Journal of Shandong University(Engineering Science) ›› 2023, Vol. 53 ›› Issue (4): 149-156.doi: 10.6040/j.issn.1672-3961.0.2022.264

• Others • Previous Articles     Next Articles

Optimization of manufacturing parameters for optical fiber preform core based on intelligent algorithm

Haoyuan LI1(),Jingming YU2,Guilin ZHANG3,Bin ZHANG1,*()   

  1. 1. School of Mechanical, Electrical & Information Engineering, Shandong University, Weihai 264200, Shandong, China
    2. Weihai Changhe Guangdao Technology Co., Ltd., Weihai 264200, Shandong, China
    3. Hongan Group Co., Ltd., Weihai 264200, Shandong, China
  • Received:2022-07-27 Online:2023-08-20 Published:2023-08-18
  • Contact: Bin ZHANG E-mail:sdulihaoyuan@mail.sdu.edu.cn;bin.zhang@mail.sdu.edu.cn

RichHTML

3

PDF (PC)

96

Abstract:

Combined with back propagation (BP) neural network and genetic algorithm, a high-quality and low-cost process parameter optimization method was proposed. The flow rate of two blowtorch gases (H2-1, H2-2, H2-3, Ar-1, Ar-2, Ar-3, O2-1, O2-2, SiCl4) during the preparation of optical fiber preform core layer by vapor axial deposition (VAD) was selected as the input variable. The quality of the prepared optical fiber preform core layer was taken as the output variable in the established neural network model. The trained neural network model was combined with the genetic algorithm with global optimization ability, and the high quality core layer of optical fiber preform was taken as the optimization objective to obtain high quality gas parameters. The obtained parameters were selected at low cost, and the high quality and low cost process parameters were obtained. The experimental results showed that compared with the manual optimization results before optimization, the prepared optical fiber preform core layer met the high quality requirements and the cost was reduced by 22.19%.

Key words: optical fiber preform, core layer, vapor axial deposition, BP neural network, intelligent algorithm, manufacturing parameters optimization

CLC Number: 

  • O469

Table 1

Part of the production data"

样本 气体流量变化/%质量等级 成本系数
H2-1 H2-2 Ar-1 O2-1 Ar-2 H2-3 Ar-3 O2-2 SiCl4
2 -4.11 -0.33 0.91 -1.77 1.06 0.95 1.06 0.99 -15.25 3 9.25
3 18.49 -2.95 6.15 17.96 -8.97 -7.92 -8.97 -9.03 -3.39 5 10.17
4 4.11 0.33 -0.91 1.85 -0.76 -0.82 -0.76 -0.79 -11.86 5 9.42
5 -5.48 -5.41 -10.25 6.80 -10.18 6.88 -10.18 -4.72 -15.25 3 10.26
6 -6.16 -3.77 3.64 -7.43 3.80 3.76 3.80 3.81 -20.34 1 9.00
7 -6.85 -4.92 -34.85 0.52 -2.13 5.28 -2.13 3.81 -11.86 4 9.42
8 -6.85 -4.10 3.19 -6.17 3.34 3.29 3.34 3.32 -20.34 1 9.01

Fig.1

BP neural network structure for quality optimization of optical fiber preform"

Fig.2

Mean square error of BP neural network model training and testing"

Fig.3

Comparison of simulation results of BP neural network and experimental results"

Fig.4

The error of simulation results of BP neural network"

Table 2

Comparison of test samples quality grade between experiment and simulation"

样本序号 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
试验等级 1 4 5 4 4 4 1 1 1 1 1 1 2 1 2 1 3
模拟等级 1 5 4 4 4 4 1 1 1 2 1 1 1 1 2 1 3
误差 0 1 -1 0 0 0 0 0 0 1 0 0 -1 0 0 0 0

Fig.5

Flow chart of optimization algorithm"

Fig.6

Average fitness and minimum fitness of each generation of genetic algorithm"

Table 3

Comparison between simulation result and experimental result"

