Surrogate Model-Based Calibration of a Flying Satellite Battery Digital Twin

At the European Space Agency (ESA), Modeling and Simulation (M&S) plays a fundamental role during the lifetime of a spacecraft, being used from the design phase to the testing and during operations in space. In particular, the European Space Operation Center (ESOC) makes use of M&S tools for various tasks such as monitoring and control, procedure validations, training, maintenance, planning and scenarios investigation, to mention a few. Moreover, moving towards the digital twin paradigm, simulation models are gaining growing attention with the expectation to provide ultra-fidelity capabilities to represent the live status and dynamics of flying spacecraft. In this respect, M&S tools embed general physics-based models and disciplines characterized by configurable parameters which have to be calibrated in order to mimic the behavior of the actual flying spacecraft. However, their calibration requires a large number of simulations which are unfeasible to be obtained through computationally expensive high-fidelity simulation models. In this light, the present work proposes the use of a surrogate model-based approach for the calibration of simulation models of spacecraft. The approach integrates a computationally inexpensive deep-learning-based surrogate model. The approach's effectiveness is shown by its application to real flying Earth observation satellite data and simulation models.

Keywords: Spacecraft, European Space Agency (ESA), Modeling and simulation, Calibration, Deep-Learning, Artificial intelligence, Surrogate model, Spacecraft, Satellite battery, Digital twin.

Download PDF