Frangipani
Top 20
Maybe I missed it or forgotten about but this project appears to have only just started at the beginning of Sept with OHB, fortiss etc.
AI4FDIR - fortiss
The research projects at fortiss Institut contribute to the sustainable development of research and economy. All projects are based on the basic competence "software-intensive systems and services".www.fortiss.org
AI4FDIR
AI-based system for fault detection, recovery, and resource management in satellites
AI4FDIR
AI4FDIR is an ESA-funded project led by OHB System AG to develop an AI-based framework for autonomous fault detection, isolation, and recovery (FDIR), as well as constellation-level management and resource optimization in satellite telecommunication systems. By combining machine learning, deep learning, and neuromorphic computing, the project targets a tenfold reduction in both operational outage time and the time to restore nominal service. The consortium—comprising OHB DC, OHB Hellas, SATE, Kepler, and fortiss—will validate the approach through simulators and hardware-in-the-loop platforms, including BrainChip’s Akida neuromorphic processors. fortiss will implement a neuromorphic proof-of-concept for spacecraft-level FDIR.
Project description
The project addresses the need for greater autonomy in managing large satellite constellations, where traditional ground-based fault management is costly, slow, and increasingly impractical. The main challenge is to detect, isolate, and resolve failures on board in real time, while predicting potential degradations before they affect service.
To tackle this, the consortium combines advanced AI methods with neuromorphic hardware, enabling fast, low-power decision-making directly on spacecraft. This proof-of-concept approach will demonstrate how predictive monitoring and autonomous recovery can reduce outage and restoration times by an order of magnitude and pave the way for resilient, self-managing space systems.
Research contribution
fortiss will investigate CNN-based classification and detection algorithms on the BrainChip Akida platform. In addition, we will explore pattern-matching techniques, encoders, and complementary network architectures to process heterogeneous multi-channel inputs. As a first step, we will use the public ESA anomaly dataset to identify suitable network models for fault detection. Building on these results, we will validate the implemented algorithms using real-time data from Kepler and the OHB constellation simulator.
Funding
European Space Agency and OHB System
Project duration
01.09.2025 - 31.08.2027
Your contact
Dr. Axel von Arnim
+49 89 3603522 538
vonarnim@fortiss.org
Your contact
Priyadarshini Kannan
+49 89 3603522 275
kannan@fortiss.org
Project partner
View attachment 92129
Quote from the above fortiss project webpage @Fullmoonfever shared last month:
(https://www.fortiss.org/en/research/projects/detail/ai4fdir):
“AI4FDIR
AI4FDIR is an ESA-funded project led by OHB System AG to develop an AI-based framework for autonomous fault detection, isolation, and recovery (FDIR), as well as constellation-level management and resource optimization in satellite telecommunication systems. By combining machine learning, deep learning, and neuromorphic computing, the project targets a tenfold reduction in both operational outage time and the time to restore nominal service. The consortium—comprising OHB DC, OHB Hellas, SATE, Kepler, and fortiss—will validate the approach through simulators and hardware-in-the-loop platforms, including BrainChip’s Akida neuromorphic processors. fortiss will implement a neuromorphic proof-of-concept for spacecraft-level FDIR.[…] fortiss will investigate CNN-based classification and detection algorithms on the BrainChip Akida platform.”
#spacetechexpo | Axel von Arnim
Our ESA project AI4FDIR, about anomaly detection in SATCOM constellations, met today at #SpaceTechExpo in Bremen. Partners OHB, SATE and ESA exchanged on the scope of the project. I was also impressed by the vibrant diversity of space players and the adoption of edge AI in many space...
:
