Anomaly detection using deep learning respecting the resources on board a CubeSat

Ross Horne, Sjouke Mauw, Andrzej Mizera, Jan Thoemel

Research output: Contribution to journalArticlepeer-review

Abstract

We explore the feasibility of onboard anomaly detection using artificial neural networks for CubeSat systems and related spacecraft where computing resources are limited. We gather data for training and evaluation using a CubeSat in a laboratory for a scenario where a malfunctioning component affects temperature fluctuations across the control system. This data, published in an open repository, guides the selection of suitable features, neural network architecture, and metrics comprising our anomaly detection algorithm. The precision and recall of the algorithm demonstrate improvements as compared to out-of-limit methods, whereas our open-source implementation for a typical microcontroller exhibits small memory overhead, and hence may coexist with existing control software without introducing new hardware. These features make our solution feasible to deploy on board a CubeSat, and thus on other, more advanced types of satellites.
Original languageEnglish
Pages (from-to)1-14
Number of pages14
JournalJournal of Aerospace Information Systems
Early online date23 Aug 2023
DOIs
Publication statusE-pub ahead of print - 23 Aug 2023

Keywords

  • satellites
  • artificial neural network
  • telemetry
  • algorithms and data structures
  • anomaly detection
  • CubeSat
  • data-driven system monitoring
  • spacecraft health monitoring
  • complex data analysis
  • deep learning

Fingerprint

Dive into the research topics of 'Anomaly detection using deep learning respecting the resources on board a CubeSat'. Together they form a unique fingerprint.

Cite this