光纤陀螺温度漂移模型的PPLN辨识

环境温度变化造成的较大温度漂移始终是制约光纤陀螺(FOG)性能提高的重要因素．FOG温度漂移本质上是一组与温度有关的多变量非线性时间序列，为此采用投影寻踪学习网络(PPLN)方法建立新的FOG温度漂移模型．该方法结合了统计学中投影寻踪算法节点函数灵活的非参数估计特点和人工神经网络的自学习功能，具有简捷的网络结构和良好的鲁棒性能，对未知模型辨识能力较强．将该方法应用于某型FOG温漂模型实测数据的辨识中，经验证表明其具有良好的预测效果．

Temperature Drift Modeling of Fiber Optical Gyroscope Based on Projection Pursuit Learning Network

Projection pursuit learning network (PPLN) was employed to establish the temperature drift of fiber optical gyroscope (FOG). The large temperature drift caused by the variation of environmental temperature is the main factor to holdback the FOG performance improving. Essentially, the FOG's temperature drift is a group of nonlinear time series related with temperature changing. The PPLN algorithm integrates the advantage of artificial neural network (ANN) with a nonparametric statistical technique, projection pursuit algorithm (PP), which is capable of providing less network neurons and good robustness. The proposed algorithm was described, and the method was applied to the analysis of a certain FOG's temperature drift's model. Good predication of independent tested data was verified.