光纤光栅传感阵列的数据融合分析

针对一种结合神经网络技术对光纤光栅传感阵列信号进行分析的方案.以光纤光栅为传感元件,混凝土简支梁模板为研究对象,BP神经网络为信号处理方法,研究了光纤光栅传感阵列和BP神经网络技术在载荷应变损伤监测中的应用.通过有限元法对模板试件的应变分布进行分析,确定光纤光栅应变传感阵列的合理位置,用液压机进行加载实验.通过BP神经网络对这些离散的应变信号进行数据融合,反向分析模板试件的载荷.实验表明,在加载范围0～110 kN内,识别样本相对误差均在3%以下,均方误差小于1 kN.

Fiber Bragg Grating Sensing Array based on Information Fusion Analysis

This paper presents a signal analysis method for fiber Bragg grating sensing array based on neural network technology. The application of fiber Bragg grating sensor and neural network in inspection of strain damage, in which fiber Bragg grating was used as sensing element, concrete simple supporting plank was investigated, and neural network was utilized as signal processing means. We analyzed the distribution of moulding board strain by the finite element method and positioned the fiber Bragg grating array. We sampled the discrete strain signals in experiment and fused the information to deduce the load value reversely by means of neural network. Experimental results illustrate that in load range of 0KN to110KN, the relative error of sample identification is under 3%, Mean Square Error(MSE) is less than 1kN.