Cloud-Enabled Autoencoder-Based Anomaly Detection for Gas Turbine Faults
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Engine Health Monitoring (EHM) is critical to reducing service disruption and operational costs in the aerospace industry.
While traditional physics-based algorithms have been effective, the increasing volume and complexity of sensor data
necessitate more scalable, automated, and accurate detection methods. This paper discusses the transition of Rolls Royce
EHMcapability- for civil and commercial aircraft engines toward a modern Machine Learning (ML) paradigm within
the Rolls-Royce Data Science Environment (DSE). Leveraging a cloud-based architecture and its tech stack, we address
the challenges of manual recalibration and high false-positive rates. We present a case study of an anomaly detection frame
work utilizing a two-stage approach: a deep neural network for input-output residual generation followed by an autoencoder with a custom loss function for latent representation. Furthermore, we outline the integration of MLflow to ensure
robust experiment tracking, as well as the use of a cloud-based unified data governance framework. This work demonstrates
how end-to-end ML lifecycle management maintains model performance and operational trust in a highly regulated envi
ronment.
How to Cite
##plugins.themes.bootstrap3.article.details##
anomaly detection, gas turbine, autoencoder, machine learning, engine health monitoring, cloud
Liang, Q., Knutsen, K. E., Vanem, E., Æsøy, V., & Zhang, H. (2024). A review of maritime equipment prognostics health management from a classification society perspective. Ocean Engineering, 301, 117619. doi: https://doi.org/10.1016/j.oceaneng.2024.117619
Zhang, P., Wang, J., Wang, Y., Li, X., & Zhang, Z. (2022). Marine systems and equipment prognostics and health management: A systematic review from health condition monitoring to maintenance strategy. Machines, 10(2), 72. doi: https://doi.org/10.3390/machines10020072
Chen, C., Fu, H., Zheng, Y., Tao, F., & Liu, Y. (2023). The advance of digital twin for predictive maintenance: The role and function of machine learning. Journal of Manufacturing Systems, 71, 581–594. doi: https://doi.org/10.1016/j.jmsy.2023.10.010
You, Y., Chen, C., Hu, F., Liu, Y., & Ji, Z. (2022). Advances of digital twins for predictive maintenance. Procedia Computer Science, 200, 1471–1480. doi: https://doi.org/10.1016/j.procs.2022.01.348
Wu, F., Shao, Y., Zhang, J., & Chen, Z. (2024). Remaining useful life prediction based on deep learning: A survey. Sensors, 24(11), 3454. doi: https://doi.org/10.3390/s24113454
Si, X.-S., Wang, W., Hu, C.-H., & Zhou, D.-H. (2011). Remaining useful life estimation: A review on the statistical data-driven approaches. European Journal of Operational Research, 213(1), 1–14. doi: https://doi.org/10.1016/j.ejor.2010.11.018
Jardine, A. K. S., Lin, D., & Banjevic, D. (2006). A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, 20(7), 1483–1510. doi: https://doi.org/10.1016/j.ymssp.2005.09.012
Heng, A., Zhang, S., Tan, A. C. C., & Mathew, J. (2009). Rotating machinery prognostics: State of the art, challenges and opportunities. Mechanical Systems and Signal Processing, 23(3), 724–739. doi: https://doi.org/10.1016/j.ymssp.2008.06.009
Peng, Y., Dong, M., & Zuo, M. J. (2010). Current status of machine prognostics in condition-based maintenance: A review. International Journal of Advanced Manufacturing Technology, 50, 297–313. doi: https://doi.org/10.1007/s00170-009-2482-0
Lei, Y., Li, N., Guo, L., Li, N., Yan, T., & Lin, J. (2018). Machinery health prognostics: A systematic review from data acquisition to remaining useful life prediction. Mechanical Systems and Signal Processing, 104, 799–834. doi: https://doi.org/10.1016/j.ymssp.2017.11.016
Tsarouhas, P. H., & Fourlas, G. K. (2015). Reliability and maintainability analysis of a robotic system for industrial applications: A case study. International Journal of Performability Engineering, 11(5), 453–462. doi: 10.23940/ijpe.15.5.p453.mag
Aivaliotis, P., Arkouli, Z., Georgoulias, K., & Makris, S. (2023). Methodology for enabling dynamic digital twins and virtual model evolution in industrial robotics: A predictive maintenance application. International Journal of Computer Integrated Manufacturing, 36(7), 947–965. doi: https://doi.org/10.1080/0951192X.2022.2162591
Tsai, C.-M., Wang, C.-S., Chung, Y.-J., Sun, Y.-D., & Perng, J.-W. (2021). Multi-sensor fault diagnosis of underwater thruster propeller based on deep learning. Sensors, 21(21), 7187. doi: https://doi.org/10.3390/s21217187
Cho, H., Park, J.-H., Choo, K.-B., Kim, M., Ji, D.-H., & Choi, H.-S. (2024). Unmanned surface vehicle thruster fault diagnosis via vibration signal wavelet transform and vision transformer under varying rotational speed conditions. Sensors, 24(5), 1697.
