Development of a hybrid PHM system for flight control actuators fusing data analytics with physical knowledge
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
It is well known that the development of PHM systems can be approached with a large variety of techniques. In general, the different prognostics techniques are classified as "data driven", or "physics model based", depending on whether the assessment of a system health status and its evolution with time is performed with an intelligent statistical analysis of present and historical data (data driven approach), or the system actual operating status derived from different sensors is compared with the expected system status in the same operating conditions (model based approach). When a large database of historical data is available, data driven techniques can be accurate and do not require a knowledge of the underlying physics as for the case of model-based techniques. On the other hand, a data driven approach detects only anticipated faults, while a physics-based model approach can also detect unanticipated faults, that never occurred in the past. Flight control actuators of aircraft in revenue service are a typical application in which a large historical database can be available from maintenance, repair and overhaul departments, still the prediction of their health status may fall short of the necessary accuracy without a model description of their physics. For this reason, Safran Actuation, a leading manufacturer of flight control actuators, is conducting an extensive R&D work, together with Politecnico di Torino and Forvis Mazars, aimed at developing an effective PHM system with specific reference to the spoiler actuators of the Airbus A320. This use case is of a particular interest due to the very large number of this type of aircraft in service, to their expected continued use in the years to come and to the number of actuators per aircraft. With reference to this use case, this paper shows how an intelligent fusion of data analytics with physical knowledge can be a multiplying factor in improving accuracy and reliability of the PHM system, with the objective of developing a technological demonstrator for its validation in the lab prior to the implementation of a prototype.
How to Cite
##plugins.themes.bootstrap3.article.details##
PHM development, Flight Control Actuators, Particle Filtering, Echo-State Networks, Physics-Informed Machine Learning
Acuña, D. E., & Orchard, M. E. (2018). A theoretically rigorous approach to failure prognosis. In Proceedings of the 10th Annual Conference of the Prognostics and Health Management Society 2018 (PHM18). Philadelphia, PA, USA.
Arulampalam, M. S., Maskell, S., Gordon, N., & Clapp, T. (2009). A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. In Bayesian Bounds for Parameter Estimation and Nonlinear Filtering/Tracking. IEEE. doi: https://doi.org/10.1109/9780470544198.ch73
Autin, S., De Martin, A., Jacazio, G., Socheleau, J., & Vachtsevanos, G. J. (2021). Results of a feasibility study of a prognostic system for electro-hydraulic flight control actuators. International Journal of Prognostics and Health Management, 12(3), 1–18. doi: https://doi.org/10.36001/ijphm.2021.v12i3.2935
Baldo, L., De Martin, A., Jacazio, G., & Sorli, M. (2025). A systematic literature review on PHM strategies for hydraulic primary flight control actuation systems. Actuators, 14(8), 382. doi: https://doi.org/10.3390/act14080382
Baldo, L., De Martin, A., Terner, M., Jacazio, G., & Sorli, M. (2025). Implementing PHM for legacy flight control actuators through operational aircraft data: Approach and lessons learned. Results in Engineering, 28. doi: https://doi.org/10.1016/j.rineng.2025.107214
Bergstra, J., Bardenet, R., Bengio, Y., & Kégl, B. (2011). Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems, 24.
Byington, C. S., Watson, M., & Edwards, D. (2004). Data-driven neural network methodology to remaining life predictions for aircraft actuator components. In IEEE Aerospace Conference Proceedings (Vol. 6, pp. 3581–3589). doi: https://doi.org/10.1109/AERO.2004.1368175
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). doi: https://doi.org/10.1145/2939672.2939785
De Martin, A., Dellacasa, A., Jacazio, G., & Sorli, M. (2018). High-fidelity model of electro-hydraulic actuators for primary flight control systems. In Proceedings of the 2018 Bath/ASME Symposium on Fluid Power and Motion Control, FPMC2018 (Vol. 4, p. V001T01A058). University of Bath, United Kingdom. doi: https://doi.org/10.1115/FPMC2018-8917
Guo, R., & Gan, Q. (2017). Prognostics for a leaking hydraulic actuator based on the F-distribution particle filter. IEEE Access, 5, 22409–22420. doi: https://doi.org/10.1109/ACCESS.2017.2759119
Guo, R., & Sui, J. (2019). Remaining useful life prognostics for the electro-hydraulic servo actuator using Hellinger distance-based particle filter. IEEE Transactions on Instrumentation and Measurement. doi: https://doi.org/10.1109/TIM.2019.2910919
Li, Y. (2016). Mathematical modelling and characteristics of the pilot valve applied to a jet-pipe/deflector-jet servovalve. Sensors and Actuators A: Physical, 245, 150–159. doi: https://doi.org/10.1016/j.sna.2016.04.048
Lukoševičius, M. (2012). A practical guide to applying echo state networks. Neural Networks.
Lundberg, S. M., Allen, P. G., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems. Retrieved from https://github.com/slundberg/shap
Orchard, M. E., & Vachtsevanos, G. J. (2009). A particle-filtering approach for online fault diagnosis and failure prognosis. Transactions of the Institute of Measurement and Control. doi: https://doi.org/10.1177/0142331208092026
Percival, D. B., & Walden, A. T. (2000). Wavelet methods for time series analysis. Cambridge University Press. doi: https://doi.org/10.1017/CBO9780511841040
Shahkar, S., & Khorasani, K. (2022). A multidimensional Bayesian methodology for diagnosis, prognosis, and health monitoring of electrohydraulic servo valves. IEEE Transactions on Control Systems Technology, 30(3), 931–943. doi: https://doi.org/10.1109/TCST.2021.3079198
Singh, P., & Balasubramanian, R. (2025). Echo state networks as state-space models: A systems perspective. arXiv preprint arXiv:2509.04422.
Sprong, J. P., Jiang, X., & Polinder, H. (2020). Deployment of prognostics to optimize aircraft maintenance: A literature review. Journal of International Business Research and Marketing, 5(4), 26–37. doi: https://doi.org/10.18775/jibrm.1849-8558.2015.54.3004
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.