Spacecraft cannot be manually inspected, so instead humans must look at graphs of sensor output to identify problems. Humans cost money and miss details.

What it does

Given example data of nominal spacecraft behavior, abnormalities are detected in real time and users are alerted.

How it works

  1. Simlualted telemetry is developed for both periodic and mode-dependent variables.
  2. Predictions are framed as a time-series forecasting model, with regression on a sliding window using a multilayer perceptron neural network on one set of training data.
  3. Bounds of uncertainty are developed using a random forest regressor on a second set of training data.
  4. Simulated real time data, with anomalies, is displayed in the COSMOS command and telemetry system
  5. After training, the system produces "blue limit" bounds in real time for incoming data, and alerts the user when an anomaly deviates from these bounds.

Biggest challenges

  1. Dynamically determining levels of uncertainty for data with variable noise
  2. Using interprocess communication to integrate with COSMOS


Unlike other research in this area, this project:

  1. Handles multiple modes of operation, with different levels of uncertainty. For example, acceleration should be zero if the spacecraft is not maneuvering, but will be highly variable during maneuvers
  2. Is capable of analyzing many different variables at the same time
  3. Automatically detects anomalies and produces real-time alerts based on live data

This creates a "plug and play" system that can be used by operators without machine learning experience.

What we learned

Scikit-learn is awesome.

What's next for ML for Satellite Anomaly Detection

Testing on real spacecraft telemetry (which is not available for use in a hackathon)

Built With

Share this project: