ADIA
The detection and treatment of anomalies on board spacecraft is currently largely based on the evaluation of telemetry data by experts on the ground. The status data (also known as housekeeping) periodically recorded by the spacecraft, such as temperatures, voltages, currents and switching states, is stored on board, transmitted to the control center when it flies over a ground station and compared there with the target values and permissible limit values in order to detect existing or imminent malfunctions.
As part of the ADIA (Autonomous Diagnostic System for Satellites) project, a system was developed that is capable of independently analyzing imminent or existing faults on board satellites and determining their causes. This can save valuable time in detecting and rectifying problems, which can contribute to increasing the operational safety of satellites.
The software makes the diagnosis using an expert system based on heuristics, which checks a predefined set of potentially occurring symptoms in each cycle, maps these to a set of pre-formulated possible causes in the event of positive findings and then outputs the determined diagnoses in order of probability.
The project is being carried out in close cooperation with the Chair of Artificial Intelligence and Applied Computer Science (Computer Science VI) at the University of Würzburg and is being funded by the Space Agency of the German Aerospace Center (DLR) under the funding code 50RM1231 with funds from the Federal Ministry of Economics and Technology (BMWi).
Contact:
Gerhard Fellinger (Project Manager)
