Document Open Access Logo

Hybrid Fault Detection and Isolation for the Fuel Turbopump Subsystem of the LOX/LNG Expander-Bleed Rocket Engine LUMEN

Authors Eldin Kurudzija , Marcos Quinones-Grueiro , Kai Dresia , Austin Coursey , Gautam Biswas , Jan Deeken , Günther Waxenegger-Wilfing

PDF

File

Thumbnail PDF
PDF
OASIcs.DX.2026.8.pdf
  • Filesize: 1.13 MB
  • 20 pages

Document Identifiers

Subject Classification

ACM Subject Classification
  • Applied computing → Aerospace
  • Computing methodologies → Anomaly detection
  • Computing methodologies → Neural networks
  • Mathematics of computing → Time series analysis
Keywords
  • Hybrid
  • Fault Detection and Isolation
  • Liquid Rocket Engines
  • LUMEN

Metrics

Abstract

The transition toward reusable and cost-efficient launch systems increases the need for advanced fault detection and isolation (FDI) capabilities to support the reliable and safe operation of liquid rocket engines. Development of these systems typically relies on physics-based simulation models and experimental data. LUMEN (Liquid Upper stage deMonstrator ENgine) is a modular, pump-fed LOX/LNG rocket engine with a nominal thrust of 25 kN, developed and operated by the Institute of Space Propulsion of the German Aerospace Center (DLR). The Rocket Engine Control and Diagnosis Benchmark provides a high-fidelity, experimentally validated EcosimPro/ESPSS simulation model of LUMEN for FDI system development. In this work, we use the fuel turbopump subsystem of this model as a case study and integrate data-driven components into a consistency-based diagnosis (CBD) framework to improve diagnostic performance. The results demonstrate that the hybrid architecture improves isolation accuracy, increasing it from 0.46 to 0.76 compared to the CBD baseline. In addition, we propose a sensor validation network (SVN) that uses a grey-box neural ordinary differential equation surrogate driven by valve-command inputs to decouple sensor faults from component faults. This further increases the isolation accuracy to 0.92, while retaining the ability to detect unknown component faults. These results indicate that incorporating data-driven components helps to compensate for structural non-isolability and improve diagnostic performance while preserving physical interpretability.

Cite As Get BibTex

Eldin Kurudzija, Marcos Quinones-Grueiro, Kai Dresia, Austin Coursey, Gautam Biswas, Jan Deeken, and Günther Waxenegger-Wilfing. Hybrid Fault Detection and Isolation for the Fuel Turbopump Subsystem of the LOX/LNG Expander-Bleed Rocket Engine LUMEN. In 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026). Open Access Series in Informatics (OASIcs), Volume 148, pp. 8:1-8:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026) https://doi.org/10.4230/OASIcs.DX.2026.8

Author Details

Eldin Kurudzija
  • Institute of Space Propulsion, German Aerospace Center (DLR), Köln, Germany
Marcos Quinones-Grueiro
  • Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA
Kai Dresia
  • Institute of Space Propulsion, German Aerospace Center (DLR), Erlenbach, Germany
Austin Coursey
  • Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA
Gautam Biswas
  • Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA
Jan Deeken
  • Institute of Space Propulsion, German Aerospace Center (DLR), Hardsthausen, Germany
  • Institute of Jet Propulsion and Turbomachinery, RWTH Aachen, Germany
Günther Waxenegger-Wilfing
  • Institute of Space Propulsion, German Aerospace Center (DLR), Hardthausen, Germany
  • Institute of Computer Science, University of Würzburg, Germany

Acknowledgements

ChatGPT (GPT-5.3-5.6) and Claude (Opus 4.6/4.7, Sonnet 4.6/5) were used for language editing and code development. The authors reviewed and verified all generated outputs.

