Self-Adaptive Reconstruction of Spacecraft Irregular Sampling Telemetry Data Based on Neural Ordinary Differential Equation

Spacecraft telemetry data is crucial for assessing the health of a spacecraft, but it often contains missing or redundant information that affects data quality. To ensure accurate status assessments, it is necessary to research methods for reconstructing telemetry data. Since spacecraft are subject to many short-term disturbances, the number of missing points or redundancy in the data on a short time scale is highly random, so it is difficult to reconstruct the data using traditional deep learning models (such as recurrent neural networks). Therefore, this paper proposes a self-adaptive reconstruction method of spacecraft telemetry data based on a neural ordinary differential equation (NODE). First, this paper uses a time-continuous model based on NODE to better learn the long-term continuity of data. On this basis, self-adaptive reconstruction windows are constructed on the time scale for irregular sampling telemetry data (with only one missing condition in each window). Afterward, the NODE model is used to adaptively reconstruct the data. Finally, a real spacecraft telemetry dataset is used to verify the method proposed in this paper.