样本气体流量变化/%成本系数质量等级
H2-1 H2-2 Ar-1 O2-1 Ar-2 H2-3 Ar-3 O2-2 SiCl4 仿真 试验
1 -6.07 -20.65 10.59 -28.61 -30.47 2.63 -58.73 58.47 -37.84 7.83 4.93 5
2 14.60 3.55 -30.37 -29.83 -69.62 28.85 -15.96 33.31 -16.86 8.51 5.00 5
3 19.51 71.25 54.92 14.23 -81.21 -17.48 -66.16 11.43 14.70 7.68 5.00 5
4 24.74 57.80 28.03 -12.73 -90.43 19.78 -7.45 1.46 -26.48 8.80 5.00 5
5 -12.35 88.45 22.34 11.10 -92.24 0.96 -28.25 -4.97 -49.84 8.46 5.00 5
6 22.37 48.67 -23.67 5.62 -82.38 3.14 -10.62 8.17 -59.78 8.28 5.00 5
7 38.99 50.80 101.54 8.98 -35.49 -16.38 -71.04 0.93 2.76 7.26 5.00 5
8 15.29 122.67 51.15 -3.29 -66.09 -26.56 -69.37 25.44 -25.41 8.27 5.00 4
9 81.99 86.10 100.04 -27.64 -44.97 14.55 -59.73 0.66 1.38 7.88 5.04 4
10 -90.55 37.63 -15.76 6.94 -57.66 -28.78 -30.15 43.92 -55.50 7.51 5.00 4

Fig.7

The refractive index profile of the optical fiber preform core produced by the simulation results"

