Reaction Wheels Fault Isolation Onboard 3-Axis Controlled Satel-lite using Enhanced Random Forest with Multidomain Features
Mofiyinoluwa O. Folami
As the number of satellite launches increases each year, it is only natural that an interest in the safety and monitoring of these systems would increase as well. However, as a system becomes more complex, generating a high-fidelity model that accurately describes the system becomes complicated. Therefore, imploring a data-driven method can provide to be more beneficial for such applications. This research proposes a novel approach for data-driven machine learning techniques on the detection and isolation of nonlinear systems, with a case-study for an in-orbit closed loop-controlled satellite with reaction wheels as actuators. High-fidelity models of the 3-axis controlled satellite are employed to generate data for both nominal and faulty conditions of the reaction wheels. The generated simulation data is used as input for the isolation method, after which the data is pre-processed through feature extraction from a temporal, statistical, and spectral domain. The pre-processed features are then fed into various machine learning classifiers. Isolation results are validated with cross-validation, and model parameters are tuned using hyperparameter optimization. To validate the robustness of the proposed method, it is tested on three characterized datasets and three reaction wheel configurations, including standard four-wheel, three-orthogonal, and pyramid. The results prove superior performance isolation accuracy for the system under study compared to previous studies using alternative methods (Rahimi & Saadat, 2019, 2020).
Reaction Wheels, Fault Isolation, Random Forest, Satellite Attitude Control
Barandas, M., Folgado, D., Fernandes, L., Santos, S., Abreu, M., Bota, P., Liu, H., Schultz, T., & Gamboa, H. (2020). TSFEL: Time Series Feature Extraction Library. SoftwareX. https://doi.org/10.1016/j.softx.2020.100456
Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. In Artificial Intelligence Review (Vol. 54, Issue 3). Springer Netherlands. https://doi.org/10.1007/s10462-020-09896-5
Bialke, B. (1998). High Fidelity Mathematical Modeling of Reaction Wheel Performance. 1998 Annual AAS Rocky Mountain Guidance and Control Conference, Advances in the Astronautical Sciences, 483–496.
Charbuty, B., & Abdulazeez, A. (2021). Classification Based on Decision Tree Algorithm for Machine Learning. Journal of Applied Science and Technology Trends, 2(01), 20–28. https://doi.org/10.38094/jastt20165
ElDali, M., & Kumar, K. D. (2021). Fault Diagnosis and Prognosis of Aerospace Systems Using Growing Recurrent Neural Networks and LSTM. 1–20. https://doi.org/10.1109/aero50100.2021.9438432
Godard. (2010). Fault Tolerant Control of Spacecraft [Ryerson University]. https://digital.library.ryerson.ca/islandora/object/RULA%3A1518/datastream/OBJ/download/Fault_Tolerant_Control_Of_Spacecraft.pdf
Ismail, Z., & Varatharajoo, R. (2010). A study of reaction wheel configurations for a 3-axis satellite attitude control. Advances in Space Research, 45(6), 750–759. https://doi.org/10.1016/j.asr.2009.11.004
Jia, Q., Li, H., Chen, X., & Zhang, Y. (2019). Observer-based reaction wheel fault reconstruction for spacecraft attitude control systems. Aircraft Engineering and Aerospace Technology, 91(10), 1268–1277. https://doi.org/10.1108/AEAT-07-2018-0203
Kök, I. (2012). Comparison and Analysis of Attitude Control Systems of a Satellite Using Reaction Wheel Actuators. 17–18.
Kumar, K. D., Godard, Abreu, N., & Sinha, M. (2018). Fault-tolerant attitude control of miniature satellites using reaction wheels. Acta Astronautica, 151(May), 206–216. https://doi.org/10.1016/j.actaastro.2018.05.004
Lee, K. H., Lim, S. M., Cho, D. H., & Kim, H. D. (2020). Development of Fault Detection and Identification Algorithm Using Deep learning for Nanosatellite Attitude Control System. International Journal of Aeronautical and Space Sciences, 21(2), 576–585. https://doi.org/10.1007/s42405-019-00235-9
Mishra, K. M., & Huhtala, K. J. (2019). Fault Detection of Elevator Systems Using Multilayer Perceptron Neural Network. IEEE International Conference on Emerging Technologies and Factory Automation, ETFA, 2019-Septe, 904–909. https://doi.org/10.1109/ETFA.2019.8869230
Nemati, F., Safavi Hamami, S. M., & Zemouche, A. (2019). A nonlinear observer-based approach to fault detection, isolation and estimation for satellite formation flight application. Automatica, 107, 474–482. https://doi.org/10.1016/j.automatica.2019.06.007
Nozari, H. A., Castaldi, P., Banadaki, H. D., & Simani, S. (2019). Novel non-model-based fault detection and isolation of satellite reaction wheels based on a mixed-learning fusion framework. IFAC-PapersOnLine. https://doi.org/10.1016/j.ifacol.2019.11.222
Probst, P., Wright, M. N., & Boulesteix, A. L. (2019). Hyperparameters and tuning strategies for random forest. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 9(3), 1–15. https://doi.org/10.1002/widm.1301
Rahimi, A., Kumar, K. D., & Alighanbari, H. (2017). Fault estimation of satellite reaction wheels using covariance based adaptive unscented Kalman filter. Acta Astronautica, 134, 159–169. https://doi.org/10.1016/j.actaastro.2017.02.003
Rahimi, A., & Saadat, A. (2019). Fault isolation of reaction wheels onboard 3-axis controlled in-orbit satellite using ensemble machine learning techniques. The International Conference on Aerospace System Science and Engineering.
Rahimi, A., & Saadat, A. (2020). Fault isolation of reaction wheels onboard three-axis controlled in-orbit satellite using ensemble machine learning. Aerospace Systems, 3(2), 119–126. https://doi.org/10.1007/s42401-020-00046-x
Ramachandran, M., & Siddique, Z. (2019). A Data-Driven, Statistical Feature-Based, Neural Network Method for Rotary Seal Prognostics. Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems. https://doi.org/10.1115/1.4043191
Sobhani-Tehrani, E., Talebi, H. A., & Khorasani, K. (2014). Hybrid fault diagnosis of nonlinear systems using neural parameter estimators. Neural Networks, 50, 12–32. https://doi.org/10.1016/j.neunet.2013.10.005
Tidriri, K., Chatti, N., Verron, S., & Tiplica, T. (2016). Bridging data-driven and model-based approaches for process fault diagnosis and health monitoring: A review of researches and future challenges. Annual Reviews in Control, 42, 63–81. https://doi.org/10.1016/j.arcontrol.2016.09.008