Comparative Analysis of LSTM Variants for Fault Detection and Classification in Aircraft Control Surfaces
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Aircraft control surfaces play a critical role in ensuring safe and efficient flight. Faults in these surfaces could lead to catastrophic consequences. This paper investigates the application of Long Short-Term Memory (LSTM) networks for fault detection and classification in aircraft control surfaces. Four deep learning models: LSTM, Stacked-LSTM, Bi-LSTM, and Attention-based LSTM (ALSTM), were trained, validated, and tested to classify faults based on residual features. The methodology involved data generation, preprocessing, normalization, and training the models over 200 epochs. Evaluation metrics, including confusion matrices, precision, recall, and F1-scores, were used to assess model performance. Results show that Bi-LSTM achieved the highest accuracy (98.93%) and lowest loss (0.0264), significantly outperforming other models in fault detection, particularly for challenging fault types such as hard-over and lock-in-place. ALSTM followed closely, with notable performance improvements over standard and stacked LSTM models.
##plugins.themes.bootstrap3.article.details##
Fault Detection, Fault Classification, Long Short-Term Memory (LSTM), Stacked-LSTM, Bi-LSTM, Attention-based LSTM (ALSTM)
Alwi, H., Edwards, C., & Tan, C. P. (2011). Fault detection and fault-tolerant control using sliding modes. Springer. https://doi.org/10.1007/978-0-85729-650-4
Bahdanau, D. (2014). Neural machine translation by jointly learning to align and translate. arXiv Preprint arXiv:1409.0473.
Bharatheedasan, K., Maity, T., Kumaraswamidhas, L. A., & Durairaj, M. (2023). An intelligent of fault diagnosis and predicting remaining useful life of rolling bearings based on convolutional neural network with bidirectional LSTM. Sādhanā, 48(3), 131. https://doi.org/10.1007/s12046-023-02169-1
Boni, P., Mazzoleni, M., Previdi, F. (2024). Robust data-driven design of a jamming detection filter for airborne electromechanical actuators. European Journal of Control. 75. 100926. https://doi.org/10.1016/j.ejcon.2023.100926
Borré, A., Seman, L. O., Camponogara, E., Stefenon, S. F., Mariani, V. C., & Coelho, L. dos S. (2023). Machine Fault Detection Using a Hybrid CNN-LSTM Attention-Based Model. Sensors, 23(9). https://doi.org/10.3390/s23094512
Bošković, J. D., & Mehra, R. K. (2003). Failure Detection, Identification and Reconfiguration in Flight Control. In F. Caccavale & L. Villani (Eds.), Fault Diagnosis and Fault Tolerance for Mechatronic Systems:Recent Advances (pp. 129–167). Springer Berlin Heidelberg. https://doi.org/10.1007/3-540-45737-2_5
Cieslak, J., Zolghadri, A., Goupil, P., Dayre, R. (2016). A Comparative Study of Three Differentiation Schemes for the Detection of Runaway Faults in Aircraft Control Surfaces. IFAC-PapersOnLine. 49(17). 70-75. https://doi.org/10.1016/j.ifacol.2016.09.013
Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. Association for Computational Linguistics. Doi: 10.3115/v1/D14-1179. https://aclanthology.org/D14-1179/
Gao, Y., Kim, C. H., & Kim, J.-M. (2021). A Novel Hybrid Deep Learning Method for Fault Diagnosis of Rotating Machinery Based on Extended WDCNN and Long Short-Term Memory. Sensors, 21(19), 6614. https://doi.org/10.3390/s21196614
Grehan, J., Ignatyev, D., Zolotas, A. (2023). Fault Detection in Aircraft Flight Control Actuators Using Support Vector Machines. Machines, 11, 211. https://doi.org/10.3390/machines11020211
Giral, F., Gómez, I., Vinuesa, R., Clainche, S.L. (2024). Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation. arXiv Preprint arXiv:2411.02975.
