Combined Transmission Laser Spectrum of Core-Offset Fiber and BP Neural Network for Temperature Sensing Research
WANG Fang1,2, ZHU Han1, LI Yun-peng1, LIU Yu-fang1, 2*
1. College of Physics and Electrical Engineering, Henan Normal University, Xinxiang 453007, China 2. Infrared Optoelectronic Science and Technology Key Laboratory of Henan Province, Xinxiang 453007, China
Abstract：When studying the wavelength response to the temperature of the single mode fiber interference laser spectrum，a three layer BP neural network model is built to solve the problem of high complexity and low accuracy of temperature measurement system. With the Discussion of the parameters of network model, we obtain the optimal network structure by comparing the data acquisition which is the laser wavelength corresponding to its temperature trained by BP neural network. With network training completed and the wavelength of input laser reached the specified value, the corresponding temperature prediction can be obtained from the output layer. In conclusion, it shows a clear correlation between the predictive value and the actual value, i.e. the former is approximately equal to the latter. The correlation coefficients of the calibration and prediction are 0.999 61 and 0.979 27, respectively; while the standard errors of the calibration and prediction are 0.017 5 and 0.144 0, respectively, and the average relative error of prediction set is 0.17%. The residual predictive deviation (RPD), obtained theoretically, is 5.258 3. RPD>3. It indicates that the calibration effect is good, and the model can be used for practical testing. In addition, the algorithm is also applied to the system of double coupled structure with single-mode core-offset fiber and correction for the temperature measurement. The results show that BP neural network method can deal with the nonlinear relationship between the laser spectral data and the temperature in the optical fiber temperature measurement system. The correlation and the average relative error between the predicted temperature and the true temperature are 0.996 58 and 0.63%, respectively. The precision and stability of the fiber optic temperature sensor are significantly improved. At the same time, the feasibility of the proposed algorithm is verified in the fiber optical sensor system. It also provides a new way for the accurate measurement of pressure, curvature and other physical quantities of the core-offset fiber.
王 芳1, 2，朱 晗1，李云鹏1，刘玉芳1, 2* . 错位光纤干涉激光谱结合BP神经网络的温度传感研究 [J]. 光谱学与光谱分析, 2016, 36(11): 3732-3736.
WANG Fang1,2, ZHU Han1, LI Yun-peng1, LIU Yu-fang1, 2* . Combined Transmission Laser Spectrum of Core-Offset Fiber and BP Neural Network for Temperature Sensing Research. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(11): 3732-3736.
[1] Li Lecheng, Xia Li, Xie Zhenhai, et al. Optics Express, 2012, 20(10): 11109. [2] Han Wei, Tong Zhengrong, Cao Ye. Optics Communications，2014，321：134. [3] Zhang Jing, Sun Hao, Rong Qiangzhou, et al. Chinese Optics Letters, 2012，10(7): 070607. [4] Sun Hao, Yang Shen, Zhang Xiaolei, et al. Optics Communications, 2015，340：39. [5] Li X W, Cho S J, Kim S T. Optics Communications, 2014，315: 147. [6] Ding H Q, Lu Q P, Gao H Z, et al. Biomedical Optics Express, 2014，5(4): 1145. [7] LIU Tao, LI Yong-feng，HUANG Wei(刘 涛, 李永峰, 黄 威). Infrared and Laser Engineering(红外与激光工程), 2012，41(9): 2304. [8] Zhao Yong, Bai Lu, Wang Qi. Optics Communications，2013，309：328. [9] Hao Xia, Tong Zhengrong, Zhang Weihua, et al. Optics Communications, 2015，335：78. [10] Gao X J, Huang T W, Wang Z Y, et al. Cogn. Comput., 2014, 6: 331. [11] José P, Leonardo T, Patricia M. Soft Comput, 2014，18: 1603.
