Detection of Abnormal Conditions in Electro-Mechanical Actuators by Physics-Informed Long Short-term Memory Networks

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Chenyang Lai Piero Baraldi Gaetano Quattrocchi Matteo Davide Lorenzo Dalla Vedova Leonardo Baldo Matteo Bertone Enrico Zio

Abstract

Electro-Mechanical Actuators (EMAs) are projected to revolutionize the flight control actuator paradigm, potentially replacing hydraulic-powered systems in the future. Consequently, the functioning of EMAs is destined to become critical for the safe and reliable operation of aircraft. Abnormal conditions of the mechanical components of EMAs can lead to their failure. The objective of this work is to develop a method for the early detection of abnormal conditions of the components of EMAs. The proposed method is based on a signal reconstruction model that estimates the motor position of EMA as expected in normal conditions of its components. Then, the presence of an abnormal condition is identified when the difference between the motor position and its reconstructed position in normal conditions exceeds a preset threshold. The signal reconstruction model employs a Physics-Informed Long Short-Term Memory network (PILSTM), whose architecture combines a physics-informed cell for the solution of the differential equations governing the EMA operation, and a data-driven Long Short-Term Memory (LSTM) cell which receives in input the output of the physics-informed cell and reconstructs the position expected in normal conditions. The proposed method is applied to data simulated by a high-fidelity model of EMAs. The results show that PILSTM is able to provide accurate, physics-consistent estimates of the motor position of EMA in normal conditions and the missed and false detection alarms are lower than those of other state-of-the-art methods.

How to Cite

Lai, C., Baraldi, P., Quattrocchi, G., Dalla Vedova, M. D. L. ., Baldo, L. ., Bertone, M. ., & Zio, E. (2024). Detection of Abnormal Conditions in Electro-Mechanical Actuators by Physics-Informed Long Short-term Memory Networks. PHM Society European Conference, 8(1), 8. https://doi.org/10.36001/phme.2024.v8i1.4018
Abstract 243 | PDF Downloads 131

##plugins.themes.bootstrap3.article.details##

Keywords

Electro-Mechanical Actuators, Physics-Informed Neural Networks, Long Short-term Memory, Fault detection

References
Baldo, L., Bertone, M., Dalla Vedova, M. D., & Maggiore, P. (2022). High-Fidelity Digital-Twin Validation and Creation of an Experimental Database for Electromechanical Actuators Inclusive of Failures. In 2022 6th International Conference on System Reliability and Safety (ICSRS) (pp. 19-25). IEEE. Baraldi, P., Di Maio, F., Genini, D., & Zio, E. (2015). Comparison of data-driven reconstruction methods for fault detection. IEEE Transactions on Reliability, 64(3), 852-860. Berri, P. C., Dalla Vedova, M. D., & Maggiore, P. (2019). A lumped parameter high fidelity EMA model for model based prognostics. Proceedings of the 29th ESREL, Hannover, Germany, 22-26. Butcher, J. C. (1987). The numerical analysis of ordinary differential equations: Runge-Kutta and general linear methods. Wiley-Interscience.
Chao, M. A., Kulkarni, C., Goebel, K., & Fink, O. (2022). Fusing physics-based and deep learning models for prognostics. Reliability Engineering & System Safety, 217, 107961. Chen, Y., Rao, M., Feng, K., & Zuo, M. J. (2022). Physics Informed LSTM hyperparameters selection for gearbox fault detection. Mechanical Systems and Signal Processing, 171, 108907. Hines, J. W., Uhrig, R. E., & Wrest, D. J. (1998). Use of autoassociative neural networks for signal validation. Journal of Intelligent and Robotic Systems, 21, 143-154. Li, W., & Deka, D. (2021). Physics-informed learning for high impedance faults detection. In 2021 IEEE Madrid PowerTech (pp. 1-6). IEEE. Nascimento, R. G., Fricke, K., & Viana, F. A. (2020). A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural network. Engineering Applications of Artificial Intelligence, 96, 103996. Qi, M., Jang, K., Cui, C., & Moon, I. (2023). Novel control aware fault detection approach for non -stationary processes via deep learning-based dynamic surrogate modeling. Process Safety and Environmental Protection, 172, 379-394. Sarikhani, A., & Mohammed, O. A. (2012). Inter -turn fault detection in PM synchronous machines by physics-based back electromotive force estimation. IEEE Transactions on Industrial Electronics, 60(8), 3472-3484. Shen, S., Lu, H., Sadoughi, M., Hu, C., Nemani, V., Thelen, A., ... & Kenny, S. (2021). A physics-informed deep learning approach for bearing fault detection. Engineering Applications of Artificial Intelligence, 103, 104295. Xu, M., Baraldi, P., Lu, X., & Zio, E. (2022). Generative Adversarial Networks With AdaBoost Ensemble Learning for Anomaly Detection in High-Speed Train Automatic Doors. IEEE Transactions on Intelligent Transportation Systems, 23(12), 23408-23421. Yang, J., Guo, Y., & Zhao, W. (2019). Long short-term memory neural network-based fault detection and isolation for electro-mechanical actuators. Neurocomputing, 360, 85-96. Yang, Z., Ling, B. W. K., & Bingham, C. (2013). Fault detection and signal reconstruction for increasing operational availability of industrial gas turbines. Measurement, 46(6), 1938-1946. Yucesan, Y. A., & Viana, F. A. (2021). Hybrid physics informed neural networks for main bearing fatigue prognosis with visual grease inspection. Computers in Industry, 125, 103386. Zhang, X., Foo, G., Don Vilathgamuwa, M., Tseng, K. J., Bhangu, B. S., & Gajanayake, C. (2013). Sensor fault detection, isolation and system reconfiguration based on extended Kalman filter for induction motor drives. IET Electric Power Applications, 7(7), 607-617.

Zhang, X., Tang, L., & Chen, J. (2021). Fault diagnosis for electro-mechanical actuators based on STL-HSTA-GRU and SM. IEEE Transactions on Instrumentation and Measurement, 70, 1-16.
Section
Technical Papers