Enhancing Medium-Orbit Satellite Orbit Prediction: Application and Experimental Validation of the BiLSTM-TS Model DOI Open Access
Yang Guo,

Bingchuan Li,

Xueshu Shi

и другие.

Electronics, Год журнала: 2025, Номер 14(9), С. 1734 - 1734

Опубликована: Апрель 24, 2025

To mitigate the limited accuracy of Simplified General Perturbations 4 (SGP4) model in predicting medium-orbit satellite trajectories, we propose an enhanced methodology integrating deep learning with traditional algorithms. The developed BiLSTM-TS forecasting framework comprises a Bidirectional Long Short-Term Memory (BiLSTM) network, trend analysis module (T), and seasonal decomposition (S). This architecture effectively captures sequential dependencies, variations, periodic patterns within time series data, thereby improving prediction interpretability. In our experimental validation, chose Beidou-2 M6 (C14), GSAT0203 (GALILEO 7), Global Positioning System (GPS) named GPS BIIR-13 (PRN 02) as representative satellites. Satellite position data derived from conventional orbital models were input into for statistical to predict deviations. These predicted errors subsequently combined SGP4 outputs obtained through Two-Line Element set (TLE) minimize overall trajectory inaccuracies. Using BeiDou-2 (C14) case study, results indicated that implementation achieved significant error reduction; mean-squared along X-axis was reduced 0.0309 km2, mean absolute 0.1245 km, maximum constrained 0.4448 km.

Язык: Английский

Enhancing Medium-Orbit Satellite Orbit Prediction: Application and Experimental Validation of the BiLSTM-TS Model DOI Open Access
Yang Guo,

Bingchuan Li,

Xueshu Shi

и другие.

Electronics, Год журнала: 2025, Номер 14(9), С. 1734 - 1734

Опубликована: Апрель 24, 2025

To mitigate the limited accuracy of Simplified General Perturbations 4 (SGP4) model in predicting medium-orbit satellite trajectories, we propose an enhanced methodology integrating deep learning with traditional algorithms. The developed BiLSTM-TS forecasting framework comprises a Bidirectional Long Short-Term Memory (BiLSTM) network, trend analysis module (T), and seasonal decomposition (S). This architecture effectively captures sequential dependencies, variations, periodic patterns within time series data, thereby improving prediction interpretability. In our experimental validation, chose Beidou-2 M6 (C14), GSAT0203 (GALILEO 7), Global Positioning System (GPS) named GPS BIIR-13 (PRN 02) as representative satellites. Satellite position data derived from conventional orbital models were input into for statistical to predict deviations. These predicted errors subsequently combined SGP4 outputs obtained through Two-Line Element set (TLE) minimize overall trajectory inaccuracies. Using BeiDou-2 (C14) case study, results indicated that implementation achieved significant error reduction; mean-squared along X-axis was reduced 0.0309 km2, mean absolute 0.1245 km, maximum constrained 0.4448 km.

Язык: Английский

Процитировано

0