Combined Fault Diagnosis Scheme Based on Recurrent Neural Network and Observer for Satellite Attitude Control System
Publication: Journal of Aerospace Engineering
Volume 36, Issue 5
Abstract
This study proposes a combined fault diagnosis scheme based on a recurrent neural network (RNN) and an observer for satellite attitude control systems (ACSs) in the presence of model uncertainties, external disturbances, and measurement noise. The ACS is decoupled into multiple independent channels, such that the residuals generated by the observers respond to the corresponding faults. A novel multilayer adaptive Gaussian recurrent neural network (MAGRNN) structure is developed as an approximator to estimate the lumped disturbance; a robust term is introduced to improve accuracy. Considering the actuator fault in the finite frequency domain and the fault-sensitive index, a set of unknown input observers (UIOs) is designed using the output of the MAGRNN-based approximator as compensation. The existence conditions of the approximator and observer are proposed and proved. The fault diagnosis results for three cases verify that the proposed method can be used for small fault detection and isolation.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This work was supported by the Interdisciplinary Innovation Foundation for Graduates (Grant No. KXKCXJJ202010), the Experimental Technology Research and Development Project 2020 of Nanjing University of Aeronautics and Astronautics (Grant No. 2020051500058011), the Chinese Scholarship Council (Grant No. 202106830050), and the Foundation of Graduate Innovation Center in Nanjing University of Aeronautics and Astronautics (Grant No. kfjj20181507).
References
Ahmadi, N., and G. Akbarizadeh. 2018. “Hybrid robust iris recognition approach using iris image pre-processing, two-dimensional gabor features and multi-layer perceptron neural network/PSO.” IET Biom. 7 (2): 153–162. https://doi.org/10.1049/iet-bmt.2017.0041.
Baldi, P., M. Blanke, P. Castaldi, N. Mimmo, and S. Simani. 2019. “Fault diagnosis for satellite sensors and actuators using nonlinear geometric approach and adaptive observers.” Int. J. Robust Nonlinear Control 29 (16): 5429–5455. https://doi.org/10.1002/rnc.4083.
Chen, J., and Y. Y. Cao. 2013. “A fault detection observer design for LPV systems in finite frequency domain.” Int. J. Control 86 (2): 290–298. https://doi.org/10.1080/00207179.2012.723829.
Chen, T., C. Wang, H. Guo, J. David, and D. Zhaoyang. 2019. “Small fault detection for a class of closed-loop systems via deterministic learning.” IEEE Trans. Cybern. 49 (3): 897–906. https://doi.org/10.1109/TCYB.2018.2789360.
Cheng, L., Z. Wang, Y. Song, and F. Jiang. 2020. “Real-time optimal control for irregular asteroid landings using deep neural networks.” Acta Astronaut. 170 (11): 66–79. https://doi.org/10.1016/j.actaastro.2019.11.039.
Cheng, Y., R. Wang, and M. Xu. 2015. “A combined model-based and intelligent method for small fault detection and isolation of actuators.” IEEE Trans. Ind. Electron. 2015 (1): 1–11. https://doi.org/10.1109/TIE.2015.2499722.
Choi, Y. C., J. H. Son, and H. S. Ahn. 2015. “Fault detection and isolation for a small CMG-based satellite: A fuzzy Q-learning approach.” Aerosp. Sci. Technol. 47 (Dec): 340–355. https://doi.org/10.1016/j.ast.2015.10.006.
Chu, Y., J. Fei, and S. Hou. 2019. “Adaptive global sliding-mode control for dynamic systems using double hidden layer recurrent neural network structure.” IEEE Trans. Networks Learn. Syst. 31 (4): 1297–1309. https://doi.org/10.1109/TNNLS.2019.2919676.
El-Sousy, F. F. M., and K. A. Abuhasel. 2016. “Self-organizing recurrent fuzzy wavelet neural network-based mixed H2/H∞ adaptive tracking control for uncertain two-axis motion control system.” IEEE Trans. Ind. Appl. 52 (6): 5139–5155. https://doi.org/10.1109/TIA.2016.2591901.
Fei, J., and H. Ding. 2012. “Adaptive sliding mode control of dynamic system using RBF neural network.” Nonlinear Dyn. 70 (2): 1563–1573. https://doi.org/10.1007/s11071-012-0556-2.
Gao, C., Q. Zhao, and G. Duan. 2013. “Robust actuator fault diagnosis scheme for satellite attitude control systems.” J. Franklin Inst. 350 (9): 2560–2580. https://doi.org/10.1016/j.jfranklin.2013.02.021.
Guo, X. G., M. E. Tian, Q. Li, C. Ahn, and Y. H. Yang. 2020. “Multiple-fault diagnosis for spacecraft attitude control systems using RBFNN-based observers.” Aerosp. Sci. Technol. 106 (Nov): 106195. https://doi.org/10.1016/j.ast.2020.106195.
Hwang, I., S. Kim, Y. Kim, and C. E. Seah. 2010. “A survey of fault detection, isolation, and reconfiguration methods.” IEEE Trans. Control Syst. Technol. 18 (3): 636–653. https://doi.org/10.1109/TCST.2009.2026285.
