Uncertainty-Aware and Risk-Controlled Identification of Abnormal Parametric Changes in Space Launcher Electrical Valve Actuators
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
In the context of health monitoring for the next generation of reusable space launchers, this work presents an uncertainty-aware method for detecting and diagnosing off-nominal parameter variations in the electrical system that drives engine valves. The study relies on data generated from a physics-based model, where deviations of nine key parameters simulate realistic faults and degradations.
The proposed pipeline combines domain-driven segmentation to isolate valve-motion intervals, automated statistical feature extraction, and multiclass gradient-boosting-based classification, together with out-of-distribution detection using an isolation forest. To enable uncertainty-aware decisions with user-defined confidence levels, all predictive stages are calibrated through a learn--then--test risk-control framework, providing finite-sample guarantees for out-of-distribution rejection, fault detection, and diagnosis via prediction sets.
Numerical results on the available data demonstrate the effectiveness of the pipeline and an improvement over our previously published approach. However, a class-separability analysis reveals intrinsic limitations of the available signals for near-nominal fault classes, underscoring the need for improved observability or alternative modeling assumptions in future real-data deployments.
How to Cite
##plugins.themes.bootstrap3.article.details##
Space Launcher, Electrical Valve Actuator, Fault Diagnosis, Machine Learning, Conformal Prediction, Risk Control
Bagnall, A., Lines, J., Bostrom, A., Large, J., & Keogh, E. (2017). The great time series classification bake off: A review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 31, 606–660.
Basora, L., Bocquet-Nouaille, L., Robinson, E., & Gonidec, S. L. (2025). Fault detection and diagnosis for the engine electrical system of a space launcher based on a temporal convolutional autoencoder and calibrated classifiers. arXiv preprint arXiv:2507.13022.
Bates, S., Angelopoulos, A., Lei, L., Malik, J., & Jordan, M. (2021). Distribution-free, risk-controlling prediction sets. Journal of the ACM, 68(6), 1–34.
Benbouzid, M. E. H. (2000). A review of induction motor signature analysis as a medium for fault detection. IEEE Transactions on Industrial Electronics, 47(5), 984–993.
Bretz, F., Maurer, W., Brannath, W., & Posch, M. (2009). A graphical approach to sequentially rejective multiple test procedures. Statistics in Medicine, 28(4), 586–604. doi: https://doi.org/10.1002/sim.3495
Choi, K., Yi, J., Park, C., & Yoon, S. (2021). Deep learning for anomaly detection in time-series data: Review, analysis, and guidelines. IEEE Access, 9, 120043–120065.
Christ, M., Braun, N., Neuffer, J., & Kempa-Liehr, A. W. (2018). Time series feature extraction on the basis of scalable hypothesis tests: tsfresh, a Python package. Neurocomputing, 307, 72–77.
Cordier, T. (2025). Risk control for machine learning. Available at: thibaultcordier.github.io/risk-control.
Diallo, A. R., Homri, L., & Dantan, J.-Y. (2025). Reducing false alarms in fault detection: A comparative analysis between conformal prediction and classical methods applied to PCA and autoencoders. Journal of Process Control, 152, 103495.
Férard, B., Le Gonidec, S., Galeotta, M., Oriol, S., & Dreyer, S. (2021). Anomaly detection on propulsive systems by global approach using autoencoders. IFAC-PapersOnLine, 54(4), 31–37.
Heddoub, A., Diallo, A. R., Homri, L., Dantan, J.-Y., & Siadat, A. (2025). Uncertainty-aware fault diagnosis with conformal prediction. IFAC-PapersOnLine, 59(10), 536–541.
Husebø, A. B., Kandukuri, S. T., Klausen, A., Huynh, K., & Robbersmyr, K. G. (2020). Rapid diagnosis of induction motor electrical faults using convolutional autoencoder feature extraction. Annual Conference of the PHM Society.
Ismail Fawaz, H., Forestier, G., Weber, J., Idoumghar, L., & Muller, P.-A. (2019). Deep learning for time series classification: A review. Data Mining and Knowledge Discovery, 33(4), 917–963.
Javanmardi, A., & Hüllermeier, E. (2023). Conformal prediction intervals for remaining useful lifetime estimation. International Journal of Prognostics and Health Management, 14(2).
Jiménez-Guarneros, M., Morales-Perez, C., & de Jesus Rangel-Magdaleno, J. (2021). Diagnostic of combined mechanical and electrical faults in ASD-powered induction motor using MODWT and a lightweight 1-D CNN. IEEE Transactions on Industrial Informatics, 18(7), 4688–4697.
Kayali, M., & Wang, C. (2022). Mining robust default configurations for resource-constrained AutoML. arXiv preprint arXiv:2202.09927.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30.
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In 2008 Eighth IEEE International Conference on Data Mining (pp. 413–422).
Nandi, S., Toliyat, H. A., & Li, X. (2005). Condition monitoring and fault diagnosis of electrical motors: A review. IEEE Transactions on Energy Conversion, 20(4), 719–729.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Robinson, C. (2026). Remaining useful life estimation for aircraft engines with risk-aware prediction intervals via conformalized quantile regression. International Journal of Prognostics and Health Management, 17(1).
Shafer, G., & Vovk, V. (2008). A tutorial on conformal prediction. Journal of Machine Learning Research, 9(3).
Shao, S., Yan, R., Lu, Y., Wang, P., & Gao, R. X. (2019). DCNN-based multi-signal induction motor fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 69(6), 2658–2669.
Thomson, W. T., & Fenger, M. (2003). Case histories of current signature analysis to detect faults in induction motor drives. In IEEE International Electric Machines and Drives Conference, 2003. IEMDC’03 (Vol. 3, pp. 1459–1465).
Verma, S. (2023). Deep neural network modeling of electric motors (PhD thesis). Université Paris-Saclay. HAL Id: tel-04231692.
Verma, S., Henwood, N., Castella, M., Malrait, F., & Pesquet, J.-C. (2020). Modeling electrical motor dynamics using encoder-decoder with recurrent skip connection. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, pp. 1387–1394).
Wang, C., Wu, Q., Weimer, M., & Zhu, E. (2021). FLAML: A fast and lightweight AutoML library. In MLSys.
Yang, C.-L., Meles, T. Y., Yilma, A. A., & Teshome, M. M. (2026). Uncertainty-aware predictive maintenance using a hybrid Transformer with Monte Carlo Dropout and conformal prediction. Ain Shams Engineering Journal, 17(2), 103992.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.