Liu, F., Tang, H., Qin, Y., Duan, C., Luo, J., & Pu, H. (2022). A review on fault diagnosis of unmanned underwater vehicles. Ocean Engineering, 243, 110290. doi: https://doi.org/10.1016/j.oceaneng.2021.110290
Thuillier, J., Lallart, M., & Nguyen, D. K. (2024). Prognostics-aware control design for extended remaining useful life. International Journal of Prognostics and Health Management, 15(1).
Tsarouhas, P. H., & Fourlas, G. K. (2016). Mission reliability estimation of mobile robot system. International Journal of System Assurance Engineering and Management, 7, 220–228. doi: https://doi.org/10.1007/s13198-015-0408-9
Heshmati-Alamdari, S., Sharifi, M., Karras, G. C., & Fourlas, G. K. (2024). Control barrier function-based visual servoing for mobile manipulator systems under functional limitations. Robotics and Autonomous Systems, 182, 104813. doi: https://doi.org/10.1016/j.robot.2024.104813
Heshmati-Alamdari, S., Karras, G. C., Sharifi, M., & Fourlas, G. K. (2023). Control barrier function-based visual servoing for underwater vehicle manipulator systems under operational constraints. In 31st Mediterranean Conference on Control and Automation (MED). doi: https://doi.org/10.1109/MED59994.2023.10185835
Pan, Y., Liu, Y., Zhang, J., & Chen, Z. (2025). Remaining useful life prediction methods of equipment components based on deep learning for sustainable manufacturing: A literature review. Artificial Intelligence for Engineering Design, Analysis and Manufacturing (AI EDAM).
Blue Robotics. (2026). T200 thruster (R2) product page. Retrieved from https://bluerobotics.com/store/thrusters/t100-t200-thrusters/t200-thruster-r2-rp/
Basora, L., Olive, X., & Dubot, T. (2019). Recent advances in anomaly detection methods applied to aviation. Aerospace, 6(11), 117.
Cruz-Manzo, S., Panov, V., & Zhang, Y. (2018). Gas path fault and degradation modelling in twin-shaft gas turbines. Machines, 6(4), 43. doi: https://doi.org/10.3390/machines6040043
Fentaye, A. D., Baheta, A. T., Gilani, S. I., & Kyprianidis, K. G. (2019). A review on gas turbine gas-path diagnostics: State-of-the-art methods, challenges and opportunities. Aerospace, 6(7). doi: 10.3390/aerospace6070083
Ferracuti, F., Freddi, A., Monteriu, A., & Romeo, L. (2022). Fault diagnosis of rotating machinery based on Wasserstein distance and feature selection. IEEE Transactions on Automation Science and Engineering, 19(3), 1997–2007. doi: https://doi.org/10.1109/tase.2021.3069109
Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., & Zhang, G. (2018). Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 1–1. doi: https://doi.org/10.1109/tkde.2018.2876857
Montana, F., Anderson, S., Mills, A., Naylor, P., Ameri, N., & Jacobs, W. (2026). Deep anomaly detection for gas turbine engines using model residuals and time-constrained autoencoders. Engineering Applications of Artificial Intelligence.
Montana, F., Jacobs, W., Ameri, N., Naylor, P., & Mills, A. (2024a, December). Next generation diagnostic network: A method of training an encoder model. UK Patent Application 2024P00471 GB. Pending.
Montana, F., Jacobs, W., Ameri, N., Naylor, P., & Mills, A. (2024b, December). Next generation diagnostic network: Autoencoder. UK Patent Application 2024P00260 GB. Pending.
Montana, F., Jacobs, W., Ameri, N., Naylor, P., & Mills, A. (2024c, December). Next generation diagnostic network: Fault determination. UK Patent Application 2024P00258 GB. Pending.
Munir, M., Siddiqui, S. A., Dengel, A., & Ahmed, S. (2019). DeepAnT: A deep learning approach for unsupervised anomaly detection in time series. IEEE Access, 7, 1991–2005. doi: 10.1109/ACCESS.2018.2886457
Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S. A., Binder, A., ... Kloft, M. (2018). Deep one-class classification. In International Conference on Machine Learning (pp. 4393–4402).
Vela, D., Sharp, A., Zhang, R., Nguyen, T., Hoang, A., & Pianykh, O. S. (2022). Temporal quality degradation in AI models. Scientific Reports, 12(1). doi: https://doi.org/10.1038/s41598-022-15245-z
Verhagen, W. J. C., Santos, B. F., Freeman, F., van Kessel, P., Zarouchas, D., Loutas, T., ... Heiets, I. (2023). Condition-based maintenance in aviation: Challenges and opportunities. Aerospace, 10(9), 762. doi: https://doi.org/10.3390/aerospace10090762
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.