Simultaneous fault detection in satellite power systems using deep autoencoders and classifier chain

M. Ganesan () and R. Lavanya ()
Additional contact information
M. Ganesan: Amrita Vishwa Vidyapeetham
R. Lavanya: Amrita Vishwa Vidyapeetham

Telecommunication Systems: Modelling, Analysis, Design and Management, 2023, vol. 83, issue 1, No 1, 15 pages

Abstract: Abstract A satellite system’s health is heavily dependent on the proper functioning of the Satellite Power System (SPS), which is regarded as the core component of a satellite. Fault detection and diagnosis (FDD) plays a vital role in maintaining the stable and efficient operation of the SPS and ensuring the success of a satellite mission. Automated FDD can reduce the burden and false alarm rate associated with manual level checking of individual sensors, by effectively leveraging the correlation between sensor measurements. In many real-world applications, multiple faults can occur simultaneously and SPS is not an exception. Simultaneous fault diagnosis is especially challenging, involving detection of multiple faults occurring concurrently. In this paper, this problem is addressed using a multilabel classification model. A Deep Autoencoder and Random Forest based Classifier Chain is employed for this purpose. The proposed model is used not only for fault detection and classification, but also for localizing single as well as simultaneous sensor faults in SPS. NASA’s Advanced Diagnostic and Prognostic Testbed (ADAPT) dataset has been used for validating the system, yielding an accuracy as high as 94.63% and precision, recall, and F1-score of 0.95, 0.91 and 0.93 respectively.

Keywords: Autoencoder; Classifier chain; Deep learning; Multilabel classification; Random forest; Satellite power system; Simultaneous Faults (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11235-023-00998-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:telsys:v:83:y:2023:i:1:d:10.1007_s11235-023-00998-3

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/11235

DOI: 10.1007/s11235-023-00998-3

Access Statistics for this article

Telecommunication Systems: Modelling, Analysis, Design and Management is currently edited by Muhammad Khan

More articles in Telecommunication Systems: Modelling, Analysis, Design and Management from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().