Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

Christopher Goetze, Tim Schlippe, Daniel Lakey

Abstract

Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.

Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

Abstract

Spacecraft anomaly detection is critical for mission safety, yet deploying sophisticated models on-board presents significant challenges due to hardware constraints. This paper investigates three approaches for spacecraft telemetry anomaly detection -- forecasting & threshold, direct classification, and image classification -- and optimizes them for edge deployment using multi-objective neural architecture optimization on the European Space Agency Anomaly Dataset. Our baseline experiments demonstrate that forecasting & threshold achieves superior detection performance (92.7% Corrected Event-wise F0.5-score (CEF0.5)) [1] compared to alternatives. Through Pareto-optimal architecture optimization, we dramatically reduced computational requirements while maintaining capabilities -- the optimized forecasting & threshold model preserved 88.8% CEF0.5 while reducing RAM usage by 97.1% to just 59 KB and operations by 99.4%. Analysis of deployment viability shows our optimized models require just 0.36-6.25% of CubeSat RAM, making on-board anomaly detection practical even on highly constrained hardware. This research demonstrates that sophisticated anomaly detection capabilities can be successfully deployed within spacecraft edge computing constraints, providing near-instantaneous detection without exceeding hardware limitations or compromising mission safety.

Paper Structure

This paper contains 23 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Anomaly Detection in Spacecraft Telemetry
  4. Forecasting & Threshold
  5. Direct Classification
  6. Image Classification
  7. Neural Architecture Search and Optimization
  8. Spacecraft Telemetry Data
  9. Experimental Setup
  10. Forecasting & Threshold Models
  11. Direct Classification
  12. Image Classification
  13. ESA-ADB
  14. Evaluation Metrics
  15. Optimization for Edge Devices
  16. ...and 8 more sections

Figures (3)

  • Figure 1: Pareto Front Plot for Forecasting & Threshold.
  • Figure 2: Pareto Front Plot for Direct Classification.
  • Figure 3: Pareto Front Plot for Image Classification.