Abstract
In this paper, a recurrent neural network (RNN) based robust tracking controller is designed for a class of multiple-input-multiple-output discrete time nonlinear systems. The RNN is used in the closed-loop system to estimate online unknown nonlinear system function. A multivariable robust adaptive gradient-descent training algorithm is developed to train RNN. The weight convergence and system stability are proven in the sense of Lyapunov function. Simulation results are presented for a two-link robot tracking control problem.
Similar content being viewed by others
References
Zerkaoui S, Druaux F, Leclercq E, Lefebvre D (2009) Stable adaptive control with recurrent neural networks for square MIMO non-linear systems. Eng Appl Artif Intell 22:702–717
Song Q, Hu WJ, Yin L, Soh YC (2002) Robust adaptive dead zone technology for fault-tolerant control of robot manipulators using neural networks. J Intell Robot Syst 33:113–137
Jagannathan S (2001) Control of a class of nonlinear discrete-time systems using multilayer neural networks. IEEE Trans Neural Netw 12:1113–1120
Song Q, Xiao J, Soh YC (1999) Robust backpropagation training algorithm for multilayered neural tracking controller. IEEE Trans Neural Netw 10:1133–1141
Spall JC, Cristion JA (1997) A neural network controller for systems with unmodeled dynamics with applications to wastewater treatment. IEEE Trans Syst Man Cybern B 27:369–375
Fu-Chuang C, Khalil HK (1995) Adaptive control of a class of nonlinear discrete-time systems using neural networks. IEEE Trans Automat Control 40:791–801
Park YM, Choi MS, Lee KY (1996) An optimal tracking neuro-controller for nonlinear dynamic systems. IEEE Trans Neural Netw 7:1099–1110
Narendra K, Parthasarathy K (1989) Adaptive identification and control of dynamical systems using neural networks. In: Proceedings of the 28th IEEE conference on decision and control, pp 1737–1738
Haykin S, Li L (1995) Nonlinear adaptive prediction of nonstationary signals. IEEE Trans Signal Process 43:526–535
Baltersee J, Chambers JA (1998) Nonlinear adaptive prediction of speech with a pipelined recurrent neural network. IEEE Trans Signal Process 46:2207–2216
Stavrakoudis DG, Theocharis JB (2007) Pipelined recurrent fuzzy neural networks for nonlinear adaptive speech prediction. IEEE Trans Syst Man Cybern B 37:1305–1320
Zhao HQ, Zhang JS (2009) A novel adaptive nonlinear filter-based pipelined feedforward second-order Volterra architecture. IEEE Trans Signal Process 57:237–246
Chang PR, Hu JT (1997) Optimal nonlinear adaptive prediction and modeling of MPEG video in ATM networks using pipelined recurrent neural networks. IEEE J Select Areas Commun 15:1087–1100
Chen YS, Chang CJ, Hsieh YL (2006) A channel effect prediction-based power control scheme using PRNN/ERLS for uplinks in DS-CDMA cellular mobile systems. IEEE Trans Wireless Commun 5:23–27
Mandic DP, Chambers JA (1999) Toward an optimal PRNN based nonlinear prediction. IEEE Trans Neural Netw 10:1435–1442
Mandic DP, Chambers JA (2000) On the choice of parameters of the cost function in nested modular RNNs. IEEE Trans Neural Netw 11:315–322
Zhao HQ, Zhang JS (2010) Pipelined Chebyshev functional link artificial recurrent neural network for nonlinear adaptive filter. IEEE Trans Syst Man Cybern B Cybern 40:162–172
Werbos PJ (1988) Generalization of backpropagation with application to a recurrent gas market model. Neural Netw 1:339–356
Rumelhart D, Hinton G, Williams R (1986) Learning internal representations by error backpropagation. Parallel Distribut Process 1:318–362
Williams RJ, Zipser D (1995) Gradient-based learning algorithms for recurrent networks and their computational complexity. Backpropagat Theory Architect Appl 2:433–501
Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280
Liu ZZ, Elhanany I (2008) A fast and scalable recurrent neural network based on stochastic meta descent. IEEE Trans Neural Netw 19:1652–1658
Song Q, Wu Y, Soh YC (2008) Robust adaptive gradient-descent training algorithm for recurrent neural networks in discrete time domain. IEEE Trans Neural Netw 19:1841–1853
Adetona O, Garcia E, Keel L (2000) A new method for the control of discrete nonlinear dynamic systems using neural networks. IEEE Trans Neural Netw 11:102–112
Jagannathan S, Lewis FL (1996) Robust implicit self-tuning regulator: convergence and stability. Automatica 32:1629–1644
Jagannathan S, Lewis FL (1996) Multilayer discrete-time neural-net controller with guaranteed performance. IEEE Trans Neural Netw 7:107–130
Trentin E (2001) Networks with trainable amplitude of activation functions. Neural Netw 14:471–493
Goh SL, Mandic DP (2003) Recurrent neural networks with trainable amplitude of activation functions. Neural Netw 16:1095–1100
Talebi HA, Khorasani K, Tafazoli S (2009) A recurrent neural-network-based sensor and actuator fault detection and isolation for nonlinear systems with application to the satellite’s attitude control subsystem. IEEE Trans Neural Netw 20:45–60
Yu W (2006) Multiple recurrent neural networks for stable adaptive control. Neurocomputing 70:430–444
Tian L, Collins C (2004) A dynamic recurrent neural network-based controller for a rigid-flexible manipulator system. Mechatronics 14:471–490
Abdelhameed M, Tolbah F (2002) A recurrent neural network-based sequential controller for manufacturing automated systems. Mechatronics 12:617–633
Lin FJ, Wai RJ, Hong CM (2000) Recurrent neural network control for LCC-resonant ultrasonic motordrive. IEEE Trans Ultrason Ferroelectr Frequency Control 47:737–749
Venugopal KP, Pandya AS, Sudhakar R (1994) A recurrent neural network controller and learning algorithm for the on-line learning control of autonomous underwater vehicles. Neural Netw 7:833–846
Haykin S (1999) Neural networks: a comprehensive foundation. Printice Hall, New Jersey
Lewis F, Abdalla C, Dawson D (1993) Control of robot manipulators. Macmillan, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xu, Z., Song, Q. & Wang, D. Recurrent neural tracking control based on multivariable robust adaptive gradient-descent training algorithm. Neural Comput & Applic 21, 1745–1755 (2012). https://doi.org/10.1007/s00521-011-0618-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0618-2