Diagonal recurrent neural network based identification of nonlinear dynamical systems with Lyapunov stability based adaptive learning rates

Abstract This paper proposes a diagonal recurrent neural network (DRNN) based identification model for approximating the unknown dynamics of the nonlinear plants. The proposed model offers deeper memory and a simpler structure. Thereafter, we have developed a dynamic back-propagation learning algorithm for tuning the parameters of DRNN. Further, to guarantee the faster convergence and stability of the overall system, dynamic (adaptive) learning rates are developed in the sense of Lyapunov stability method. The proposed scheme is also compared with multi-layer feed forward neural network (MLFFNN) and radial basis function network (RBFN) based identification models. Numerical experiments reveal that DRNN has performed much better in approximating the dynamics of the plant and have also shown more robustness toward system uncertainties.

[1]  Jie Yao,et al.  Nonlinear System Identification using Genetic Algorithm Based Recurrent Neural Networks , 2006, 2006 Canadian Conference on Electrical and Computer Engineering.

[2]  Wen Yu,et al.  Dead-zone Kalman filter algorithm for recurrent neural networks , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[3]  R. Garrido,et al.  A fuzzy neural recurrent multi-model for systems identification and control , 2001, 2001 European Control Conference (ECC).

[4]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[5]  Feng Ding,et al.  Identification of Hammerstein nonlinear ARMAX systems , 2005, Autom..

[6]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[7]  A. Isidori.  Nonlinear Control Systems , 1985 .

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

[9]  Wei Wu,et al.  Convergence of gradient method for a fully recurrent neural network , 2010, Soft Comput..

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

[11]  Junfei Qiao,et al.  Nonlinear system modeling using a self-organizing recurrent radial basis function neural network , 2017, Appl. Soft Comput..

[12]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[13]  Ahmad Banakar,et al.  Local recurrent sigmoidal-wavelet neurons in feed-forward neural network for forecasting of dynamic systems: Theory , 2012, Appl. Soft Comput..

[14]  Okyay Kaynak,et al.  A comparative study of neural network structures in identification of nonlinear systems , 1999 .

[15]  Laxmidhar Behera,et al.  Intelligent Systems and Control Principles and Applications , 2010 .

[16]  Jiamei Deng,et al.  Dynamic neural networks with hybrid structures for nonlinear system identification , 2013, Eng. Appl. Artif. Intell..

[17]  Hamid Reza Karimi,et al.  Reliable Output Feedback Control of Discrete-Time Fuzzy Affine Systems With Actuator Faults , 2017, IEEE Transactions on Circuits and Systems I: Regular Papers.

[18]  Smriti Srivastava,et al.  Online modeling and adaptive control of robotic manipulators using Gaussian radial basis function networks , 2016, Neural Computing and Applications.

[19]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[20]  P. S. Sastry,et al.  Memory neuron networks for identification and control of dynamical systems , 1994, IEEE Trans. Neural Networks.

[21]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[22]  M. Schetzen.  The Volterra and Wiener Theories of Nonlinear Systems , 1980 .

[23]  Alireza Roudbari,et al.  Intelligent modeling and identification of aircraft nonlinear flight , 2014 .

[24]  John J. Hopfield,et al.  Connected-digit speaker-dependent speech recognition using a neural network with time-delayed connections , 1991, IEEE Trans. Signal Process..

[25]  Ramazan Coban.  A context layered locally recurrent neural network for dynamic system identification , 2013, Eng. Appl. Artif. Intell..

[26]  Yi Cao,et al.  Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation , 2008 .

[27]  Andrej Dobnikar,et al.  On-line identification and reconstruction of finite automata with generalized recurrent neural networks , 2003, Neural Networks.

[28]  Wang Sanxiu,et al.  Adaptive Friction Compensation of Robot Manipulator , 2011 .

[29]  Guoping Liu,et al.  On-line identification of nonlinear systems using volterra polynomial basis function neural networks , 1997, 1997 European Control Conference (ECC).

[30]  Francisco Sandoval Hernández,et al.  Identification of noisy dynamical systems with parameter estimation based on Hopfield neural networks , 2013, Neurocomputing.

[31]  Stephen A. Billings,et al.  International Journal of Control , 2004 .

[32]  Hamid Reza Karimi,et al.  Improved Stability and Stabilization Results for Stochastic Synchronization of Continuous-Time Semi-Markovian Jump Neural Networks With Time-Varying Delay , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[33]  A. Unnikrishnan,et al.  Particle filter based neural network modeling of nonlinear systems for state space estimation , 2009, 2009 Chinese Control and Decision Conference.

[34]  Sheng Chen,et al.  Identification of non-linear rational systems using a prediction-error estimation algorithm , 1989 .

[35]  Tsu-Tian Lee,et al.  The Chebyshev-polynomials-based unified model neural networks for function approximation , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[36]  T. Martin McGinnity,et al.  Predicting a Chaotic Time Series using Fuzzy Neural network , 1998, Inf. Sci..

[37]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.