基于KPCA和数据处理组合方法神经网络的半球谐振陀螺温度建模补偿方法

张晨,汪立新,孔祥玉

Temperature modeling and compensation method of hemispherical resonator gyro based on KPCA and grouped method of data handling neural network

Chen ZHANG,Lixin WANG,Xiangyu KONG

表 1 样本初选特征向量的统计特性

Tab.1 Statistical characteristics of primary feature vectors for samples

特征 最大值 最小值 平均值 $ \sqrt f $ 69.9349 69.9309 69.9340 $ f $ 4890.8881 4890.3364 4890.7693 $ {f^2} $ 2.319 2×107 2.391 5×107 2.392 0×107 $ {\mathrm{d}}f $ 0.0042 −0.0005 0.0008 $ \sqrt f \cdot {\mathrm{d}}f $ 0.2950 −0.0329 0.0540 $ f \cdot {\mathrm{d}}f $ 20.6294 −2.3008 3.7751 $ {f^2} \cdot {\mathrm{d}}f $ 1.008 9×105 −1.125 3×104 1.846 3×104 $ {({\mathrm{d}}f)^2} $ 1.7795×10−5 0 1.6851×10−6 $ \sqrt f \cdot {({\mathrm{d}}f)^2} $ 0.0012 0 1.1785×10−4 $ f \cdot {({\mathrm{d}}f)^2} $ 0.0870 0 0.0082 $ {f^2} \cdot {({\mathrm{d}}f)^2} $ 425.5719 0 40.3035