Space object orbit forecasting method based on data fusion

• Main Authors: WANG ZHELONG, CHU QINGHAO, HOU PENGRONG
• Format: Patent
• Language: Chinese; English
• Published: 30.04.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; GYROSCOPIC INSTRUMENTS; MEASURING; MEASURING DISTANCES, LEVELS OR BEARINGS; NAVIGATION; PHOTOGRAMMETRY OR VIDEOGRAMMETRY; PHYSICS; SURVEYING; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING

The invention relates to the technical field of aerospace and the technical field of artificial intelligence, and provides a space object orbit forecasting method based on data fusion, which integrates a traditional orbit forecasting model and a machine learning method, constructs a hybrid model adopting a parallel structure, does not depend on a complex numerical simulation environment and high-precision orbit tracking data, and improves the orbit forecasting accuracy. Only TLE and a traditional SGP4/SDP4 model are used for research, and the method is suitable for improving the accuracy and precision of orbit prediction of space objects. According to the method, the orbit propagation state vector is predicted, and meanwhile, the uncertainty of the predicted value is provided, so that the orbit prediction precision is improved on the basis of not being lower than the existing orbit prediction capability and stability. 本发明涉及航空航天技术领域及人工智能技术领域，提供一种基于数据融合的空间物体轨道预报方法，通过融合传统轨道预报模型与机器学习方法，构建采用并联结构的混合模型，不依赖复杂的数值仿真环境以