He, C., Yasenjiang, J., Lv, L., Xu, L., & Lan, Z. (2024). Gearbox Fault Diagnosis Based on MSCNN-LSTM-CBAM-SE. Sensors, 24(14). https://doi.org/10.3390/s24144682
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Hu, J., Zhu, M., Zheng, Z., & Chen, T. (2024). A data-based fault detection scheme for the stratospheric airship control system. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, 238(5), 803–819. https://doi.org/10.1177/09596518231209542
Huang, S., Rong, L., Chang, X., Wang, Z., Yuan, Z., Wei, C. (2021). BLSTM-Based Adaptive Finite-Time Output-Constrained Control for a Class of AUSs with Dynamic Disturbances and Actuator Faults. Mathematical Problems in Engineering. https://doi.org/10.1155/2021/2221495
Keshun, Y., Puzhou, W., & Yingkui, G. (2024). Toward Efficient and Interpretative Rolling Bearing Fault Diagnosis via Quadratic Neural Network With Bi-LSTM. IEEE Internet of Things Journal, 11(13), 23002–23019. https://doi.org/10.1109/JIOT.2024.3377731
Lee, D., Choo, H., & Jeong, J. (2024). GCN-Based LSTM Autoencoder with Self-Attention for Bearing Fault Diagnosis. Sensors, 24(15). https://doi.org/10.3390/s24154855
Lei, J., Liu, C., & Jiang, D. (2019). Fault diagnosis of wind turbine based on Long Short-term memory networks. Renewable Energy, 133, 422–432. https://doi.org/10.1016/j.renene.2018.10.031
Li, Y., Liu, B., Jia, Z., Liu, Z. (2023). Transformer-based fault diagnosis method for fixed-wing UAV elevator. Maintainability and Safety (ICRMS). Urumuqi, China. 1018-1023. doi: 10.1109/ICRMS59672.2023.00178.
Ma, L., Guo, J., Wang, S., Wang, J. (2021). Multi-Source Sensor Fault Diagnosis Method Based on Improved CNN-GRU Network [J]. Transactions of Beijing Institute of Technology, 2021, 41(12): 1245-1252. DOI: 10.15918/j.tbit1001-0645.2020.183
Masalimov, K., Muslimov, T., Munasypov, R. (2022). Real-Time Monitoring of Parameters and Diagnostics of the Technical Condition of Small Unmanned Aerial Vehicle’s (UAV) Units Based on Deep BiGRU-CNN Models. Drones, 6(11), 368. https://doi.org/10.3390/drones6110368
Mao, N., Xu, J., Li, J., He, H. (2021). A LSTM-RNN-Based Fiber Optic Gyroscope Drift Compensation. Mathematical Problems in Engineering. 1-10. https://doi.org/10.1155/2021/1636001
Mohsan, S. A. H., Khan, M. A., Noor, F., Ullah, I., & Alsharif, M. H. (2022). Towards the Unmanned Aerial Vehicles (UAVs): A Comprehensive Review. Drones, 6(6). https://doi.org/10.3390/drones6060147
Ossmann, D., Weiser, C., Biertumpfel, F., Pfifer, H., Cieslak, J. (2023). Flight Control Reconfiguration in Oscillatory Failure Case Scenarios. IFAC-PapersOnLine. 56(2). 396-401. https://doi.org/10.1016/j.ifacol.2023.10.1600
Ossmann, D., & van der Linden, F. L. J. (2015). Advanced sensor fault detection and isolation for electro-mechanical flight actuators. 2015 NASA/ESA Conference on Adaptive Hardware and Systems (AHS), 1–8. https://doi.org/10.1109/AHS.2015.7231162
Pang, Y., Kendall, A. P., & Clarke, J. P. (2025). The Reliability of Remotely Piloted Aircraft System Performance under Communication Loss and Latency Uncertainties. arXiv preprint arXiv:2501.07743. https://doi.org/10.48550/arXiv.2501.07743
Park, W., Lee, S., Song, J. (2009). Fault detection and isolation of DURUMI-II using similarity measure. Journal of Mechanical Science and Technology. 23(2). 302-310. https://doi.org/10.1007/s12206-009-0107-z
Peng, Z., Sun, Z., Chen, J., Ping, Z., Dong, K., Li, J., Fu, Y., Zio, E. (2022). A Fault Diagnosis Approach for Electromechanical Actuators with Simulating Model under Small Experimental Data Sample Condition. Actuators, 11(3), 66. https://doi.org/10.3390/act11030066
Puchalski, R., Bondyra, A., Giernacki, W., & Zhang, Y. (2022). Actuator fault detection and isolation system for multirotor unmanned aerial vehicles. 2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR), 364–369. https://doi.org/10.1109/MMAR55195.2022.9874283
Puchalski, R., & Giernacki, W. (2022). UAV Fault Detection Methods, State-of-the-Art. Drones, 6(11). https://doi.org/10.3390/drones6110330
Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., & Cottrell, G. W. (2017). A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, 2627–2633. https://doi.org/10.24963/ijcai.2017/366
Reynoso-Meza, G., Ribeiro, V. H. A., Filho, M. F., de Abreu, B. Z. (2023). Time Stacking Decision Tree for Oscillatory Failure Case Detection in a Flight Control System. IFAC-PapersOnLine. 56(2). 354-359. https://doi.org/10.1016/j.ifacol.2023.10.1593
Rudin, K., Mosimann, L., Ducard, G. J. J., & Siegwart, R. Y. (2015). Robust Actuator Fault-tolerant Control using DK-Iteration: Theory and Application to UAS. IFAC-PapersOnLine, 48(21), 392–397. https://doi.org/10.1016/j.ifacol.2015.09.558
Schuster, M., & Paliwal, K. K. (1997). Bidirectional recurrent neural networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681. https://doi.org/10.1109/78.650093
Simani, S., Fantuzzi, C., & Patton, R. J. (2003). Model-based fault diagnosis in dynamic systems using identification techniques. International Journal of Robust and Nonlinear Control, XV, 282. https://doi.org/10.1007/978-1-4471-3829-7
Singh, Y., Bagri, K., Jayakumar, A., Rizzoni, G. (2023). Fault Diagnostics for Oscillatory Failure Case in Aircraft Elevator Servos. IFAC-PapersOnLine. 56(2). 408-415. https://doi.org/10.1016/j.ifacol.2023.10.1602
Su, Z., Qi, B., Wang, B., Liu, D. (2024). A Transformer-Based Condition Monitoring Method for UAV. Lecture Notes in Electrical Engineering, vol 1173. Springer, Singapore. https://doi.org/10.1007/978-981-97-1087-4_45
Sun, J., Ren, H., Duan, Y., Yang, X., Wang, D., & Tang, H. (2024). Fusion of Multi-Layer Attention Mechanisms and CNN-LSTM for Fault Prediction in Marine Diesel Engines. Journal of Marine Science and Engineering, 12(6). https://doi.org/10.3390/jmse12060990
Tao, X., Guo, Y., Zhao, W., Zhou, Q., Xu, K. (2023). Fault detection and isolation of electromechanical actuator based on SAE-BiLSTM. Journal of Physics: Conference Series. 2472(1). 012031. https://doi.org/10.1088/1742-6596/2472/1/012031
Telli, K., Kraa, O., Himeur, Y., Ouamane, A., Boumehraz, M., Atalla, S., & Mansoor, W. (2023). A Comprehensive Review of Recent Research Trends on Unmanned Aerial Vehicles (UAVs). Systems, 11(8). https://doi.org/10.3390/systems11080400
Vanga, J., Ranimekhala, D. P., Jonnala, S., Jamalapuram, J., Gutta, B., Gampa, S. R., & Alluri, A. (2023). Fault classification of three phase induction motors using Bi-LSTM networks. Journal of Electrical Systems and Information Technology, 10(1), 28. https://doi.org/10.1186/s43067-023-00098-x
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, L., Polosukhin, I. (2017). Attention Is All You Need. 10.48550/arXiv.1706.03762.
Venkataraman, R., Bauer, P., Sailer, P., Vanek, B. (2019). Comparison of Fault Detection and Isolation Methods for A Small Unmanned Aircraft. Control Engineering Practice. 84. 365-376. https://doi.org/10.1016/j.conengprac.2018.12.002
Wang, L., Zhao, W., Liu, Z., Dang, Q., Zou, X., Wang, K. (2023). Incipient Fault Detection and Reconstruction Using an Adaptive Sliding-Mode Observer for the Actuators of Fixed-Wing Aircraft. Aerospace, 10, 422. https://doi.org/10.3390/aerospace10050422
Yoo, J., Song, S., Chang, K., & Baek, J.-G. (2023). Fault detection and diagnosis using two-stage attention-based variational LSTM in electrolytic copper manufacturing process. The International Journal of Advanced Manufacturing Technology, 129(3), 1269–1288. https://doi.org/10.1007/s00170-023-12356-3
Yu, J., Chang, J., Chen, W., Cieslak, J., Ossmann, D. (2024). IFAC-PapersOnLine. 58(4). 115-120. https://doi.org/10.1016/j.ifacol.2024.07.203
Yu, L., Qu, J., Gao, F., & Tian, Y. (2019). A Novel Hierarchical Algorithm for Bearing Fault Diagnosis Based on Stacked LSTM. Shock and Vibration, 2019(1), 2756284. https://doi.org/10.1155/2019/2756284
Zhang, Q., Zhang, J., Zou, J., & Fan, S. (2020). A Novel Fault Diagnosis Method based on Stacked LSTM. IFAC-PapersOnLine, 53(2), 790–795. https://doi.org/10.1016/j.ifacol.2020.12.832
Zolghadri, A., Gheorghe, A., Cieslak, J., Henry, D., Goupil, P., Dayre, R., Le Berre, H. (2011). A Model-based Solution of Robust and Early Detection of Control Surface Runaways. SAE International Journal of Aerospace. 4(2). 2011-01-2803. https://doi.org/10.4271/2011-01-2803