Selection Scheme using Q-learning Algorithm for Cognitive Terminal
Tan, Haifeng
Li, Yizhe
Chen, Yami
Tan, Li
Li, Qian
2010 5TH INTERNATIONAL ICST CONFERENCE ON COMMUNICATIONS AND NETWORKING IN CHINA (CHINACOM), 2010,
[42] Q-learning Based Dynamic Optimal Relax Automatic Generation Control
Yu, Tao
Yuan, Ye
Liang, Haihua
POWER AND ENERGY ENGINEERING CONFERENCE 2010, 2010, : 797 - 800
[43] Q-Learning Algorithm Enabled Topology Control Scheme in Power Line Communication Networks
Liu, Lin
Zheng, Libin
Wang, Yusi
2022 4TH INTERNATIONAL CONFERENCE ON SMART POWER & INTERNET ENERGY SYSTEMS, SPIES, 2022, : 2229 - 2232
[44] Output-only structural damage identification based on Q-learning hybrid evolutionary algorithm and response reconstruction technique
Zhang, Guangcai
Kang, Jianfei
Wan, Chunfeng
Xie, Liyu
Xue, Songtao
MEASUREMENT, 2024, 224
[45] Multi-AGV route planning in automated warehouse system based on shortest-time Q-learning algorithm
Zhang, Zheng
Chen, Juan
Zhao, Wenbing
ASIAN JOURNAL OF CONTROL, 2024, 26 (02) : 683 - 702
[46] The Q-learning obstacle avoidance algorithm based on EKF-SLAM for NAO autonomous walking under unknown environments
Wen, Shuhuan
Chen, Xiao
Ma, Chunli
Lam, H. K.
Hua, Shaoyang
ROBOTICS AND AUTONOMOUS SYSTEMS, 2015, 72 : 29 - 36
[47] Relay selection algorithm based on social network combined with Q-learning for vehicle D2D communication
Qian, Hongzhi
Yu, Jinming
Hua, Licheng
IET COMMUNICATIONS, 2019, 13 (20) : 3582 - 3587
[48] Single step phase optimisation for coherent beam combination using deep learning
Mills, Ben
Grant-Jacob, James A.
Praeger, Matthew
Eason, Robert W.
Nilsson, Johan
Zervas, Michalis N.
SCIENTIFIC REPORTS, 2022, 12 (01)
[49] Learning to estimate phases from single local patterns for coherent beam combination
Liu, Haoyu
Jin, Kun
Li, Jun
Wu, Jian
Ma, Yanxing
Su, Rongtao
Leng, Jinyong
Zhou, Pu
OPTICAL FIBER TECHNOLOGY, 2024, 88
[50] Far-field phasing method based on deep learning for tiled-aperture coherent beam combination
Li, Xunzheng
Peng, Chun
Liang, Xiaoyan
OPTICS COMMUNICATIONS, 2023, 527

← 1 2 3 4 5 →