A Self-Supervised Task for Fault Detection in Satellite Multivariate Time Series

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cena, Carlo, Bucci, Silvia, Balossino, Alessandro, Chiaberge, Marcello
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913592940429312
author Cena, Carlo
Bucci, Silvia
Balossino, Alessandro
Chiaberge, Marcello
author_facet Cena, Carlo
Bucci, Silvia
Balossino, Alessandro
Chiaberge, Marcello
contents In the space sector, due to environmental conditions and restricted accessibility, robust fault detection methods are imperative for ensuring mission success and safeguarding valuable assets. This work proposes a novel approach leveraging Physics-Informed Real NVP neural networks, renowned for their ability to model complex and high-dimensional distributions, augmented with a self-supervised task based on sensors' data permutation. It focuses on enhancing fault detection within the satellite multivariate time series. The experiments involve various configurations, including pre-training with self-supervision, multi-task learning, and standalone self-supervised training. Results indicate significant performance improvements across all settings. In particular, employing only the self-supervised loss yields the best overall results, suggesting its efficacy in guiding the network to extract relevant features for fault detection. This study presents a promising direction for improving fault detection in space systems and warrants further exploration in other datasets and applications.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02861
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Self-Supervised Task for Fault Detection in Satellite Multivariate Time Series
Cena, Carlo
Bucci, Silvia
Balossino, Alessandro
Chiaberge, Marcello
Machine Learning
Robotics
In the space sector, due to environmental conditions and restricted accessibility, robust fault detection methods are imperative for ensuring mission success and safeguarding valuable assets. This work proposes a novel approach leveraging Physics-Informed Real NVP neural networks, renowned for their ability to model complex and high-dimensional distributions, augmented with a self-supervised task based on sensors' data permutation. It focuses on enhancing fault detection within the satellite multivariate time series. The experiments involve various configurations, including pre-training with self-supervision, multi-task learning, and standalone self-supervised training. Results indicate significant performance improvements across all settings. In particular, employing only the self-supervised loss yields the best overall results, suggesting its efficacy in guiding the network to extract relevant features for fault detection. This study presents a promising direction for improving fault detection in space systems and warrants further exploration in other datasets and applications.
title A Self-Supervised Task for Fault Detection in Satellite Multivariate Time Series
topic Machine Learning
Robotics
url https://arxiv.org/abs/2407.02861