Design of Neural Network for Satellite’s Attitude Control Systems


Article Preview

The objective of this paper is to design a neural network-based residual generator to detect the fault in the actuators for a specific communication satellite in its attitude control system (ACS). First, a design of dynamic neural network with dynamic neurons is done, those neurons corresponds a second order linear Infinite Impulse Response (IIR) filter and a nonlinear activation function with adjustable parameters. Second, the parameters from the network are adjusted to minimize a performance index specified by the output estimated error, with the given input-output data collected from the specific ACS. Then, the designed dynamic neural network is trained and applied for detecting the faults injected to the wheel, which is the main actuator in the normal mode for the communication satellite. Then the performance and capabilities of the designed network were tested and compared with a conventional model-based observer residual, showing the differences between these two methods, and indicating the benefit of the proposed design to know the real status of the momentum wheel. Finally, the application of the methods in a satellite ground station is discussed.



Edited by:

Wu Fan




S. Montenegro and L. Luna, "Design of Neural Network for Satellite’s Attitude Control Systems", Applied Mechanics and Materials, Vols. 110-116, pp. 5001-5008, 2012

Online since:

October 2011




[1] R. Isermann. Fault-Diagnosis System, Springer-Verlag Berlin Heidelberg. (2006).

[2] J R. Patton, F Uppal and C. Lopez, Soft computing approaches to fault diagnosis for dynamic systems: a survey, 4th. IFAC Symposium on fault Detection, Budapest, Vol. 1, pp.298-311, June (2000).


[3] S. Montenegro and K. Amezquita, Accomplishing Station Keeping Mode for AOCS designed for T-SAT, Advances in Neural Network Research, The sixth ISNN 2009, Wuhan, China, (2009).


[4] A. Alessandri, Fault diagnosis for nonlinear systems using a bank of neural estimators, Computers in Industry, Vol. 52, No. 3, Dec. (2003).


[5] K. Patan, T. Parisini, Identification of neural dynamic models for fault detection and isolation, Journal of Process Control, (2004).

[6] T. Sorsa, H. N. Koivo, and H. Koivisto, Neural networks in process fault diagnostics, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 21, No. 4, 815 - 825, (1991).


[7] S. Simani, C. Fantuzzi and R. J. Patton, Model-Based Fault Diagnosis in Dynamic Systems Using Identification Techniques, Springer (2003).


[8] J. Wertz. Spacecraft Attitude Determination and Control., Kluwer Academic Publishers, (1978).

[9] M. J. Sidi. Spacecraft Dynamics and Control., Cambridge University Press, Cambridge New York, (1997).

[10] B Bialke, High fidelity mathematical modelling of reaction wheel performance, 21st AAAS. Guidance and Control Conference, (1998).

[11] W. Qing and S. Mehrdad Model-based Robust Fault Diagnosis for Satellite Control Systems Using Learning and Sliding Mode Approaches, Journal of Computers, Canada. (2009).


[12] M. Ayoubi, Fault diagnosis with dynamic neural structure and application to a turbo-charger, " AFEPROCESS, 94, Espoo, Finland, Vol. 2, pp.618-623, (1994).

[13] J. Korbicz and K. Patan, Dynamic neural networks for process modeling in fault detection and isolation systems, International Journal of Applied Mathematics and Computer Science, (1999).

[14] I. Al-Zyoud and K. Khorasani, Neural network-based Actuactor Fault Diagnosis for Attitude Control Subsystem of an Unmanned Space Vehicle, International Joint Conference on Neural Networks, Vancouver, Canada. pp.3686-3693. July, (2006).


Fetching data from Crossref.
This may take some time to load.