Design of Bismuth-Doped Fiber Amplifier Based on Neural Network and Multi-Objective Optimization Algorithm

Wenqiang Hou; Li Pei; Jianshuai Wang; Jingjing Zheng; Wenxuan Xu; Zichen Tian; Dingchen Wang; Lihong Wang; jing Li; Tigang Ning

doi:10.3788/AOS231173

Acta Optica Sinica, Volume. 44, Issue 2, 0206001(2024)

Design of Bismuth-Doped Fiber Amplifier Based on Neural Network and Multi-Objective Optimization Algorithm

Wenqiang Hou^1,2, Li Pei^1,2、*, Jianshuai Wang^1,2, Jingjing Zheng^1,2, Wenxuan Xu^1,2, Zichen Tian^1,2, Dingchen Wang^1,2, Lihong Wang^1,2, jing Li^1,2, and Tigang Ning^1,2

Author Affiliations

¹School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China

²Key Laboratory of All Optical Network＆Advanced Telecommunication Network of EMC, Institute of Lightwave Technology, Beijing Jiaotong University, Beijing 100044, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(11)

Fig. 1. Schematic diagram of the two-stage BDFA

Download full size

Fig. 2. Structure diagram of BPNN

Download full size

Fig. 3. NSGA-Ⅱ algorithm flow chart

Download full size

Fig. 4. The test performance of Gain and NF after training BPNN model with different sample sizes

Download full size

Fig. 5. Fitting of predicted value and target value. (a)(b) Gain and NF predicted by BPNN

Download full size

Fig. 6. Pareto optimal solution set

Download full size

Fig. 7. Gain and NF in different configurations

Download full size

Fig. 8. PDF curves of testing absolute errors for Gain and NF using BPNN and SVM models. (a) Gain; (b) NF

Download full size

Fig. 9. Time consuming to optimize design with different methods

Download full size

Table 1. The ranges of parameters in the simulation

View table

Table 1. The ranges of parameters in the simulation

Parameter		Value range
Wavelength of signal /nm	$λ_{s}$	1320-1360
Length of first BDF /m	$L_{1}$	0-50
Length of second BDF /m	$L_{2}$	100-250
Pump power of stage 1 /S	$P_{1}$	0-0.1
Pump power of stage 2 /W	$P_{2}$	0.3-0.7
Pump power ratio of stage 2	$R$	0-1

Table 2. Partial Pareto optimal solution sets and corresponding fitness values

View table

Table 2. Partial Pareto optimal solution sets and corresponding fitness values

Two-stage BDFA parameter						Average Gain /dB	Average NF /dB
Group	$L_{1}$ /m	$L_{2}$ /m	$P_{1}$ /W	$P_{2}$ /W	$R$	Average Gain /dB	Average NF /dB
1	48.82	246.43	0.10	0.69	0.28	37.67	5.31
2	18.65	249.94	0.10	0.67	0.58	35.01	5.18
3	5.33	249.93	0.10	0.69	0.83	32.71	5.13
4	6.11	203.15	0.10	0.70	0.80	28.21	5.11
5	6.10	185.59	0.10	0.69	0.93	25.81	5.10

Tools

Get Citation

Copy Citation Text

Wenqiang Hou, Li Pei, Jianshuai Wang, Jingjing Zheng, Wenxuan Xu, Zichen Tian, Dingchen Wang, Lihong Wang, jing Li, Tigang Ning. Design of Bismuth-Doped Fiber Amplifier Based on Neural Network and Multi-Objective Optimization Algorithm[J]. Acta Optica Sinica, 2024, 44(2): 0206001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Fiber Optics and Optical Communications

Received: Jun. 21, 2023

Accepted: Sep. 20, 2023

Published Online: Jan. 5, 2024

The Author Email: Pei Li (lipei@bjtu.edu.cn)

DOI:10.3788/AOS231173

CSTR:32393.14.AOS231173

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology