摘要
基于光纤应变分布与布里渊散射谱频移的关系，提出了利用广义回归神经网络提取布里渊谱的应变特征方法。将布里渊谱的频率、增益分别作为广义回归神经网络的输入矢量和目标矢量，对广义回归神经网络进行训练和仿真，计算出调节权值和阈值，从而获得更加精确的布里渊谱频移。仿真实验结果和理论分析表明，与非线性最小二乘法、反向传播神经网络、径向基函数网络预测布里渊谱的应变特征相比，广义回归神经网络能够获得更精确的布里渊谱特征，相应的光纤应力误差最小，在1％之内。
The method of extracting Brillouin spectrum characteristics by using the general regression neural network is proposed based on the relationship between the optical fiber strain and the Brillouin spectrum frequency shift. The Brillouin spectrum frequency shift and gain are taken as the input vector and target vector of general regression neural network, respectively. Then the general regression neural network is trained and simulated. The more accurate Brillouin spectrum frequency shift can be calculated with the obtained weight and threshold. Experimental results and theoretical analysis show that the Brillouin spectral feature and optical fiber strain obtained by using the general regression neural network are more accurate compared with the nonlinear least square method, back propagation neural network and radial basis function network, and the corresponding optical fiber strain error is the least （within 1% ）.
出处
《中国激光》
EI
CAS
CSCD
北大核心
2013年第B12期152-157,共6页
Chinese Journal of Lasers
关键词
光纤光学
布里渊谱
广义回归神经网络
光纤传感器
fiber optics
Brillouin spectrum
general regression neural network
optical fiber sensor
