Machine Learning-based vs Deep Learning-based Anomaly Detection in Multivariate Time Series for Spacecraft Attitude Sensors
This work addresses anomaly detection for spacecraft safety, but it is incremental as it compares existing methods without introducing new techniques.
The study compared machine learning and deep learning methods for detecting stuck values in spacecraft attitude sensor data, finding performance differences and discussing their interpretability and generalization.
In the framework of Failure Detection, Isolation and Recovery (FDIR) on spacecraft, new AI-based approaches are emerging in the state of the art to overcome the limitations commonly imposed by traditional threshold checking. The present research aims at characterizing two different approaches to the problem of stuck values detection in multivariate time series coming from spacecraft attitude sensors. The analysis reveals the performance differences in the two approaches, while commenting on their interpretability and generalization to different scenarios.