Robust adaptive nonlinear observer design via multi-time scales neural network

This paper deals with the robust adaptive observer design for nonlinear dynamic systems that have an underlying multiple time-scales structure via different time-scales neural network. The Lyapunov function method is used to develop a novel stable updating law for the multi-time scales neural networks model and prove that the state error, output estimation error and the neural network weights errors are all uniformly ultimately bounded around the zero point during the entire learning process. Furthermore, passivity-based approach is used to derive the robust property of the proposed multi-time scales neural networks observer. Compared with the other nonlinear observers without considering the time scales, the proposed observer demonstrates faster convergence and more accurate properties. Two examples are presented confirming the validity of the above approach.

[1]  Huaguang Zhang,et al.  Novel Weighting-Delay-Based Stability Criteria for Recurrent Neural Networks With Time-Varying Delay , 2010, IEEE Transactions on Neural Networks.

[2]  Zhongke Shi,et al.  Direct neural control of hypersonic flight vehicles with prediction model in discrete time , 2013, Neurocomputing.

[3]  J. Reyes-Reyes,et al.  Passivation and control of partially known SISO nonlinear systemsvia dynamic neural networks , 2000 .

[4]  T. Westerlund,et al.  Remarks on "Asymptotic behavior of the extended Kalman filter as a parameter estimator for linear systems" , 1980 .

[5]  Xiaoou Li,et al.  Passivity Analysis of Dynamic Neural Networks with Different Time-scales , 2006, Neural Processing Letters.

[6]  Chenguang Yang,et al.  Global Neural Dynamic Surface Tracking Control of Strict-Feedback Systems With Application to Hypersonic Flight Vehicle , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[7]  C.-S. Liu,et al.  Adaptive neural-networks-based fault detection and diagnosis using unmeasured states , 2008 .

[8]  Alexander S. Poznyak,et al.  New Sliding-Mode Learning Law for Dynamic Neural Network Observer , 2006, IEEE Transactions on Circuits and Systems II: Express Briefs.

[9]  Bing Chen,et al.  Observer-based adaptive neural control for a class of nonlinear pure-feedback systems , 2016, Neurocomputing.

[10]  A. J. Koshkouei,et al.  Sliding mode state observation for non-linear systems , 2004 .

[11]  Paul I. Ro,et al.  Reduced-order modelling and parameter estimation for a quarter-car suspension system , 2000 .

[12]  Bin Xu,et al.  Robust adaptive neural control of flexible hypersonic flight vehicle with dead-zone input nonlinearity , 2015 .

[13]  Heidar Ali Talebi,et al.  Neural Network-Based State Estimation of Nonlinear Systems: Application to Fault Detection and Isolation , 2009 .

[14]  Zhongke Shi,et al.  Composite Neural Dynamic Surface Control of a Class of Uncertain Nonlinear Systems in Strict-Feedback Form , 2014, IEEE Transactions on Cybernetics.

[15]  Martin Corless,et al.  COMPARATIVE STUDY OF NONLINEAR STATE OBSERVATION TECHNIQUE , 1987 .

[16]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control , 2004, IEEE Transactions on Neural Networks.

[17]  J.A.R. Vargas,et al.  Robust neural adaptive observer for MIMO nonlinear systems , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

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

[19]  Xiaoou Li,et al.  Dynamic system identification via recurrent multilayer perceptron , 2002, Inf. Sci..

[20]  Josep M. Guerrero,et al.  Hybrid Three-Phase/Single-Phase Microgrid Architecture With Power Management Capabilities , 2015, IEEE Transactions on Power Electronics.

[21]  S. Hadjeri,et al.  Adaptive sliding mode observer for induction motor using two-time-scale approach , 2007 .

[22]  Frank L. Lewis,et al.  Multilayer neural-net robot controller with guaranteed tracking performance , 1996, IEEE Trans. Neural Networks.

[23]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[24]  Keith J. Burnham,et al.  On designing observers for time-delay systems with non-linear disturbances , 2002 .

