Certain Formation Flying missions rely on their orbital control thrusters to maintain the formation, making a Fault Detection and Isolation (FDI) system that is capable of detecting thruster faults very valuable. In addition, communication between satellites in a formation can be expensive. In this thesis, a distributed FDI approach was developed making use of Recurrent Neural Networks (RNNs), utilizing the already available relative position and velocity data as input.
To test the approach, a numerical simulation of a Virtual-Rigid-Body formation in low Earth orbit was developed in MATLAB. The RNNs were trained on noisy data from the simulation, utilizing the tensorflow library. The resulting system was analyzed and compared against a centralized Kalman-filter based approach, in detection capability, isolation capability and robustness. The developed approach showed overall worse performance, but offers reduced communication needs compared to the comparison method.

Lunar exploration initially started as a race between two superpowers to see who had the highest technical capabilities to send a human onto the Moon’s surface. Until recently, the frequency of Moon missions has been in decline, but in the last couple years there has been an increasing interest in returning. Scientific studies and observations will be performed and will give humanity a better understanding of the solar system and our place in it. As a result there will be a need for a direct communication line between the lunar surface and Earth, such that rovers can be controlled in real-time and immediately relay their data back, independent of their location on the Moon.