A projection pursuit learning network, for modeling temperature drift of FOG

The large temperature drift caused by variation of environmental temperature is the main factor affecting the performance of fiber optical gyroscope (FOG). Considering the fact that the temperature drift is a group of multi-variable nonlinear time series related with temperature, a new method named projection pursuit learning network (PPLN) is employed in this paper to model the temperature drift of FOG. The PPLN integrates the advantages of artificial neural network (ANN) and projection pursuit algorithm (PP), and is capable of providing less network neurons and good robustness. Numerical results from measured temperature drift data of FOG verify the effectiveness of the proposed method, and good predication of independent tested data is obtained.