References

  1. J. Cha. Numerical Simulation of Chemical Propulsion Systems: Survey and Fundamental Mathematical Modeling Approach. Aerospace, 10(10), 2023. URL: https://doi.org/10.3390/aerospace10100839.
  2. J. Cha and S. Ko. General Fault Factor Method for Health Monitoring of a Liquid Rocket Engine. Journal of Spacecraft and Rockets, 62(6):2236-2248, 2025. URL: https://doi.org/10.2514/1.A36337.
  3. R. L. Christenson, M. A. Nelson, and J. P. Butas. Rocket Engine Health Management: Early Definition of Critical Flight Measurements. In 39th AIAA/ASME/SAE/ASEE Joint Propulsion Conference and Exhibit, Huntsville, Alabama, 2003. URL: https://doi.org/10.2514/6.2003-5251.
  4. H. A. Cikanek. Characteristics of Space Shuttle Main Engine Failures. In 23rd Joint Propulsion Conference, San Diego, California, June 1987. AIAA Paper 87-1939. URL: https://doi.org/10.2514/6.1987-1939.
  5. M. Davidson and J. Stephens. Advanced Health Management System for the Space Shuttle Main Engine. In 40th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit, Fort Lauderdale, FL, July 2004. AIAA 2004-3912. Google Scholar
  6. J. de Kleer. Hitting Set Algorithms for Model-Based Diagnosis. In 22nd International Workshop on Principles of Diagnosis (DX'11), Murnau, Germany, 2011. Google Scholar
  7. J. de Kleer and B. C. Williams. Diagnosing Multiple Faults. Artificial Intelligence, 32(1):97-130, 1987. URL: https://doi.org/10.1016/0004-3702(87)90063-4.
  8. K. Dresia, E. Kurudzija, V. Bareiß, J. Dauer, J. Deeken, and G. Waxenegger-Wilfing. Health Monitoring and Intelligent Control Benchmark for Reusable Liquid-Propellant Rocket Engines. In Space Propulsion Conference, Bari, Italy, 2026. 3AF. URL: https://doi.org/10.60711/SPC2026.20260715.37863079794095352.
  9. K. Dresia, T. Traudt, M. Börner, D. Suslov, W. Armbruster, R. dos Santos Hahn, E. Kurudzija, C. Groll, M. A. Müller, S. Klein, J. Hämisch, J. Deeken, J. Hardi, and S. Schlechtriem. Hot-Fire Testing and System Analysis of the LUMEN Liquid Upper Stage Demonstrator Engine. In 3rd Int. Conf. on Flight Vehicles, Aerothermodynamics and Re-entry (FAR), Arcachon, France, 2025. Google Scholar
  10. European Commission. ENLIGHTEN: European iNitiative for Low Cost, Innovative & Green High Thrust Engine, October 2022. URL: https://doi.org/10.3030/101082326.
  11. B. Férard, S. Le Gonidec, M. Galeotta, S. Oriol, and S. Dreyer. Anomaly Detection on Propulsive Systems by Global Approach Using Autoencoders. IFAC-PapersOnLine, 54(4):31-37, 2021. URL: https://doi.org/10.1016/j.ifacol.2021.10.006.
  12. E. Frisk, M. Krysander, and D. Jung. A Toolbox for Analysis and Design of Model Based Diagnosis Systems for Large Scale Models. IFAC-PapersOnLine, 50(1):3287-3293, 2017. 20th IFAC World Congress. URL: https://doi.org/10.1016/j.ifacol.2017.08.504.
  13. N. T. Ho. Failure Detection and Isolation for the Space Shuttle Main Engine. M.sc. thesis, Massachusetts Institute of Technology, 1998. Google Scholar
  14. M. M. Hussein, D. Terakado, and O. de Weck. Comprehensive Study of the International Space Launch Industry: Programmatic Analysis and Technical Failures. Acta Astronautica, 234:676-689, 2025. URL: https://doi.org/10.1016/j.actaastro.2025.03.015.
  15. D. Jung. Data-Driven Open-Set Fault Classification of Residual Data Using Bayesian Filtering. IEEE Transactions on Control Systems Technology, 28(5):2045-2052, 2020. URL: https://doi.org/10.1109/TCST.2020.2997648.
