A Proposal for Application of Physics-Informed Digital Twin and Particle Filtering for the Detection and Prognosis in Harmonic Drives
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Electro-mechanical actuators (EMAs) in aerospace and robotics increasingly rely on harmonic drives, whose compliant architecture introduces nonlinear dynamics and specific degradation mechanisms. Conventional Prognostics and Health Management (PHM) approaches remain limited: data-driven methods require extensive fault datasets and lack interpretability, while physics-based models are often too computationally demanding for embedded real-time use. This work proposes a physics-informed digital-twin-based framework for fault detection and prognosis in harmonic drives. The digital twin is implemented through a Physics-Informed Neural Network (PINN), so that governing mechanical relations are embedded directly into the training process. Wear evolution is described through a physics-based degradation model, while Remaining Useful Life (RUL) is estimated via particle filtering to provide probabilistic prognostic predictions. The study focuses on the digital twin and prognostic modules within a broader PHM architecture. Preliminary results show accurate reconstruction of nonlinear dynamics, physically coherent degradation tracking, and consistent probabilistic RUL prediction.
How to Cite
##plugins.themes.bootstrap3.article.details##
electromechanical actuators, harmonic drive, Physics-Informed Digital Twin
Al-Adly, A. I., & Kripakaran, P. (2024). Physics-informed neural networks for structural health monitoring: A case study for Kirchhoff–Love plates. Data-Centric Engineering, 5, e6.
Archard, J. (1953). Contact and rubbing of flat surfaces. Journal of Applied Physics, 24(8), 981–988.
Ayankoso, S., Kaigom, E., Louadah, H., Faham, H., Gu, F., & Ball, A. (2024). A hybrid digital twin scheme for the condition monitoring of industrial collaborative robots. Procedia Computer Science, 232, 1099–1108.
Behbahani, A. R., & Semega, K. J. (2010). Control strategy for electromechanical actuators versus hydraulic actuation systems for aerospace applications. SAE Technical Paper. Power Systems Conference.
Biondani, F., Dall’Ora, N., Tosoni, F., Fraccaroli, E., Migliore, D. F., Acerra, F., & Fummi, F. (2024). Fault injection for synthetic data generation in aircraft: A simulation-based approach. In Proceedings of the 2024 IEEE 22nd International Conference on Industrial Informatics (INDIN) (pp. 1–8). IEEE.
Cai, S., Mao, Z., Wang, Z., Yin, M., & Karniadakis, G. E. (2021). Physics-informed neural networks (PINNs) for fluid mechanics: A review. Acta Mechanica Sinica, 37(12), 1727–1738.
Chen, Y. C., Cheng, Y. H., Tseng, J. T., & Hsieh, K. J. (2017). Study of a harmonic drive with involute profile flexspline by two-dimensional finite element analysis. Engineering Computations, 34(7), 2107–2130.
Clochiatti, E., Scalera, L., Boscariol, P., & Gasparetto, A. (2024). Electromechanical modeling and identification of the UR5 e-series robot. Robotica, 42(7), 2430–2452.
Guida, R., Bertolino, A. C., De Martin, A., & Sorli, M. (2024). Comprehensive analysis of major fault-to-failure mechanisms in harmonic drives. Machines, 12(11), 776.
Guida, R., Bertolino, A. C., De Martin, A., & Sorli, M. (2025). A new computationally efficient model of the non-linear dynamics in harmonic drive reducers. Mechanism and Machine Theory, 209, 105992.
Jaber, A. A., & Bicker, R. (2016). Fault diagnosis of industrial robot gears based on discrete wavelet transform and artificial neural network. Insight: Non-Destructive Testing and Condition Monitoring, 58(4), 179–186.
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422–440.
Liu, Y., Liu, Y., McCrory, J., & Guo, X. (2024). High-fidelity digital twin modelling for predictive maintenance: State of the art.
Ma, H., Pang, X., Zeng, J., Wang, Q., & Wen, B. (2015). Effects of gear crack propagation paths on vibration responses of the perforated gear system. Mechanical Systems and Signal Processing, 62, 113–128.
Mazzoleni, M., Di Rito, G., & Previdi, F. (2021). Electromechanical actuators for the more electric aircraft. Cham, Switzerland: Springer.
Meng, Z., Shi, G., & Wang, F. (2020). Vibration response and fault characteristics analysis of gear based on time-varying mesh stiffness. Mechanism and Machine Theory, 148, 103786.
Nesci, A., De Martin, A., Jacazio, G., & Sorli, M. (2020). Detection and prognosis of propagating faults in flight control actuators for helicopters. Aerospace, 7(3), 20.
Ranasinghe, K., Sabatini, R., Gardi, A., Bijjahalli, S., Kapoor, R., Fahey, T., & Thangavel, K. (2022). Advances in integrated system health management for mission-essential and safety-critical aerospace applications. Progress in Aerospace Sciences, 128, 100758.
Raviola, A., De Martin, A., & Sorli, M. (2022). A preliminary experimental study on the effects of wear on the torsional stiffness of strain wave gears. Actuators, 11(11), 305.
Swearingen, K., Majkowski, W., Bruggeman, B., Gilbertson, D., Dunsdon, J., & Sykes, B. (2007). An open system architecture for condition-based maintenance overview. In Proceedings of the 2007 IEEE Aerospace Conference (pp. 1–8). IEEE.
Tian, A., He, L., Ding, T., Dong, K., Wang, Y., & Jiang, J. (2025). A generic physics-informed neural network framework for lithium-ion batteries state of health estimation. Energy, 332, 137215.
Tsui, K. L., Chen, N., Zhou, Q., Hai, Y., & Wang, W. (2015). Prognostics and health management: A review on data-driven approaches. Mathematical Problems in Engineering, 2015(1), 793161.
Tuttle, T. D. (1992). Understanding and modeling the behavior of a harmonic drive gear transmission [Doctoral dissertation, Massachusetts Institute of Technology]. Cambridge, MA.
Tuttle, T. D., & Seering, W. P. (2002). A nonlinear model of a harmonic drive gear transmission. IEEE Transactions on Robotics and Automation, 12(3), 368–374.
Wang, Z., Jahanshahi, M. R., Lund, A., Shahriar, A., & Montoya, A. (2025). Physics-informed machine learning for hybrid digital twin-enhanced damage detection and localization. Journal of Engineering Mechanics, 151(12), 04025080.
Yang, L. T., Shao, Y. M., Jiang, W. W., Zhang, L. K., Wang, L. M., & Xu, J. (2021). Effects of tooth surface crack propagation on meshing stiffness and vibration characteristic of spur gear system. Applied Sciences, 11(4), 1968.
Yucesan, Y. A., Dourado, A., & Viana, F. A. (2021). A survey of modeling for prognosis and health management of industrial equipment. Advanced Engineering Informatics, 50, 101404.
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.