Anomaly Detection and Fault Prediction in Spacecraft Sensors

Authors

  • Nandini S D PG Scholar, Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India. Author
  • Prof. Indra C Associate professor, Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India. Author
  • Harshitha L PG Scholar, Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India. Author
  • Nayana B PG Scholar, Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India. Author
  • Nithyashree K L PG Scholar, Department of MCA, P.E.S. College of Engineering, Mandya, Karnataka, India. Author

DOI:

https://doi.org/10.47392/IRJAEH.2026.0616

Keywords:

Spacecraft telemetry, anomaly detection, fault prediction, predictive maintenance, Random Forest, SVM, LSTM Autoencoder, NASA SMAP, MSL

Abstract

This paper presents a hybrid machine learning and deep learning framework for spacecraft sensor anomaly detection and fault prediction using NASA SMAP and MSL telemetry datasets. The framework combines Random Forest, Support Vector Machine (SVM), and LSTM Autoencoder models to improve anomaly detection accuracy and predictive maintenance capabilities. Experimental evaluation demonstrates strong classification performance, high ROCAUC values, and effective real-time monitoring through a dashboard-driven architecture.

Downloads

Download data is not yet available.

Downloads

Published

2026-07-20

Issue

Vol. 4 No. 07 (2026): IRJAEH Vol.04 Issue 07- [JULY 2026]

Section

Research Articles

License

Copyright (c) 2026 International Research Journal on Advanced Engineering Hub (IRJAEH)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

Anomaly Detection and Fault Prediction in Spacecraft Sensors. (2026). International Research Journal on Advanced Engineering Hub (IRJAEH), 4(07), 4690-4694. https://doi.org/10.47392/IRJAEH.2026.0616