Two New Types of Zhang Neural Networks Solving Systems of Time-Varying Nonlinear Inequalities

To solve systems of time-varying nonlinear inequalities, this paper proposes two new types of Zhang neural networks. The first new type of Zhang neural network is based on the conventional Zhang 's neural-dynamics design method, and is termed a conventional Zhang neural network (CZNN). The other one is based on a novel variant of the conventional Zhang 's neural-dynamics design method, and is termed a modified Zhang neural network (MZNN). The theoretical analysis of both CZNN and MZNN is presented to show their excellent convergence performance. Compared with CZNN for solving systems of time-varying nonlinear inequalities, it is discovered that MZNN incorporates CZNN as its special case [i.e., MZNN using linear activation functions (MZNNL) reduces to CZNN exactly]. Besides, MZNN using power-sum activation functions (MZNNP) possesses superior convergence performance to CZNN. Computer-simulation results further demonstrate and substantiate the theoretical analysis and efficacy of both CZNN and MZNN for solving systems of time-varying nonlinear inequalities.

[1]  Jeen-Shing Wang,et al.  A fully automated recurrent neural network for unknown dynamic system identification and control , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[2]  Gang Feng,et al.  A Scaling Parameter Approach to Delay-Dependent State Estimation of Delayed Neural Networks , 2010, IEEE Transactions on Circuits and Systems II: Express Briefs.

[3]  David Q. Mayne,et al.  Solving nonlinear inequalities in a finite number of iterations , 1981 .

[4]  Shuzhi Sam Ge,et al.  Output Feedback NN Control for Two Classes of Discrete-Time Systems With Unknown Control Directions in a Unified Approach , 2008, IEEE Transactions on Neural Networks.

[5]  A. G. Ramm,et al.  A nonlinear inequality and applications , 2009 .

[6]  Olvi L. Mangasarian,et al.  Smoothing methods for convex inequalities and linear complementarity problems , 1995, Math. Program..

[7]  Yunong Zhang,et al.  Continuous and discrete time Zhang dynamics for time-varying 4th root finding , 2010, Numerical Algorithms.

[8]  Wen Yu,et al.  Stability Analysis of Nonlinear System Identification via Delayed Neural Networks , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.

[9]  Vimal Singh.  A stability inequality for nonlinear discrete-time systems with slope-restricted nonlinearity , 1984 .

[10]  Xiaofeng Liao,et al.  Robust Stability and Robust Periodicity of Delayed Recurrent Neural Networks With Noise Disturbance , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[11]  Xin-Ping Guan,et al.  New Exponential Stability Criteria for Neural Networks With Time-Varying Delay , 2011, IEEE Transactions on Circuits and Systems II: Express Briefs.

[12]  M. Sahba,et al.  On the solution of nonlinear inequalities in a finite number of iterations , 1985 .

[13]  Yunong Zhang,et al.  Obstacle avoidance for kinematically redundant manipulators using a dual neural network , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Shuzhi Sam Ge,et al.  Design and analysis of a general recurrent neural network model for time-varying matrix inversion , 2005, IEEE Transactions on Neural Networks.

[15]  S. M. Robinson.  Stability Theory for Systems of Inequalities, Part II: Differentiable Nonlinear Systems , 1976 .

[16]  Youshen Xia.  A new neural network for solving linear programming problems and its application , 1996, IEEE Trans. Neural Networks.

[17]  Wing-Sum Cheung.  Some new nonlinear inequalities and applications to boundary value problems , 2006 .

[18]  Binghuang Cai,et al.  From Zhang Neural Network to Newton Iteration for Matrix Inversion , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[19]  Ke Chen,et al.  Performance Analysis of Gradient Neural Network Exploited for Online Time-Varying Matrix Inversion , 2009, IEEE Transactions on Automatic Control.

[20]  Jin Bae Park,et al.  Generalized predictive control based on self-recurrent wavelet neural network for stable path tracking of mobile robots: adaptive learning rates approach , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[21]  G. Geng,et al.  Application of a neural-network-based RLS algorithm in the generalized predictive control of a nonlinear air-handling plant , 1997, IEEE Trans. Control. Syst. Technol..

[22]  Yunong Zhang,et al.  A set of nonlinear equations and inequalities arising in robotics and its online solution via a primal neural network , 2006, Neurocomputing.

[23]  J. Daniel.  Newton's method for nonlinear inequalities , 1973 .

[24]  Leon O. Chua,et al.  Pyramidal cells: a novel class of adaptive coupling cells and their applications for cellular neural networks , 1998 .

[25]  Youshen Xia,et al.  A recurrent neural network for nonlinear convex optimization subject to nonlinear inequality constraints , 2004, IEEE Trans. Circuits Syst. I Regul. Pap..

[26]  Mauro Forti,et al.  Limit Set Dichotomy and Convergence of Cooperative Piecewise Linear Neural Networks , 2011, IEEE Transactions on Circuits and Systems I: Regular Papers.

[27]  Yunong Zhang,et al.  Zhang Neural Network Versus Gradient Neural Network for Solving Time-Varying Linear Inequalities , 2011, IEEE Transactions on Neural Networks.

[28]  Suk-Jin Lee,et al.  EXISTENCE RESULTS FOR VECTOR NONLINEAR INEQUALITIES , 2003 .

[29]  Huaguang Zhang,et al.  Improved Robust Stability Criteria for Delayed Cellular Neural Networks via the LMI Approach , 2010, IEEE Transactions on Circuits and Systems II: Express Briefs.

[30]  Chih-Chin Lai,et al.  A neural network for linear matrix inequality problems , 2000, IEEE Trans. Neural Networks Learn. Syst..

[31]  Wei Bian,et al.  Subgradient-Based Neural Networks for Nonsmooth Convex Optimization Problems , 2008, IEEE Transactions on Circuits and Systems I: Regular Papers.

[32]  Jun Wang,et al.  Recurrent neural networks for solving linear inequalities and equations , 1999 .

[33]  Tadashi Shibata,et al.  A Neuron-MOS-Based VLSI Implementation of Pulse-Coupled Neural Networks for Image Feature Generation , 2010, IEEE Transactions on Circuits and Systems I: Regular Papers.

[34]  Jun Wang,et al.  A recurrent neural network for solving Sylvester equation with time-varying coefficients , 2002, IEEE Trans. Neural Networks.

[35]  Michael A. Fiddy,et al.  Regularized image reconstruction using SVD and a neural network method for matrix inversion , 1993, IEEE Trans. Signal Process..

[36]  Shuzhi Sam Ge,et al.  Adaptive Predictive Control Using Neural Network for a Class of Pure-Feedback Systems in Discrete Time , 2008, IEEE Transactions on Neural Networks.

[37]  Yunong Zhang,et al.  Zhang neural network for online solution of time-varying convex quadratic program subject to time-varying linear-equality constraints , 2009 .