  16. D. Jung. Automated Design of Grey-Box Recurrent Neural Networks For Fault Diagnosis using Structural Models and Causal Information. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 168:8-20, 23-24 June 2022. URL: https://proceedings.mlr.press/v168/jung22a.html.
  17. D. Jung, K. Y. Ng, E. Frisk, and M. Krysander. Combining Model-Based Diagnosis and Data-Driven Anomaly Classifiers for Fault Isolation. Control Engineering Practice, 80:146-156, 2018. URL: https://doi.org/10.1016/j.conengprac.2018.08.013.
  18. D. Jung and T. Westny. Uncertainty-Aware Fault Diagnosis of Unknown Faults using Ensemble-Based NODE Residuals. Mechanical Systems and Signal Processing, 242:113599, 2026. URL: https://doi.org/10.1016/j.ymssp.2025.113599.
  19. C. Keliris, M. M. Polycarpou, and T. Parisini. A Distributed Fault Detection Filtering Approach for a Class of Interconnected Continuous-Time Nonlinear Systems. IEEE Transactions on Automatic Control, 58(8):2032-2047, 2013. URL: https://doi.org/10.1109/TAC.2013.2253231.
  20. H. Khorasgani and G. Biswas. Structural Fault Detection and Isolation in Hybrid Systems. IEEE Transactions on Automation Science and Engineering, 15(4):1585-1599, 2017. URL: https://doi.org/10.1109/TASE.2017.2749447.
  21. H. Khorasgani, A. Farahat, K. Ristovski, C. Gupta, and G. Biswas. A Framework for Unifying Model-Based and Data-Driven Fault Diagnosis. In Proceedings of the Annual Conference of the PHM Society, volume 10, September 2018. URL: https://doi.org/10.36001/phmconf.2018.v10i1.530.
  22. M. Krysander, J. Åslund, and M. Nyberg. An Efficient Algorithm for Finding Minimal Overconstrained Subsystems for Model-Based Diagnosis. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 38(1):197-206, 2008. URL: https://doi.org/10.1109/TSMCA.2007.909555.
  23. E. Kurudzija, K. Dresia, V. Bareiß, G. Waxenegger-Wilfing, and J. Deeken. Transient System-Level Simulation of the LOX/LNG Expander-Bleed Rocket Engine LUMEN. SSRN. https://ssrn.com/abstract=6806858, 2026. Google Scholar
  24. K. Lee, J. Cha, S. Ko, S.-Y. Park, and E. Jung. Fault Detection and Diagnosis Algorithms for an Open-Cycle Liquid Propellant Rocket Engine using the Kalman Filter and Fault Factor Methods. Acta Astronautica, 150:15-27, 2018. URL: https://doi.org/10.1016/j.actaastro.2018.03.001.
  25. M. A. Martin, H. H. Nguyen, W. D. Greene, and D. C. Seymout. Transient Mathematical Modeling for Liquid Rocket Engine Systems: Methods, Capabilities, and Experience. In 5th International Symposium on Liquid Space Propulsion, Chattanooga, Tennessee, October 2003. Google Scholar
  26. A. Mohammadi, M. Krysander, and D. Jung. Analysis of Grey-Box Neural Network-Based Residuals for Consistency-Based Fault Diagnosis. IFAC-PapersOnLine, 55(6):1-6, 2022. URL: https://doi.org/10.1016/j.ifacol.2022.07.097.
  27. A. Mohammadi, M. Krysander, and D. Jung. Consistency-Based Diagnosis Using Data-Driven Residuals and Limited Training Data. Control Engineering Practice, 159:106283, 2025. URL: https://doi.org/10.1016/j.conengprac.2025.106283.
  28. R. Murata, J. Marzat, H. Piet-Lahanier, S. Boujnah, and P. Belleoud. Residual Selection for Observer-Based Fault Detection and Isolation in a Multi-Engine Propulsion Cluster. In Proceedings of the European Conference of the PHM Society, volume 8, page 9, June 2024. URL: https://doi.org/10.36001/phme.2024.v8i1.4056.