Jo, S., M. Park, and G. Jung-Guk. 2016. “Approximate Bayesian MLP regularization for regression in the presence of noise.” Neural Networks 83 (Nov): 75–85. https://doi.org/10.1016/j.neunet.2016.07.010.
Li, X.-J., and G.-H. Yang. 2014. “Fault detection in finite frequency domain for Takagi-Sugeno fuzzy systems with sensor faults.” IEEE Trans. Cybern. 44 (8): 1446–1458. https://doi.org/10.1109/TCYB.2013.2286209.
Long, D., X. Wen, W. Zhang, and J. Wang. 2020. “Recurrent neural network based robust actuator and sensor fault estimation for satellite attitude control system.” IEEE Access 8 (Feb): 183165–183174. https://doi.org/10.1109/ACCESS.2020.3029066.
Lu, J.-G., and Y.-Q. Chen. 2010. “Robust stability and stabilization of fractional-order interval systems with the fractional order: The case.” IEEE Trans. Autom. Control 55 (1): 152–158. https://doi.org/10.1109/TAC.2009.2033738.
Mannarino, A., K. Mantegazza, and A. Paolo. 2015. “Nonlinear aerodynamic reduced order modeling by discrete time recurrent neural networks.” Aerosp. Sci. Technol. 47 (Dec): 406–419. https://doi.org/10.1016/j.ast.2015.10.009.
Mrugalski, M., M. Luzar, M. Pazera, M. Witczak, and C. Aubrun. 2016. “Neural network-based robust actuator fault diagnosis for a non-linear multi-tank system.” ISA Trans. 61 (Mar): 318–328. https://doi.org/10.1016/j.isatra.2016.01.002.
Rahimi, A., K. D. Kumar, and H. Alighanbari. 2019. “Fault isolation of reaction wheels for satellite attitude control.” IEEE Trans. Aerosp. Electron. Syst. 56 (1): 610–629. https://doi.org/10.1109/TAES.2019.2946665.
Simani, S., C. Fantuzzi, and R. J. Patton. 2003. “Model-based fault diagnosis techniques.” In Model-based fault diagnosis in dynamic systems using identification techniques, 19–60. Berlin: Springer.
Sobhani-Tehrani, E., H. A. Talebi, and K. Khorasani. 2014. “Hybrid fault diagnosis of nonlinear systems using neural parameter estimators.” Neural Networks 50 (Apr): 12–32. https://doi.org/10.1016/j.neunet.2013.10.005.
Tafazoli, M. 2009. “A study of on-orbit spacecraft failures.” Acta Astronaut. 64 (2–3): 195–205. https://doi.org/10.1016/j.actaastro.2008.07.019.
Wang, H., and G. H. Yang. 2008. “A finite frequency domain approach to fault detection for linear discrete-time systems.” Int. J. Control 81 (7): 1162–1171. https://doi.org/10.1080/00207170701691513.
Wang, L., Z. Lei, and Y. Zhang. 2017a. “Trajectory predictor by using recurrent neural networks in visual tracking.” IEEE Trans. Cybern. 17 (10): 3172–3183. https://doi.org/10.1109/TCYB.2017.2705345.
Wang, R., Y. Cheng, and M. Xu. 2015. “Analytical redundancy based fault diagnosis scheme for satellite attitude control systems.” J. Franklin Inst. 352 (5): 1906–1931. https://doi.org/10.1016/j.jfranklin.2015.02.003.
Wang, Z., P. Shi, and C. C. Lim. 2017b. “Fault detection observer in finite frequency domain for linear parameter-varying descriptor systems.” Automatica 86 (Dec): 38–45. https://doi.org/10.1016/j.automatica.2017.08.021.
Wu, X., S. Luo, C. Wei, and Y. Liao. 2020. “Observer-based fault-tolerant attitude tracking control for rigid spacecraft with actuator saturation and faults.” Acta Astronaut. 81 (2): 512–522. https://doi.org/10.1016/j.actaastro.2012.08.019.
Xin, W., J. Wang, and L. I. Xin. 2018. “A feed-forward wavelet neural network adaptive observer-Based fault detection technique for spacecraft attitude control systems.” Chin. J. Electron. 27 (1): 102–108. https://doi.org/10.1049/cje.2017.11.010.
Yuandong, L., H. Qinglei, and S. Xiaodong. 2022. “Neural network-based fault diagnosis for spacecraft with single-gimbal control moment gyros.” Chin. J. Aeronaut. 35 (7): 261–273. https://doi.org/10.1016/j.cja.2021.11.020.
Zhou, B. K. 1998. Solutions manual: Essentials of robust control. Upper Saddle River, NJ: Prentice-Hall.
Zhou, M., Z. Cao, M. C. Zhou, and J. Wang. 2019. “Finite-frequency H−/H∞ fault detection for discrete-time T–S fuzzy systems with unmeasurable premise variables.” IEEE Trans. Cybern. 51 (6): 3017–3026. https://doi.org/10.1109/TCYB.2019.2915050.
Information & Authors
Information
Published In
Journal of Aerospace Engineering
Volume 36 • Issue 5 • September 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Mar 26, 2022
Accepted: Mar 27, 2023
Published online: Jun 19, 2023
Published in print: Sep 1, 2023
Discussion open until: Nov 19, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.