A robust training algorithm of discrete-time MIMO RNN and application in fault tolerant control of robotic system

In this paper, a novel robust training algorithm of multi-input multi-output recurrent neural network and its application in the fault tolerant control of a robotic system are investigated. The proposed scheme optimizes the gradient type training on basis of three new adaptive parameters, namely, dead-zone learning rate, hybrid learning rate, and normalization factor. The adaptive dead-zone learning rate is employed to improve the steady state response. The normalization factor is used to maximize the gradient depth in the training, so as to improve the transient response. The hybrid learning rate switches the training between the back-propagation and the real-time recurrent learning mode, such that the training is robust stable. The weight convergence and L2 stability of the algorithm are proved via Lyapunov function and the Cluett’s law, respectively. Based upon the theoretical results, we carry out simulation studies of a two-link robot arm position tracking control system. A computed torque controller is designed to provide a specified closed-loop performance in a fault-free condition, and then the RNN compensator and the robust training algorithm are employed to recover the performance in case that fault occurs. Comparisons are given to demonstrate the advantages of the control method and the proposed training algorithm.

[1]  Sheng Liu,et al.  A Normalized Adaptive Training of Recurrent Neural Networks With Augmented Error Gradient , 2008, IEEE Trans. Neural Networks.

[2]  Zhihong Man,et al.  An RBF neural network-based adaptive control for SISO linearisable nonlinear systems , 2005, Neural Computing & Applications.

[3]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction , 2001 .

[4]  Qing Song,et al.  Robust Adaptive Dead Zone Technology for Fault-Tolerant Control of Robot Manipulators Using Neural Networks , 2002, J. Intell. Robotic Syst..

[5]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[6]  Qing Song,et al.  Robust adaptive fault accommodation for a robot system using a radial basis function neural network , 2001 .

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

[8]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[9]  XuLei Yang,et al.  Robust Recurrent Neural Network Control of Biped Robot , 2007, J. Intell. Robotic Syst..

[10]  Jiann-Ming Wu,et al.  Multilayer Potts Perceptrons With Levenberg–Marquardt Learning , 2008, IEEE Transactions on Neural Networks.

[11]  Danilo P. Mandic,et al.  Recurrent Neural Networks for Prediction: Learning Algorithms, Architectures and Stability , 2001 .

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

[13]  Mogens Blanke.  Fault-tolerant Control Systems , 1999 .

[14]  Danilo P. Mandic,et al.  A normalised real time recurrent learning algorithm , 2000, Signal Process..

[15]  Yeng Chai Soh,et al.  Robust Adaptive Gradient-Descent Training Algorithm for Recurrent Neural Networks in Discrete Time Domain , 2008, IEEE Transactions on Neural Networks.

[16]  O. Nelles.  Nonlinear System Identification , 2001 .

[17]  Mogens Blanke,et al.  Fault-tolerant control systems — A holistic view , 1997 .

[18]  Frank L. Lewis,et al.  Neural net robot controller with guaranteed tracking performance , 1993, Proceedings of 8th IEEE International Symposium on Intelligent Control.

[19]  Q. Song,et al.  Robust neural network controller for variable airflow volume system , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[20]  Chih-Min Lin,et al.  Robust Fault-Tolerant Control for a Biped Robot Using a Recurrent Cerebellar Model Articulation Controller , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[21]  Zhi Liu,et al.  Fuzzy neural network quadratic stabilization output feedback control for biped robots via H/sub /spl infin// approach. , 2003, IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society.

[22]  V. R. Cluett,et al.  Robustness Analysis of Discrete-Time Adaptive Control Systems Using Input-Output Stability Theory: a , 1988 .

[23]  Frank L. Lewis,et al.  Control of Robot Manipulators , 1993 .

[24]  Qing Song,et al.  Robust backpropagation training algorithm for multilayered neural tracking controller , 1999, IEEE Trans. Neural Networks.

[25]  Jian Yang,et al.  An architecture-adaptive neural network online control system , 2007, Neural Computing and Applications.