  29. R. Murata, J. Marzat, H. Piet-Lahanier, S. Boujnah, and P. Belleoud. Fault Detection and Isolation Based on Structural Analysis: Application to a Multi-Engine Propulsion Cluster. Sensors, 25(4), 2025. URL: https://doi.org/10.3390/s25041054.
  30. J. W. Owen. Shuttle Propulsion System Major Events and the Final 22 Flights. In 6th JANNAF Liquid Propulsion Subcommittee Meeting, NASA Marshall Space Flight Center, Huntsville, AL, USA, 2011. Google Scholar
  31. S.-Y. Park and J. Ahn. Deep Neural Network Approach for Fault Detection and Diagnosis During Startup Transient of Liquid-Propellant Rocket Engine. Acta Astronautica, 177:714-730, 2020. URL: https://doi.org/10.1016/j.actaastro.2020.08.019.
  32. I. Pill, D. Jung, E. Kurudzija, A. Sztyber-Betley, M. Syfert, K. Dresia, G. Waxenegger-Wilfing, and J. de Kleer. The DX Competition 2025 and Its Benchmarks. Open Access Series in Informatics (OASIcs), 136:14:1-14:19, 2025. 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). URL: https://doi.org/10.4230/OASIcs.DX.2025.14.
  33. S. Priotto and S. Le Gondiec. AI-Driven Health Monitoring Systems for Enhanced Propulsion Reliability. In Space Propulsion Conference, Bari, Italy, 2026. 3AF. Google Scholar
  34. R. Reiter. A Theory of Diagnosis from First Principles. Artificial Intelligence, 32(1):57-95, 1987. URL: https://doi.org/10.1016/0004-3702(87)90062-2.
  35. B. Schölkopf, J. C. Platt, J. Shawe-Taylor, A. J. Smola, and R. C. Williamson. Estimating the support of a high-dimensional distribution. Neural Computation, 13(7):1443-1471, 2001. URL: https://doi.org/10.1162/089976601750264965.
  36. P. Simontacchia, S. Sagnier, E. Edeline, R. Blasi, A. Espinosa, J.-N. Caruana, S. Boujnah, and P. Altenhöfer. PROMETHEUS: Precursor of New Low-Cost Rocket Engine Family. In Proceedings of the International Astronautical Congress, IAC, 2022. Google Scholar
  37. K. Tidriri, N. Chatti, S. Verron, and T. Tiplica. Bridging Data-Driven and Model-Based Approaches for Process Fault Diagnosis and Health Monitoring: A Review of Researches and Future Challenges. Annual Reviews in Control, 42:63-81, 2016. URL: https://doi.org/10.1016/j.arcontrol.2016.09.008.
  38. T. Traudt, W. Armbruster, C.r Groll, R. H. Dos Santos Hahn, K. Dresia, M. Börner, S. Klein, D. Suslov, E. Kurudzija, J. Haemisch, M. A. Müller, J. C. Deeken, J. Hardi, and S. Schlechtriem. LUMEN, the Test Bed for Rocket Engine Components: Results of the Acceptance Tests and Overview on the Engine Test Preparation. In 9th Edition of the Space Propulsion Conference, Glasgow, Scotland, 2024. Google Scholar
  39. C. Wang, Y. Zhang, Z. Zhao, X. Chen, and J. Hu. Dynamic Model-Assisted Transferable Network for Liquid Rocket Engine Fault Diagnosis Using Limited Fault Samples. Reliability Engineering & System Safety, 243:109837, 2024. URL: https://doi.org/10.1016/j.ress.2023.109837.
  40. T. Wang, L. Ding, and H. Yu. Research and Development of Fault Diagnosis Methods for Liquid Rocket Engines. Aerospace, 9(9):481, 2022. Google Scholar
  41. J. Wu. Liquid-Propellant Rocket Engines Health-Monitoring — a Survey. Acta Astronautica, 56(3):347-356, 2005. URL: https://doi.org/10.1016/j.actaastro.2004.05.070.
  42. X. Zhu, Y. Cheng, J. Wu, R. Hu, and X. Cui. Steady-State Process Fault Detection for Liquid Rocket Engines Based on Convolutional Auto-Encoder and One-Class Support Vector Machine. IEEE Access, 8:3144-3158, 2020. URL: https://doi.org/10.1109/ACCESS.2019.2961742.
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact