-
Ambient temperature fluctuations often induce measurement errors in fiber-optic Fabry-Perot strain sensors. To effectively compensate for the influence of temperature on measurement accuracy, this study proposes an optimized particle swarm optimization-back propagation (PSO-BP) neural network algorithm. The combined predictive model is applied to the monitoring data of a Fabry-Perot strain sensor based on a single-mode fiber-hollow-core fiber-single-mode fiber (SMF-HCF-SMF) structure. By preprocessing the data collected from the sensor, the temperature values and spectral valley shift data obtained from the fiber-optic Fabry-Perot strain sensor are directly used as input features to establish a temperature-compensated neural network model. Based on the traditional PSO-BP neural network algorithm, an optimization strategy incorporating adaptive adjustment of inertia weights and learning factors is employed to enhance global search capability and local convergence accuracy, thereby enabling effective compensation for temperature-induced effects. Experimental results demonstrate that in the entire temperature measurement range of the sensor, the optimized PSO-BP neural network achieves a mean absolute percentage error (MAPE) of about 1.2% and a root mean square error (RMSE) of about 5.9, significantly outperforming other methods. Comparative analysis with different model architectures reveals that compared with the BP, PSO-BP, RF, and GA-BP models, the optimized PSO-BP model improves MAPE by 57.14%, 45.45%, 73.91%, and 53.85%, respectively, while reducing RMSE by 68.11%, 52.42%, 72.94%, and 63.13%. Moreover, the coefficient of determination (R2) consistently exceeds 0.995 under various temperature conditions, indicating that the model effectively compensates for temperature-induced errors in the sensor under different thermal and strain conditions, and has excellent stability and adaptability. Therefore, the temperature compensation method proposed in this study not only offers a novel approach for improving the measurement accuracy of fiber-optic Fabry-Perot strain sensors, but also provides a valuable reference for studying the temperature compensation in related sensor technologies. Future research may further explore the applicability of this method to other types of sensors, thereby promoting the sustaining development of intelligent sensing technologies. 
-
Keywords:
- optical fiber sensor /
- optimized particle swarm optimization-back propagation neural network /
- temperature compensation /
- Fabry-Perot interference
-
图 1 传感器结构示意图
Figure 1. Structural diagram of sensor.
图 2 传感器温度仿真反射光谱漂移图
Figure 2. Temperature-induced drift in simulated reflectance spectra of sensors.
图 3 传感器应变测试 (a) 反射光谱漂移图; (b) 线性拟合图
Figure 3. Sensor strain test: (a) Reflection spectrum drift map; (b) linear fitting map.
图 4 温度漂移实验装置图
Figure 4. Temperature drift experiment device diagram.
图 5 温度标定实验下不同温度光纤应变传感器的波谷漂移波长特性曲线
Figure 5. Wavelength drift characteristics curve of fiber optic strain sensors at different temperatures under temperature calibration experiment.
图 6 卡尔曼滤波前后信噪比对比
Figure 6. Comparison of SNR before and after Kalman filtering
图 7 优化PSO-BP神经网络流程图
Figure 7. Flowchart of the optimized PSO-BP neural network.
图 8 优化PSO-BP神经网络结构图
Figure 8. Structural diagram of the optimized PSO-BP neural network.
图 9 训练结果 (a) 预测输出; (b) 相对误差
Figure 9. Training results: (a) Predicted output; (b) relative error.
图 10 不同温度下应变预测值与实际值对比图 (a) 优化前; (b) 优化后
Figure 10. Comparison of predicted and actual strain values at different temperatures: (a) Before optimization; (b) after optimization.
图 11 不同神经网络模型对比
Figure 11. Comparison of different neural network models.
表 1 不同隐藏层误差对比
Table 1. Comparison of errors for different hidden layers.
隐藏层
节点个数3 4 5 6 7 8 9 10 11 MAPE/% 1.96 2.16 1.93 1.47 2.08 1.60 1.96 1.21 1.92 
DownLoad: CSV
表 2 不同神经网络模型对比
Table 2. Comparison of different neural network models.
性能指标 BP PSO-BP RF GA-BP 优化PSO-BP MAPE/% 2.8 2.2 4.6 2.6 1.2 RMSE 18.5 12.4 21.8 16.0 5.9
DownLoad: CSV
-
[1] 冯德全, 罗小东, 樊伟, 朱宝辉, 乔学光 2021 光学学报 41 2106004
Google Scholar
Feng D Q, Luo X D, Fan W, Zhu B H, Qiao X G 2021 Acta Opt. Sin. 41 2106004
Google Scholar
[2] 田晨, 陈海滨, 胡锴, 张军英, 王伟 2022 光电子·激光 33 865
Tian C, Chen H B, Hu K, Zhang J Y, Wang W 2022 J. Optoelectron. Laser 33 865
[3] Xiao Y, Cheng J 2024 Sensors 24 7805
Google Scholar
[4] Bian Q, Podhrazsky A, Bauer C, Stadler A, Buchfellner F, Kuttler R, Jakobi M, Volk W, W. Koch A, Roths J 2022 Opt. Express 30 33449
Google Scholar
[5] 芮菲, 葛益娴, 苏蕊, 倪海彬 2024 光学学报 44 1606004
Google Scholar
Rui F, Ge Y X, Su R, Ni H B 2024 Acta Opt. Sin. 44 1606004
Google Scholar
[6] 陈鸣, 常建华, 徐遥, 金澳博, 胡子怡 2023 光学学报 43 2306001
Chen M, Chang J H, Xu Y, Jin A B, Hu Z Y 2023 Acta Opt. Sin. 43 2306001
[7] 孙家程, 王婷婷, 戴洋, 常建华, 柯炜 2021 物理学报 70 064202
Google Scholar
Sun J C, Wang T T, Dai Y, Chang J H, Ke W 2021 Acta Phys. Sin. 70 064202
Google Scholar
[8] 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 43 26
Google Scholar
Wang Y L, Tu Y, Tu S D, Yu X H, Guo Y N, Ren L J, Chen S J 2023 Instrum. Tech. Sens. 43 26
Google Scholar
[9] Ding X, Chen N, Jin T, Zhang X D, Zhang R F 2023 Opt. Laser Technol. 162 109302
Google Scholar
[10] 赵勇, 蔡露, 李雪刚, 吕日清 2017 物理学报 66 070601
Google Scholar
Zhao Y, Cai L, Li X G, Lü R Q 2017 Acta Phys. Sin. 66 070601
Google Scholar
[11] 吴倩, 张诸宇, 郭晓晨, 施伟华 2018 物理学报 67 184212
Google Scholar
Wu Q, Zhang Z Y, Guo X C, Shi W H 2018 Acta Phys. Sin. 67 184212
Google Scholar
[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 Appl. Opt. 61 8212
Google Scholar
[13] 杨建宇, 梁磊, 唐浩冕, 谢官模, 徐刚 2020 光电子·激光 31 351
Yang J Y, Liang L, Tang H M, Xie G M, Xu G 2020 J. Optoelectron. Laser 31 351
[14] 李勇志, 金东洋, 黄文雪, 胡久龄, 景殿涛 2022 压电与声光 44 873
Google Scholar
Li Y Z, Jin D Y, Huang W X, Hu J L, Jing D T 2022 Piezoelectr. Acoustoopt. 44 873
Google Scholar
[15] 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
Sun C, Guo N Y, Ye L, Miao L X, Cao M, Ding J J, Yan M D 2022 Piezoelectr. Acoustoopt 44 85
[16] 孙萌萌 2023 硕士学位论文(南京: 南京信息工程大学)
Sun M M 2023 M. S. Thesis (Nanjing: Nanjing University of Information Science and Technology
[17] 张金文 2023 硕士学位论文(哈尔滨: 黑龙江大学)
Zhang J W 2023 M. S. Thesis (Haerbin: Heilongjiang University
[18] Yu W, Qu H, Zhang Y 2023 Sensors 23 7823
Google Scholar
[19] Li Y J, Li Y H, Li F, Zhao B, Li Q Q 2015 Math. Probl. Eng. 2015 854945
[20] Wei L X, Zhang Y, Ji L I, Ye L, Zhu X C, Fu J 2022 Energies 15 5880
Google Scholar
[21] Zhou Z W, Gong H Y, You J, Liu S B, He J L 2021 Mater. Today Commun. 28 102507
Google Scholar
[22] 周勇 2024 测绘与空间地理信息 47 217
Google Scholar
Zhou Y 2024 Geomatics & Spatial Information Technology 47 217
Google Scholar
[23] Li X, Ke S C, Li Y, Jin W, Fu X H, Fu G W, Bi W H 2024 Opt. Laser Technol. 176 110973
Google Scholar
DownLoad:
Metrics
- Abstract views: 371
- PDF Downloads: 4
- Cited By: 0