[25]  Weidong Luo,et al.  Nonlinear Systems Identification and Control Via Dynamic Multitime Scales Neural Networks , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[26]  E. M. Hemerly,et al.  Neural adaptive observer for general nonlinear systems , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[27]  Hu Shousong,et al.  Fault Detection for Uncertain Nonlinear SystemBased on Unknown Input Observer , 2005 .

[28]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[29]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[30]  Zhongke Shi,et al.  Reinforcement Learning Output Feedback NN Control Using Deterministic Learning Technique , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[32]  X. Ren,et al.  Adaptive memoryless observer design for nonlinear time-delay systems , 2009, 2009 IEEE International Conference on Control and Automation.

[33]  Alexander S. Poznyak,et al.  Attractive Ellipsoids in Robust Control , 2014 .

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

[35]  Silvio Simani,et al.  Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques , 2012, Neurocomputing.

[36]  I. Chairez,et al.  Practical stability analysis for DNN observation , 2008, 2008 47th IEEE Conference on Decision and Control.

[37]  Huaguang Zhang,et al.  Global stability analysis of multitime-scale neural networks , 2011, Neural Computing and Applications.

[38]  Hassan K. Khalil,et al.  Singular perturbation methods in control : analysis and design , 1986 .

[39]  F. L. Lewis,et al.  Nonlinear observer design using dynamic recurrent neural networks , 1996, Proceedings of 35th IEEE Conference on Decision and Control.

[40]  Encarna Sosa Sánchez,et al.  Robust asymptotic neuro observer with time delay term , 2000, Proceedings of the 2000 IEEE International Symposium on Intelligent Control. Held jointly with the 8th IEEE Mediterranean Conference on Control and Automation (Cat. No.00CH37147).

[41]  Petros A. Ioannou,et al.  Robust Adaptive Control , 2012 .

[42]  Xiaoou Li,et al.  Observer-based neuro identifier , 2000 .

[43]  Masayuki Suzuki,et al.  Control of active suspension systems using the singular perturbation method , 1996 .

[44]  Yih-Guang Leu,et al.  Observer-based direct adaptive fuzzy-neural control for nonaffine nonlinear systems , 2005, IEEE Trans. Neural Networks.

[45]  Huaguang Zhang,et al.  Near-Optimal Control for Nonzero-Sum Differential Games of Continuous-Time Nonlinear Systems Using Single-Network ADP , 2013, IEEE Transactions on Cybernetics.

[46]  Xiaoou Li,et al.  Some stability properties of dynamic neural networks with different time-scales , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[47]  Yi Xiong,et al.  Sliding mode observer for nonlinear uncertain systems , 2001, IEEE Trans. Autom. Control..

[48]  Anke Meyer-Bäse,et al.  Stochastic stability analysis of competitive neural networks with different time-scales , 2013, Neurocomputing.

[49]  Robert Hecht-Nielsen,et al.  Theory of the backpropagation neural network , 1989, International 1989 Joint Conference on Neural Networks.

[50]  Frank L. Lewis,et al.  Robot Manipulator Control: Theory and Practice , 2003 .

[51]  Alexander G. Loukianov,et al.  Discrete-Time High Order Neural Control - Trained with Kaiman Filtering , 2010, Studies in Computational Intelligence.

[52]  S. Żak,et al.  Comparative study of non-linear state-observation techniques , 1987 .

[53]  Rajesh Rajamani,et al.  Vehicle dynamics and control , 2005 .

[54]  Colin Camerer.  Judgment and decision making, J. Frank Yates. Englewood Cliffs, New Jersey, Prentice-Hall inc. 1990 , 1991 .

[55]  Zhang Ji.  Global Stability Analysis of Neural Networks , 2002 .

[56]  Ming-Shyan Wang,et al.  Robust dynamic output feedback sliding-mode control of singular perturbation systems , 1995 .

[57]  Jiping Xu,et al.  Adaptive state observer for nonlinear MIMO systems with uncertain dynamics , 2010, 2010 Chinese Control and Decision Conference.

[58]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[59]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control: Identification, State Estimation and Trajectory Tracking , 2001 .

[60]  Gildas Besancon,et al.  Nonlinear observers and applications , 2007 .