Research on short-term prediction accuracy of BDS-3 clock bias based on BiL-STM model
This paper proposes an enhanced model for BeiDou clock bias prediction,which extends the traditional LSTM to BiLSTM and introduces three adaptive hyperparameter matching algorithms(PSO,SSA,BOA)to improve short-term fore-cast accuracy.Firstly,LSTM is optimized to establish BiLSTM model,and three hyperparameter options have corresponding application scopes.Secondly,detailed steps for prediction with the hyperparameter-optimized BiLSTM model are outlined.Fi-nally,the comparative experiments which consider the factor of the orbit types and sample intervals,are conducted for 1,6,and 12 hours with the clock products provided by GFZ.The results show that the hyperparameter-optimized BiLSTM outper-forms QP,GM,LSTM,and traditional BiLSTM models with an average improvement of 86.21％,83.32％,69.99％,and 55.17％.As for the three optimization schemes,SSA exhibits the best overall optimization,and PSO and BOA are more suit-able for the IGSO and MEO satellites,respectively.Although the hyperparameter-optimized BiLSTM model takes a long time to train,its rapid forecasting speed can be guaranteed for the requirement of real-time applications.
万方数据
维普