1 崔秀国, 刘翔, 操时宜, 等. 光纤通信系统技术的发展、挑战与机遇[J]. 电信科学, 2016, 32 (5): 34- 43.
CUI Xiuguo , LIU Xiang , CAO Shiyi , et al. Development, challenge and opportunity of optical fiber communication system technologies[J]. Telecommunications Science, 2016, 32 (5): 34- 43.
2 BALLATO J , DRAGIC P . Materials development for next generation optical fiber[J]. Materials, 2014, 7 (6): 4411- 4430.
doi: 10.3390/ma7064411
3 陶伟. 基于"VAD+OVD"两步法的G. 652D光纤预制棒羟基控制工艺研究[D]. 杭州: 浙江大学, 2019.
TAO Wei. Study on hydroxyl control technology of G. 652D optical fiber preform based on "VAD+OVD" two-step method[D]. Hangzhou: Zhejiang University, 2019.
4 王兵钦, 王樯, 何炳, 等. VAD法制备大尺寸芯棒的研究[J]. 光通信技术, 2020, 44 (10): 47- 52.
WANG Bingqin , WANG Qiang , HE Bing , et al. Research on VAD method of fabricating large size core rod[J]. Optical Communication Technology, 2020, 44 (10): 47- 52.
5 SUDO S , EDAHIRO T , KAWACHI M . Sintering process of porous preforms made by a VAD method for optical fiber fabrication[J]. Ieice Transactions, 1980, 63 (10): 731- 737.
6 TRAUTVETTER T , SCHÄFER J , BENZINE O , et al. Plasma-based VAD process for multiply doped glass powders and high-performance fiber preforms with outstanding homogeneity[J]. Plasma Processes and Polymers, 2020, 17 (12): 2000140.
doi: 10.1002/ppap.202000140
7 FUKUSHIMA K . Cognitron: a self-organizing multilayered neural network[J]. Biological Cybernetics, 1975, 20 (3): 121- 136.
8 康靓, 米晓希, 王海莲, 等. 人工神经网络在材料科学中的研究进展[J]. 材料导报, 2020, 34 (21): 21172- 21179.
KANG Jing , MI Xiaoxi , WANG Hailian , et al. Research progress of artificial neural networks in material science[J]. Materials Reports, 2020, 34 (21): 21172- 21179.
9 戚云超, 方国东, 梁军, 等. 三维针刺C/C-SiC复合材料预制体工艺参数优化[J]. 材料工程, 2020, 48 (1): 27- 33.
QI Yunchao , FANG Guodong , LIANG Jun , et al. Optimization of process parameters of three-dimensional needled preforms for C/C-SiC composites[J]. Journal of Materials Engineering, 2020, 48 (1): 27- 33.
10 赖静, 王清, 孙东立. 人工神经网络在材料研究中的应用[J]. 材料工程, 2006, (增刊1): 458- 462.
LAI Jing , WANG Qing , SUN Dongli . Application ofartificial neural network in materials study[J]. Journal of Materials Engineering, 2006, (Suppl.1): 458- 462.
11 MIRJALILI S . Evolutionary algorithms and neural networks[M]. Cham, Switzerland: Springer, 2019: 43- 55.
12 SHEN C Y , WANG L , LI Q . Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method[J]. Journal of Materials Processing Technology, 2007, 183 (2/3): 412- 418.
13 郭强, 郑燕萍, 朱伟庆, 等. 基于BP神经网络遗传算法的高强钢成形研究[J]. 材料科学与工艺, 2020, 28 (2): 89- 96.
GUO Qiang , ZHENG Yanping , ZHU Weiqing , et al. Research on high strength steel forming based on BP neural network genetic algorithms[J]. Materials Science and Technology, 2020, 28 (2): 89- 96.
14 黄丽. BP神经网络算法改进及应用研究[D]. 重庆: 重庆师范大学, 2008.
HUANG Li. BP neural network algorithm improvement and application research[D]. Chongqing: Chongqing Normal University, 2008.
15 RUAN X M , ZHU Y Y , LI J , et al. Predicting the citation counts of individual papers via a BP neural network[J]. Journal of Informetrics, 2020, 14 (3): 101039.
[1] DING Fei, JIANG Mingyan. Housing price prediction based on improved lion swarm algorithm and BP neural network model [J]. Journal of Shandong University(Engineering Science), 2021, 51(4): 8-16.
[2] SUN Donglei, WANG Yan, YU Yixiao, HAN Xueshan, YANG Ming, YAN Fangqing. Interval prediction of short-term regional photovoltaic power based on BP neural network [J]. Journal of Shandong University(Engineering Science), 2020, 50(5): 70-76.
[3] Baoming JIN,Guangyi LU,Wei WANG,Lunyue DU. Research on BP neural network rainfall runoff forecasting model based on elastic gradient descent algorithm [J]. Journal of Shandong University(Engineering Science), 2020, 50(3): 117-124.
[4] Diankun ZHENG,Tongle XU,Zhaojie YIN,Qingmin MENG. Prediction method of tailing dam groundwater levels based on improved PSO-BP neural network [J]. Journal of Shandong University(Engineering Science), 2019, 49(3): 108-113.
[5] DENG Guanlong, YANG Hongyong, ZHANG Shuning, GU Xingsheng. Multi-objective scheduling in no-wait flow shop using a hybridized differential evolution algorithm [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2016, 46(5): 21-28.
[6] LIU Jie, YANG Peng, LYU Wensheng, LIU Agudamu, LIU Junxiu. Prediction models of PM2.5 mass concentration based on meteorological factors [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2015, 45(6): 76-83.
[7] YAO Fu-an,PANG Xiang-kun,JIAO Ying-ying,WANG Zhong-lin,ZHANG Xi-man . Temperature detection of a rotary kiln based on three-color measurement and the BP neural network [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2008, 38(2): 61-65 .
[8] GAO Xiao-wei,JIANG Xiao-yun . [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(6): 107-110 .
[9] ZHAO Yijun . [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(4): 81-83 .
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] WANG Su-yu,<\sup>,AI Xing<\sup>,ZHAO Jun<\sup>,LI Zuo-li<\sup>,LIU Zeng-wen<\sup> . Milling force prediction model for highspeed end milling 3Cr2Mo steel[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(1): 1 -5 .
[2] ZHANG Yong-hua,WANG An-ling,LIU Fu-ping . The reflected phase angle of low frequent inhomogeneous[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(2): 22 -25 .
[3] LI Kan . Empolder and implement of the embedded weld control system[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2008, 38(4): 37 -41 .
[4] SHI Lai-shun,WAN Zhong-yi . Synthesis and performance evaluation of a novel betaine-type asphalt emulsifier[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2008, 38(4): 112 -115 .
[5] KONG Xiang-zhen,LIU Yan-jun,WANG Yong,ZHAO Xiu-hua . Compensation and simulation for the deadband of the pneumatic proportional valve[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(1): 99 -102 .
[6] LAI Xiang . The global domain of attraction for a kind of MKdV equations[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(1): 87 -92 .
[7] YU Jia yuan1, TIAN Jin ting1, ZHU Qiang zhong2. Computational intelligence and its application in psychology[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2009, 39(1): 1 -5 .
[8] LI Liang, LUO Qiming, CHEN Enhong. Graph-based ranking model for object-level search
[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2009, 39(1): 15 -21 .
[9] CHEN Rui, LI Hongwei, TIAN Jing. The relationship between the number of magnetic poles and the bearing capacity of radial magnetic bearing[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2018, 48(2): 81 -85 .
[10] WANG Bo,WANG Ning-sheng . Automatic generation and combinatory optimization of disassembly sequence for mechanical-electric assembly[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2006, 36(2): 52 -57 .
Copyright 2018 © Editorial office of Journal of Shandong University (Engineering Science)
Supported by Beijing Magtech Co.Ltd