光纤陀螺刻度因子的建模方法

Modeling method for scale factor of fiber optic gyroscope

针对低精度光纤陀螺(FOG)刻度因子线性度较差的问题,提出了采用径向基函数(RBF)神经网络对刻度因子进行建模的方法,以减小光纤陀螺输出误差。通过测量数据对 RBF 神经网络进行训练,获得神经网络参数,根据神经网络结构和参数可以得到非线性刻度因子的解析表达式,将其作为刻度因子的模型,来提高 FOG 的精度。同时将 RBF 神经网络对刻度因子进行建模的结果与传统的建模结果进行了比较,验证了采用 RBF 神经网络对低精度刻度因子建模是非常有效的。

In view of low accuracy linearity in scale factor of fiber optic gyroscope(FOG), a method of modeling for scale factor with Radial Basis Function(RBF) neural network is proposed and this reduces the output error of fiber optic gyroscope. RBF neural network is trained by measured data and thus the parameters of the neural network can be obtained. Analytical expression for nonlinear scale factor can be obtained according to the structure and parameters of the neural network. The accuracy of fiber optic gyroscope is improved by using the expression as model of scale factor. Meanwhile the modeling results of RBF neural network for scale factor are compared with the traditional modeling results, it demonstrates that modeling for low accuracy scale factor with BRF neural network is very effective.