A Recurrent Neural-Network-Based Sensor and Actuator Fault Detection and Isolation for Nonlinear Systems With Application to the Satellite's Attitude Control Subsystem

This paper presents a robust fault detection and isolation (FDI) scheme for a general class of nonlinear systems using a neural-network-based observer strategy. Both actuator and sensor faults are considered. The nonlinear system considered is subject to both state and sensor uncertainties and disturbances. Two recurrent neural networks are employed to identify general unknown actuator and sensor faults, respectively. The neural network weights are updated according to a modified backpropagation scheme. Unlike many previous methods developed in the literature, our proposed FDI scheme does not rely on availability of full state measurements. The stability of the overall FDI scheme in presence of unknown sensor and actuator faults as well as plant and sensor noise and uncertainties is shown by using the Lyapunov's direct method. The stability analysis developed requires no restrictive assumptions on the system and/or the FDI algorithm. Magnetorquer-type actuators and magnetometer-type sensors that are commonly employed in the attitude control subsystem (ACS) of low-Earth orbit (LEO) satellites for attitude determination and control are considered in our case studies. The effectiveness and capabilities of our proposed fault diagnosis strategy are demonstrated and validated through extensive simulation studies.

[1]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[2]  Jean-Jacques E. Slotine,et al.  Hamiltonian adaptive control of spacecraft , 1990 .

[3]  David S. Bayard,et al.  Adaptive Kalman filtering, failure detection and identification for spacecraft attitude estimation , 1995, Proceedings of International Conference on Control Applications.

[4]  Thomas Bak,et al.  Autonomous attitude determination and control system for the Orsted satellite , 1996, 1996 IEEE Aerospace Applications Conference. Proceedings.

[5]  Thomas Bak,et al.  Autonomous Attitude Determination and Control System for the Ørsted Satellite 1996 , 1996 .

[6]  Rafal Wisniewski,et al.  Satellite Attitude Control Using Only Electromagnetic Actuation , 1997 .

[7]  M. Blanke,et al.  Fault-tolerant control-a case study of the Orsted satellite , 1997 .

[8]  J. E. Sedlak.  Improved spacecraft attitude filter using a sequentially correlated magnetometer noise model , 1997, 16th DASC. AIAA/IEEE Digital Avionics Systems Conference. Reflections to the Future. Proceedings.

[9]  Marios M. Polycarpou,et al.  Neural network based fault detection in robotic manipulators , 1998, IEEE Trans. Robotics Autom..

[10]  Marios M. Polycarpou,et al.  Automated fault diagnosis in nonlinear multivariable systems using a learning methodology , 2000, IEEE Trans. Neural Networks Learn. Syst..

[11]  N. Hovakimyan,et al.  An adaptive observer design methodology for bounded nonlinear processes , 2002, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[12]  Gang Tao,et al.  An adaptive actuator failure compensation controller using output feedback , 2002, IEEE Trans. Autom. Control..

[13]  A. Ng,et al.  On the Calibration of Satellite On-Board Magnetometer , 2003, 2003 4th International Conference on Control and Automation Proceedings.

[14]  Marios M. Polycarpou,et al.  Sensor Bias Fault Isolation in a Class of Nonlinear Systems , 2003 .

[15]  Ian D. Walker,et al.  Fault identification for robot manipulators , 2005, IEEE Transactions on Robotics.

[16]  M. Saif,et al.  Robust Fault Diagnosis for a Satellite System Using a Neural Sliding Mode Observer , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[17]  Qing Wu,et al.  Robust fault diagnosis for satellite attitude systems using neural state space models , 2005, 2005 IEEE International Conference on Systems, Man and Cybernetics.

[18]  M. Saif,et al.  Neural adaptive observer based fault detection and identification for satellite attitude control systems , 2005, Proceedings of the 2005, American Control Conference, 2005..

[19]  William Holderbaum,et al.  An efficient parameterization of dynamic neural networks for nonlinear system identification , 2005, IEEE Transactions on Neural Networks.

[20]  E.S. Tehrani,et al.  Dynamic neural network-based estimator for fault diagnosis in reaction wheel actuator of satellite attitude control system , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[21]  Khashayar Khorasani,et al.  A Dynamic Neural Network-based Reaction Wheel Fault Diagnosis for Satellites , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[22]  R.V. Patel,et al.  An intelligent Fault Detection and Recovery scheme for reaction wheel actuator of satellite attitude control systems , 2006, 2006 IEEE Conference on Computer Aided Control System Design, 2006 IEEE International Conference on Control Applications, 2006 IEEE International Symposium on Intelligent Control.

[23]  Chih-Min Lin,et al.  Wavelet Adaptive Backstepping Control for a Class of Nonlinear Systems , 2006, IEEE Transactions on Neural Networks.

[24]  Heidar Ali Talebi,et al.  A stable neural network-based observer with application to flexible-joint manipulators , 2006, IEEE Transactions on Neural Networks.

[25]  Khashayar Khorasani,et al.  Neural Network-based Actuator Fault Diagnosis for Attitude Control Subsystem of an Unmanned Space Vehicle , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[26]  M. Saif,et al.  Robust fault diagnosis for a satellite large angle attitude system using an iterative neuron PID (INPID) observer , 2006, 2006 American Control Conference.

[27]  Marcin Witczak,et al.  Toward the training of feed-forward neural networks with the D-optimum input sequence , 2006, IEEE Transactions on Neural Networks.

[28]  José Luis Rojo-Álvarez,et al.  Support Vector Machines for Nonlinear Kernel ARMA System Identification , 2006, IEEE Transactions on Neural Networks.

[29]  Aydogan Savran,et al.  Multifeedback-Layer Neural Network , 2007, IEEE Transactions on Neural Networks.

[30]  Thomas Parisini,et al.  Fault Detection in Mechanical Systems With Friction Phenomena: An Online Neural Approximation Approach , 2007, IEEE Transactions on Neural Networks.

[31]  Xuemei Ren,et al.  Identification of Nonlinear Systems With Unknown Time Delay Based on Time-Delay Neural Networks , 2007, IEEE Transactions on Neural Networks.

[32]  Peter Tino,et al.  IEEE Transactions on Neural Networks , 2009 .