-
环境温度变化常会引起光纤法珀应变传感器的测量误差。为有效补偿温度对测量结果的影响，本文提出了一种优化的粒子群(particle swarm optimization,PSO)-反向传播(back propagation neural network,BP)神经网络算法。该算法直接将温度和光纤法珀应变传感器测得的光谱峰值漂移数据作为实验样本输入，建立温度补偿神经网络系统模型，采用自适应调整惯性权重和学习因子动态优化调整机制，提高了算法的全局搜索能力和局部收敛精度，从而实现对温度影响的有效补偿。实验结果表明，在整个传感器的温度测量范围内，基于优化PSO-BP算法的平均绝对百分比误差为1.2%，相比传统的BP算法和PSO-BP算法的平均绝对百分比误差分别改进了57.14%、45.45%，且不同温度下R2普遍在0.995以上，这表明模型能够在不同温度条件下准确预测应变值，从而实现有效的温度补偿，为低成本高精度传感系统的开发提供了新的技术途径。
-
关键词:
- 光纤传感器 /
- 优化PSO-BP神经网络 /
- 温度补偿 /
- 法珀干涉
Ambient temperature variations frequently induce measurement errors in fiber-optic Fabry-Perot strain sensors. To effectively compensate for temperature effects, this study systematically investigates a single-mode fiber-hollow-core fiber-single-mode fiber (SMF-HCF-SMF) Fabry-Perot fiber strain sensor. Experimental datasets were collected under varying temperature and strain conditions, with Kalman filtering employed for noise suppression and data preprocessing. The processed data were subsequently fed into an optimized PSO-BP neural network, where temperature values and spectral peak shift measurements from the sensor served as direct inputs to establish a temperature-compensated neural network model. The algorithm incorporates adaptive adjustment mechanisms for inertial weights and learning factors, significantly enhancing global search capability and local convergence accuracy.Experimental results demonstrate that the optimized PSO-BP algorithm achieves a mean absolute percentage error (MAPE) of 1.2% across the sensor's operational temperature range, with R2 values consistently exceeding 0.995 under diverse thermal conditions. Comparative analyses reveal that the optimized PSO-BP model improves MAPE by 57.14%, 45.45%, 73.91%, and 53.85% relative to conventional BP, PSO-BP, RF, and GA-BP models, respectively. Corresponding reductions in root mean square error (RMSE) reach 68.11%, 52.42%, 72.94%, and 63.13%. These metrics substantiate the algorithm's superior strain prediction performance and effective temperature compensation capability. The proposed methodology provides a novel technical pathway for developing cost-effective, high-precision sensing systems with robust thermal stability.-
Keywords:
- optical fiber sensor /
- optimized PSO-BP neural network /
- temperature compensation /
- Fabry-Perot interference
-
[1] Feng D Q, Luo X D, Fan W, Zhu B H, Qiao X G 2021 Acta Opt. Sin. 41 88(in Chinese) [冯德全，罗小东，樊伟，朱宝辉，乔学光2021光学学报41 88]
[2] Tian C, Chen H B, Hu K, ZHANG J Y, WANG W 2022 Journal of Optoelectronics·Laser 33 865(in Chinese) [田晨，陈海滨，胡锴，张军英，王伟2022光电子·激光33 865]
[3] Xiao Y, Cheng J 2024 Sensors.24 7805
[4] Bian Q, Podhrazsky A, Bauer C, Stadler A, Buchfellner F, Kuttler R, Jakobi M, Volk W, W. Koch A, Roths J 2022 Optics Express 30 33449
[5] Rui F, Ge Y X, Su R, NI H B 2024 Acta Opt. Sin. 44 67(in Chinese) [芮菲，葛益娴，苏蕊，倪海彬2024光学学报44 67]
[6] Chen M, Chang J H, Xu Y, JIN A B, HU Z Y 2023 Acta Opt. Sin. 43 36(in Chinese) [陈鸣，常建华，徐遥，金澳博，胡子怡2023光学学报43 36]
[7] SUN J C, WANG T T, DAI Y, CHANG J H, KE W 2021 Acta Phys. Sin.70 214(in Chinese) [孙家程，王婷婷，戴洋，常建华，柯炜2021物理学报70 214]
[8] Wang Y L, Tu Y, Tu S D, YU X H, GUO Y N, REN L J, CHEN S J 2023 Instrument Technique and Sensor 43 26(in Chinese) [王雅莉，徒芸，涂善东，于新海，郭永宁，任利杰，陈时健2023仪表技术与传感器4326]
[9] Ding X, Chen N, Jin T, ZHANG X D, ZHANG R F 2023 Optics & Laser Technology 162 109302
[10] ZHAO Y, CAI L, LI X G, LU R Q 2017 Acta Phys. Sin.66 9(in Chinese) [赵勇，蔡露，李雪刚，吕日清2017物理学报66 9]
[11] WU Q, ZHANG Z Y, GUO X C, SHI W H 2018 Acta Phys. Sin.67 180(in Chinese) [吴倩，张诸宇，郭晓晨，施伟华2018物理学报67 180]
[12] Cao Y, Xu W Y, Lin B, Zhu Y, Meng F C, Zhao X T, Ding J M, Lou S Q, Wang X, He J W, Sheng X Z, Liang S 2022 Applied optics 61 8212
[13] Yang J Y, Liang L, Tang H M, XIE G M, XU G 2020 Journal of Optoelectronic·Laser 31351(in Chinese) [杨建宇，梁磊，唐浩冕，谢官模，徐刚2020光电子·激光 31351]
[14] Li Y Z, Jin D Y, Huang W X, HU J L, JING D T 2022 Piezoelectrics&Acoustooptics 44 873(in Chinese) [李勇志，金东洋，黄文雪，胡久龄，景殿涛2022压电与声光44873]
[15] Sun C, Guo N Y, Ye L, MIAO L X, CAO M, DING J J, YAN M D 2022 Piezoelectrics and Acoustooptics 44 85(in Chinese) [孙超，郭乃宇，叶力，苗隆鑫，曹勉，丁建军，严明蝶2022压电与声光44 85]
[16] Sun M M. M.S. Thesis(Nanjing:Nanjing University of Information Science and Technology) (in Chinese) [孙萌萌2023硕士学位论文（南京：南京信息工程大学）]
[17] ZHANG J W M.S. Thesis(Haerbin: Heilongjiang University) (in Chinese) [张金文2023硕士学位论文（哈尔滨：黑龙江大学）]
[18] Yu W, Qu H, Zhang Y 2023 Sensors 23 7823
[19] Li Y J, Li Y H, LI F, ZHAO B, LI Q Q 2015 Mathematical Problems in Engineering 2015 854945
[20] Wei L X, Zhang Y, JI L I, YE L, ZHU X C, FU J 2022 Energies 15 5880
[21] Zhou Z W, Gong H Y, You J, LIU S B, HE J L 2021 Materials Today Communications 28 102507
[22] Zhou Y 2024 Geomatics & Spatial Information Technology 47 217(in Chinese) [周勇2024测绘与空间地理信息47 217]
[23] Li X, Ke S C, Li Y, JIN W, FU X H, FU G W, BI W H 2024 Optics & Laser Technology 176 110973
计量
- 文章访问数: 13
- PDF下载量: 0
- 被引次数: 0
下载:
