مهندسی مکانیک مدرس

مهندسی مکانیک مدرس

طراحی سامانه کنترل پرواز تحمل‌پذیر خطا برای هواپیمای شش‌درجه‌آزادی مبتنی بر GRU، TCN و رأی‌گیری مقاوم

نوع مقاله : مقاله پژوهشی

نویسندگان
گروه مهندسی هوافضا، دانشکده فنی و مهندسی، دانشگاه اصفهان، اصفهان، ایران
چکیده
در این پژوهش، یک چارچوب کنترل تحمل‌پذیر خطا برای هواپیمای شش‌درجه‌آزادی با هدف حفظ عملکرد سامانه کنترل پرواز در برابر خطاهای نرم‌افزاری ارائه شده است. با توجه به وابستگی روزافزون سامانه‌های پروازی به ساختارهای نرم‌افزارمحور، بروز خطا در مسیر تولید فرمان می‌تواند موجب افت محسوس کیفیت کنترل شود. در ساختار پیشنهادی، کنترل‌کننده‌های کلاسیک برای کانال‌های طولی و عرضی طراحی شده‌اند و به‌منظور ارزیابی عملکرد روش، یک خطای نرم‌افزاری در کانال عرضی اعمال شده است. برای جبران اثر این خرابی در فرمان ایلرون، دو مدل داده‌محور شامل واحد بازگشتی دروازه‌دار (GRU) و شبکه کانولوشنی زمانی (TCN) بر پایه داده‌های زمانی پرواز آموزش داده شده‌اند تا به‌صورت موازی فرمان کمکی تولید کنند. خروجی این دو مدل همراه با خروجی کنترل‌کننده اصلی از طریق یک سازوکار رأی‌گیری مقاوم تلفیق می‌شود. این سازوکار با تکیه بر شاخص‌های سلامت و کاهش اثر مسیر معیوب، فرمان نهایی پایدارتری در اختیار سامانه قرار می‌دهد. برای بررسی پایداری و مقاومت ساختار پیشنهادی، سامانه تحت اغتشاشات شدید جوی مبتنی بر مدل استاندارد درایدن قرار گرفته است. نتایج شبیه‌سازی نشان می‌دهد که روش پیشنهادی می‌تواند اثر خرابی را تضعیف کرده، پیوستگی عملکرد کانال عرضی را حفظ کند و بدون نیاز به مدل دقیق خرابی، پایداری پاسخ سامانه را در شرایط خطا بهبود دهد. در مجموع، ترکیب کنترل کلاسیک، مدل‌های داده‌محور و رأی‌گیری مقاوم، رویکردی مؤثر برای افزایش تحمل‌پذیری خطا در سامانه‌های کنترل پرواز فراهم می‌کند.
کلیدواژه‌ها
موضوعات

عنوان مقاله English

Design of a Fault-Tolerant Flight Control System for a Six-Degree-of-Freedom Aircraft Using GRU, TCN and Robust Voting

نویسندگان English

Sayed Mahdi Mortazavi
Hojat Taei
Department of Aerospace Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran
چکیده English

This study presents a fault-tolerant control framework for a six-degree-of-freedom aircraft aimed at preserving flight control system performance in the presence of software faults. As flight systems become increasingly dependent on software-based architectures, faults in the command generation path can lead to noticeable degradation in control quality. In the proposed structure, classical controllers are designed for the longitudinal and lateral channels, and a software fault is intentionally introduced in the lateral channel to evaluate the effectiveness of the method. To compensate for the failure effect on the aileron command, two data-driven models, namely a Gated Recurrent Unit (GRU) and a Temporal Convolutional Network (TCN), are trained using flight time-series data to generate auxiliary commands in parallel. The outputs of these two models, together with the output of the main controller, are fused through a robust voting mechanism. By relying on health indicators and reducing the influence of the faulty path, this mechanism provides a more stable final command to the system. To investigate the robustness of the proposed framework, the aircraft is subjected to severe atmospheric disturbances generated based on the standard Dryden turbulence model. Simulation results demonstrate that the proposed approach can mitigate the impact of the fault, preserve the continuity of lateral channel performance, and improve the stability of the system response under faulty and turbulent conditions without requiring an accurate fault model. Overall, the integration of classical control, data-driven models, and robust voting offers an effective solution for enhancing fault tolerance in flight control systems.

کلیدواژه‌ها English

Flight Control
Fault-Tolerant Control
Robust Voting
Gated Recurrent Unit (GRU)
Temporal Convolutional Network (TCN)
[1] Y. Zhang and J. Jiang, “Bibliographical review on reconfigurable fault-tolerant control systems,” Annu. Rev. Control, vol. 49, pp. 1–20, 2020. doi: 10.1016/j.arcontrol.2020.02.001.
[2] C. Edwards, T. Lombaerts, and H. Smaili, Eds., Fault-Tolerant Flight Control: A Benchmark Challenge. Berlin, Germany: Springer, 2010. doi: 10.1007/978-3-642-11690-2.
[3] K. Cho, B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” in Proc. Conf. Empirical Methods Natural Lang. Process. (EMNLP), 2014, pp. 1724–1734.
[4] S. Bai, J. Z. Kolter, and V. Koltun, “An empirical evaluation of generic convolutional and recurrent networks for sequence modeling,” arXiv preprint arXiv:1803.01271, 2018.
[5] R. Isermann, Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance. Berlin, Germany: Springer, 2006. doi: 10.1007/978-3-540-30368-8.
[6] Q. Li, Z. Ren, S. Dai, and W. Wang, “A new robust fault-tolerant controller for self-repairing flight control system,” J. Franklin Inst., vol. 350, no. 9, pp. 2611–2633, 2013. doi: 10.1016/j.jfranklin.2013.02.020.
[7] D. Kim and Y. Kim, “Robust variable structure controller design for fault tolerant flight control,” J. Guid. Control Dyn., vol. 23, no. 3, pp. 434–442, 2000. doi: 10.2514/2.4557.
[8] B. Li, W. Dong, and C. Xiong, “Robust actuator-fault-tolerant control system based on sliding-mode observer for thrust-vectoring aircrafts,” Asian J. Control, vol. 21, no. 1, pp. 1–12, 2019. doi: 10.1002/asjc.1841.
[9] F. Caliskan and C. Hajiyev, “Active fault-tolerant control of UAV dynamics against sensor-actuator failures,” J. Aerosp. Eng., vol. 29, no. 3, 2016. doi: 10.1061/(ASCE)AS.1943-5525.0000579.
[10] Y. Liu, S. Hong, E. Zio, and J. Liu, “Integrated fault estimation and fault-tolerant control for a flexible regional aircraft,” Chin. J. Aeronaut., vol. 34, no. 1, pp. 195–207, 2021. doi: 10.1016/j.cja.2020.08.032.
[11] Y. X. Xue, Z. Y. Zhen, L. Q. Yang, and L. D. Wen, “Adaptive fault-tolerant control for carrier-based UAV with actuator failures,” Aerosp. Sci. Technol., vol. 105, Art. no. 106227, 2020. doi: 10.1016/j.ast.2020.106227.
[12] L. Zuo and L. Yao, “Fault isolation and fault tolerant control for the uncertain quadrotor UAV system,” Int. J. Control Autom. Syst., vol. 22, no. 1, pp. 301–310, 2024. doi: 10.1007/s12555-022-0249-7.
[13] A. Marcos, S. Waitman, and M. Sato, “Fault tolerant linear parameter varying flight control design, verification and validation,” J. Franklin Inst., vol. 358, no. 1, pp. 1045–1073, 2021. doi: 10.1016/j.jfranklin.2021.02.040.
[14] X. Wang, J. Du, W. Jia, S. Liu, and Y. Lyu, “A fault reconstruction method for aircraft with multiple control surfaces,” in ICGNC 2022, L. Yan et al., Eds., Lecture Notes in Electrical Engineering, vol. 845. Singapore: Springer, pp. 4672–4682, 2023. doi: 10.1007/978-981-19-6613-2_453.
[15] P. Freeman, R. Pandita, N. Srivastava, and G. J. Balas, “Model-based and data-driven fault detection performance for a small UAV,” IEEE/ASME Trans. Mechatronics, vol. 18, no. 4, pp. 1300–1309, 2013. doi: 10.1109/TMECH.2013.2258678.
[16] T. Grof and P. Bauer, “Voting-based fault detection for aircraft position measurements with dissimilar observations,” IFAC-PapersOnLine, vol. 53, no. 2, pp. 7241–7246, 2020. doi: 10.1016/j.ifacol.2020.12.1841.
[17] M. Shin, Y. Cho, and H. Son, “Robust estimation and sensor fault management using probabilistic voting algorithm in UAVs,” IEEE Sensors Journal, vol. 24, no. 24, 2024, doi: 10.1109/JSEN.2024.3483220.
[18] Z. Xu, Y. Li, C. Feng, and L. Zhang, “Exact fault-tolerant consensus with voting validity,” in Proc. 2023 IEEE Int. Parallel Distrib. Process. Symp. (IPDPS), St. Petersburg, FL, USA, 2023, pp. 842–852. doi: 10.1109/IPDPS54959.2023.00089.
[19] S. Ifqir, C. Combastel, A. Zolghadri, G. Alcalay, P. Goupil, and S. Merlet, “Fault tolerant multi-sensor data fusion for autonomous navigation in future
civil aviation operations,” Control Eng. Pract.,
vol. 123, no. 105132, 2022.
doi: 10.1016/j.conengprac.2022.105132.
[20] S. Sun, X. Feng, W. Xu, M. Shao, and K. Tang, “A deep learning framework for aircraft noise prediction and system-level application,” in Proc. 2025 4th Int. Symp. Aerospace Engineering and Systems (ISAES), 2025, doi: 10.1109/ISAES66870.2025.11274357.
[21] F. Chen, Y. Yu, and Y. Li, “An aero-engine remaining useful life prediction model based on clustering analysis and the improved GRU–TCN,” Meas. Sci. Technol., vol. 36, Art. no. 016001, 2025.
[22] B. L. Stevens, F. L. Lewis, and E. N. Johnson, Aircraft Control and Simulation: Dynamics, Controls Design, and Autonomous Systems, 3rd ed. Hoboken, NJ, USA: Wiley, 2015.
[23] B. Etkin and L. D. Reid, Dynamics of Flight: Stability and Control, 3rd ed. Hoboken, NJ, USA: Wiley, 1996.
[24] H. Asharioun, M. Jahanshahifar, M. Davoodi, and M. Mazare, " Real-Time  Fault Tolerant Attitude Stabilization  Control of a Quadrotor in the Presence of Actuator Fault," Modares Mechanical Engineering, vol. 23, no. 7, pp. 435-448, 2023. doi: 10.22034/mme.23.7.424.
[25] M. Najafi, Sh. Rahmanian, and B. Shirani, "Design of an H∞-PID Controller for an UAV Auto-Landing System Based on External Navigation," Modares Mechanical Engineering, vol. 17, no. 11, pp. 88-96, 2018. doi: 20.1001.1.10275940.1396.17.11.13.3.
[26] U.S. Department of Defense, Flying Qualities of Piloted Airplanes, Military Specification MIL-F-8785C, Nov. 1980.
[27] A. van den Oord, S. Dieleman, H. Zen, K. Simonyan, O. Vinyals, A. Graves, N. Kalchbrenner, A. Senior, and K. Kavukcuoglu, “WaveNet: A generative model for raw audio,” arXiv preprint arXiv:1609.03499, 2016.
[28] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929–1958, 2014.
[29] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
[30] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. 3rd Int. Conf. Learn. Representations (ICLR), 2015.
[31]M. Blanke, M. Kinnaert, J. Lunze, and M. Staroswiecki, Diagnosis and Fault-Tolerant Control, 3rd ed. Berlin, Germany: Springer, 2016. doi: 10.1007/978-3-662-47943-8.