Advanced Applications of Artificial Intelligence in Systems Engineering for Satellite Fault Prediction

Mohammad Ali Nezhad, Mostafa; Nasiri Sarvi, Mahdi

doi:10.22034/IJRRS.2026.9.1.5

Advanced Applications of Artificial Intelligence in Systems Engineering for Satellite Fault Prediction

Document Type : Original Research Article

Authors

Mostafa Mohammad Ali Nezhad

Mahdi Nasiri Sarvi

School of Advanced Technologies, Iran University of Science and Technology, Tehran, Iran

10.22034/IJRRS.2026.9.1.5

Abstract

Spacecraft fault prediction is difficult because flight telemetry is high-dimensional, non-stationary, and only sparsely labeled. This paper examines how artificial intelligence can be integrated into satellite systems engineering to support early warning and fault diagnosis without replacing deterministic fault detection, isolation, and recovery (FDIR) logic. The study compares Artificial Neural Networks (ANN), Support Vector Machines (SVM), Recurrent Neural Networks/Long Short-Term Memory (RNN/LSTM), and hybrid ANN-EKF models for representative AOCS, EPS, thermal, communication, and onboard-data-handling fault cases.
Because operational fault labels are limited, the revised methodology distinguishes between public spacecraft anomaly benchmarks such as SMAP/MSL, NASA Prognostics Center of Excellence degradation datasets, mission/event logs, and mission-representative fault-injection simulations. The dataset section now specifies source categories, labeling methods, telemetry variables, and sim-to-real differences. Performance is assessed using accuracy, precision, recall, F1-score, AUC/ROC, RMSE/MAE, execution time, false-alarm behavior, and interpretability through SHAP and LIME.
The results indicate that temporal models such as LSTM are most suitable for gradual degradation and drift-type anomalies, while SVM/PCA and rule-assisted classifiers remain useful when labeled data are small. Hybrid physics-informed AI is appropriate when subsystem dynamics are available. The paper further defines onboard feasibility conditions: training and validation are assumed to be ground-based, while onboard use is limited to lightweight inference subject to latency, memory, processor, power, and flight-software constraints. The contribution is therefore an AI-assisted monitoring architecture for satellite fault prediction, not a claim of fully autonomous flight qualification.

Keywords

Artificial Intelligence

Systems Engineering

Satellite Failure Prediction

Machine Learning

Deep Learning

Fault Detection and Isolation

Subjects

Reliability Engineering

[1] E. Venkatesan and V. Thangavel, “Autonomous fault detection and recovery in satellite systems using intelligent algorithms,” International Journal of Circuit, Computing and Networking, vol. 6, no. 2, pp. 96–101, 2025, https://doi.org/10.33545/27075923.2025.v6.i2b.109.

[2] I. Shafieenejad, M. Nourianpour, M. Banitalebi Dehkordi, and K. Ansari, “A comprehensive review of safety and risk management strategies in aerospace operations for human casualty mitigation,” International Journal of Reliability, Risk and Safety: Theory and Application, vol. 6, no. 1, pp. 111–130, 2023, https://doi.org/10.22034/IJRRS.2023.6.1.12.

[3] Y. Liu, J. Lei, S. Zeng, Y. Wang, and Z. Nian, “Design of satellite ground fault diagnosis system based on rule base,” ITM Web of Conferences, vol. 47, 2022, Art. no. 01013, https://doi.org/10.1051/itmconf/20224701013.

[4] A. Filippi, I. Dobreva, A. G. Klein, and J. R. Jensen, “Self-organizing map-based applications in remote sensing,” in Self-Organizing Maps, G. K. Matsopoulos, Ed. London, U.K.: InTechOpen, 2010, pp. 231–248, https://doi.org/10.5772/9163.

[5] I. Shafieenejad and M. Nourianpour, “A survey on enhancing aerospace system security, reliability, and productivity through blockchain and artificial intelligence integration,” International Journal of Reliability, Risk and Safety: Theory and Application, vol. 7, no. 1, pp. 103-114, 2024, https://doi.org/10.22034/IJRRS.2024.7.1.12.

[6] S. S. Ghasemi, A. Khamseh, and S. Iranban , “AI-based technology scouting process in high-tech industries for reducing R&D project risks: A qualitative thematic analysis,” International Journal of Reliability, Risk and Safety: Theory and Application, vol. 8, no. 1, 2025, https://doi.org/10.22034/IJRRS.2025.8.1.2.

[7] X. Zhang, H. Liu, Z. Chen, and J. Yang, “A digital twin-based approach for the fault diagnosis and health monitoring of a complex satellite system,” Symmetry, vol. 12, no. 8, 2020, Art. no. 1307, https://doi.org/10.3390/sym12081307.

[8] Z. Ma, Y. J. Wang, Y. D. Yang, Z. P. Wang, L. Tang, and S. Ackland, "Reinforcement learning-based satellite attitude stabilization method for non-cooperative target capturing,” Sensors, vol. 18, no. 12, 2018, Art. no. 4331, https://doi.org/10.3390/s18124331.

[9] G. El-Dalahmeh, M. R. Jabbarpour, B. Vo, and R. Kowalczyk, “Intelligent spacecraft attitude fault recovery using deep reinforcement learning,” IEEE Access, vol. 14, pp. 6238–6260, 2026, https://doi.org/10.1109/ACCESS.2026.3652508.

[10] Z. Peng and Q. Shen, “Fault-tolerant attitude control of flexible spacecraft via reinforcement learning,” Aerospace, vol. 13, no. 7, 2026, Art. no. 571, https://doi.org/10.3390/aerospace13070571.

[11] M. Hedayati, A. Barzegar, and A. Rahimi, “Fault diagnosis and prognosis of satellites and unmanned aerial vehicles: A review,” Applied Sciences, vol. 14, no. 20, 2024, Art. no. 9487, https://doi.org/10.3390/app14209487.

[12] Z. Chen, J. Xu, C. Alippi, S. X. Ding, Y. A. W. Shardt, T. Peng, and C. Yang, “Graph neural network-based fault diagnosis: A review,” arXiv, 2021, https://doi.org/10.48550/arXiv.2111.08185.

[13] F. Fourati and M.-S. Alouini, “Artificial intelligence for satellite communication: A review,” Intelligent and Converged Networks, vol. 2, no. 3, pp. 213–244, 2021, https://doi.org/10.23919/ICN.2021.0018.

[14] F. Fourati and M.-S. Alouini, “AI for satellite networking and telemetry data mining: Opportunities and challenges,” arXiv, 2021, https://doi.org/10.48550/arXiv.2101.10899.

[15] E. Arbon, P. Smet, L. Gunn, and M. McDonnell, “Anomaly detection in satellite communications systems using LSTM networks,” in 2018 Military Communications and Information Systems Conference (MilCIS), Canberra, Australia, 2018, Art. no. 8574109, https://doi.org/10.1109/MilCIS.2018.8574109.

[16] Wang et al., “Real-time fault detection in satellite telemetry using convolutional neural networks,” Remote Sensing of Environment, vol. 299, 2025, Art. no. 113940, https://doi.org/10.1007/s11235-020-00722-5.

[17] M. S. Islam and A. Rahimi, “Fault prognosis of satellite reaction wheels using a two-step LSTM network,” in 2021 IEEE International Conference on Prognostics and Health Management (ICPHM), Detroit, MI, USA, 2021, https://doi.org/10.1109/ICPHM51084.2021.9486655.

[18] M. S. Alghananim, C. Feng, Y. Feng, and W. Y. Ochieng, “Machine learning-based fault detection and exclusion for Global Navigation Satellite System pseudorange in the measurement domain,” Sensors, vol. 25, no. 3, 2025, Art. no. 817, https://doi.org/10.3390/s25030817.

[19] F. Caldas and C. Soares, “Machine learning in orbit estimation: A survey,” Acta Astronautica, vol. 220, pp. 97–107, 2024, https://doi.org/10.1016/j.actaastro.2024.03.072.

[20] C. Yildirim and H. E. Soken, “Fault-tolerant ADCS for small satellites using Bayesian networks,” in 2024 IEEE Aerospace Conference (AERO), Big Sky, MT, USA, 2024, https://doi.org/10.1109/AERO58975.2024.10521342.

[21] A. Azamovich et al., “Machine learning-based fault detection and classification in microgrid,” Journal of Operation and Automation in Power Engineering, vol. 12, Special Issue, pp. 43-52, 2024, https://doi.org/10.22098/JOAPE.2025.16912.2315.

[22] S. Hemmati, M. Babaei, and J. Hedengren, “Hybrid physics-informed neural networks for thermal process identification and control,” Systems and Control Transactions, vol. 5, pp. 2594–2598, 2026, https://doi.org/10.69997/sct.135132.

[23] G. Ciaburro, “Machine fault detection methods based on machine learning algorithms: A review,” Mathematical Biosciences and Engineering, vol. 19, no. 11, pp. 11453–11490, 2022, https://doi.org/10.3934/mbe.2022534.

[24] T. S. Abdel Aziz, G. I. Salama, M. S. Mohamed, and S. Hussein, “Spacecraft fault detection and identification techniques using artificial intelligence,” Journal of Physics: Conference Series, vol. 2616, no. 1, 2023, Art. no. 012025, https://doi.org/10.1088/1742-6596/2616/1/012025.

[25] C. Cena, U. Albertin, M. Martini, S. Bucci, and M. Chiaberge, “Physics-informed real NVP for satellite power system fault detection,” IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Boston, USA, 2024, https://doi.org/10.1109/AIM55361.2024.10636990.

[26] C. Cena, U. Albertin, M. Martini, S. Bucci, and M. Chiaberge, “Deep generative AI for satellite EPS diagnostics with Real-NVP,” in 2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM), Boston, MA, USA, 2024, pp. 679–684, https://doi.org/10.1109/AIM55361.2024.10636990.

[27] K. Hundman, V. Constantinou, C. Laporte, I. Colwell, and T. Soderstrom, “Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding,” in Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), London, U.K., 2018, pp. 387–395, https://doi.org/10.1145/3219819.3219845.

[28] NASA Ames Prognostics Center of Excellence, “Prognostics Data Repository,” NASA, [Online]. Available: https://www.nasa.gov/intelligent-systems-division/discovery-and-systems-health/pcoe/pcoe-data-set-repository/.

[29] Failure Modes, Effects (and Criticality) Analysis (FMEA/FMECA), ECSS-Q-ST-30-02C, European Cooperation for Space Standardization, Mar. 6, 2009, Reconfirmed Jun. 14, 2023. [Online]. Available: https://ecss.nl/standard/ecss-q-st-30-02c-failure-modes-effects-and-criticality-analysis-fmeafmeca/.

[30] Google AI Edge, “LiteRT for Microcontrollers,” 2024. [Online]. Available: https://developers.google.com/edge/litert/microcontrollers/overview.

[31] S. Vittal, “Case study on detecting anomalies in CubeSat telemetry using machine learning approach,” Acceleron Aerospace Journal, vol. 5, no. 6, pp. 1629–1638, 2025, https://doi.org/10.61359/11.2106-2568.