摘要
为了使基于偏振调制原理的光纤电流传感器(FOCS)的温度误差达到工程应用要求,从理论上分析了FOCS的温度误差特性,分别采用最小二乘法、BP神经网络对FOCS进行温度补偿,实现了传感器的非线性温度误差校正,两种温度补偿算法的实验结果进行对比分析。结果表明,基于神经网络算法的温度补偿结果优于最小二乘法的补偿效果。最后,利用FOCS全温实验对其进行重复性实验验证,经神经网络算法校正后,FOCS在-5℃~+50℃范围内的温度误差均小于0.5%。
The temperature error characteristics of the fiber optic current sensor(FOCS) based on polarization modulation principle is theoretically analyzed to meet the requirement of engineering application. The temperature compensation of FOCS is realized by least squares method and BP neural network respectively. The nonlinear tem?perature error correction is realized. And the experimental results of the two temperature compensation algorithms are compared and analyzed. The result shows that the temperature compensation result based on neural network al?gorithm is better than that of least squares method. The full temperature experiment of FOCS is used to verify the re?producibility. The experimental results show that after corrected by the neural network algorithm, the temperature error of FOCS in the range of from -5 ℃ to +50 ℃ is less than 0.5%.
引文
[1]徐金涛,王英利,王嘉,等.全光纤电流传感器在智能电网中的应用[J].电器工业,2011,(1):53-57.
[2]王志,初凤红.光纤电流传感器技术研究进展[J].传感技术学报,2014,51(10):100002-1.
[3]Barczak K.Application of photonic crystal fiberin optical fiber current sensors[J].Acta Physica Polonica A,2012,122(5):793-795.
[4]Miklos Lenner,Robert Wuest,Andreas Frank,et al.Thermal tuning of fiber quarter-wave retarders for temperature compensation of fiber-optic current sensors[J].OSASM3C,3.
[5]郭颖,周王民,马戎,等.基于神经网络的光纤光栅电流传感器的温度补偿[J].传感技术学报,2008,21(9)):1528-1531.
[6]王红星,关远鹏,胡春潮,等.全光纤电流互感器温度误差研究[J].电力自动化设备,2017,37(12):200-204.
[7]刘峰.扭转型高双折射光纤应用及制备的研究[D].杭州:浙江大学,2016.
[8]赵晶晶.光纤电流互感器光路技术研究[D].北京:北京航空航天大学,2005.
[9]周志华.机器学习[M].北京:清华大学出版社,2016.
[10]廖星宇.深度学习入门之Pytorch[M].北京:电子工业出版社,2017.