Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations

In order to solve general time-varying linear matrix equations (LMEs) more efficiently, this paper proposes two nonlinear recurrent neural networks based on two nonlinear activation functions. According to Lyapunov theory, such two nonlinear recurrent neural networks are proved to be convergent within finite-time. Besides, by solving differential equation, the upper bounds of the finite convergence time are determined analytically. Compared with existing recurrent neural networks, the proposed two nonlinear recurrent neural networks have a better convergence property (i.e., the upper bound is lower), and thus the accurate solutions of general time-varying LMEs can be obtained with less time. At last, various different situations have been considered by setting different coefficient matrices of general time-varying LMEs and a great variety of computer simulations (including the application to robot manipulators) have been conducted to validate the better finite-time convergence of the proposed two nonlinear recurrent neural networks.

[1]  Lin Xiao,et al.  A finite-time convergent neural dynamics for online solution of time-varying linear complex matrix equation , 2015, Neurocomputing.

[2]  Yunong Zhang,et al.  Two New Types of Zhang Neural Networks Solving Systems of Time-Varying Nonlinear Inequalities , 2012, IEEE Transactions on Circuits and Systems I: Regular Papers.

[3]  Lin Xiao,et al.  Accelerating a recurrent neural network to finite-time convergence using a new design formula and its application to time-varying matrix square root , 2017, J. Frankl. Inst..

[4]  Xi-Yan Hu,et al.  An iteration method for the symmetric solutions and the optimal approximation solution of the matrix equation AXB=C , 2005, Appl. Math. Comput..

[5]  Frank L. Lewis,et al.  On constructing Lyapunov functions for multi-agent systems , 2015, Autom..

[6]  Chenfu Yi,et al.  Improved gradient-based neural networks for online solution of Lyapunov matrix equation , 2011, Inf. Process. Lett..

[7]  Chenfu Yi,et al.  Comparison on neural solvers for the Lyapunov matrix equation with stationary & nonstationary coefficients , 2013 .

[8]  Masoud Hajarian,et al.  Solving the general Sylvester discrete-time periodic matrix equations via the gradient based iterative method , 2016, Appl. Math. Lett..

[9]  Bing Chen,et al.  Neural Network-Based Adaptive Dynamic Surface Control for Permanent Magnet Synchronous Motors , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[10]  Ke Chen,et al.  Simulink Modeling and Comparison of Zhang Neural Networks and Gradient Neural Networks for Time-Varying Lyapunov Equation Solving , 2008, 2008 Fourth International Conference on Natural Computation.

[11]  Shuai Li,et al.  Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function , 2012, Neural Processing Letters.

[12]  Yunong Zhang,et al.  A New Performance Index for the Repetitive Motion of Mobile Manipulators , 2014, IEEE Transactions on Cybernetics.

[13]  Lin Xiao,et al.  Finite-time solution to nonlinear equation using recurrent neural dynamics with a specially-constructed activation function , 2015, Neurocomputing.

[14]  Jinde Cao,et al.  Matrix measure based dissipativity analysis for inertial delayed uncertain neural networks , 2016, Neural Networks.

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

[16]  Feng Ding,et al.  Gradient Based Iterative Algorithms for Solving a Class of Matrix Equations , 2005, IEEE Trans. Autom. Control..

[17]  Zhenjiang Zhao,et al.  Global exponential stability of complex-valued neural networks with both time-varying delays and impulsive effects , 2016, Neural Networks.

[18]  Shaocheng Tong,et al.  Neural Network Control-Based Adaptive Learning Design for Nonlinear Systems With Full-State Constraints , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Guang-Ren Duan,et al.  A parametric periodic Lyapunov equation with application in semi-global stabilization of discrete-time periodic systems subject to actuator saturation , 2010, Proceedings of the 2010 American Control Conference.

[20]  Valeria Simoncini,et al.  Computational Methods for Linear Matrix Equations , 2016, SIAM Rev..

[21]  Peter Benner,et al.  On optimality of approximate low rank solutions of large-scale matrix equations , 2014, Syst. Control. Lett..

[22]  Lin Xiao,et al.  A convergence-accelerated Zhang neural network and its solution application to Lyapunov equation , 2016, Neurocomputing.

[23]  Long Jin,et al.  Discrete-Time Zhang Neural Network for Online Time-Varying Nonlinear Optimization With Application to Manipulator Motion Generation , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Wei Xing Zheng,et al.  Discrete-Time Neural Network for Fast Solving Large Linear $L_{1}$ Estimation Problems and its Application to Image Restoration , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[25]  Sitian Qin,et al.  A neurodynamic approach to convex optimization problems with general constraint , 2016, Neural Networks.

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

[27]  Yuanqing Li,et al.  Neural-Dynamic-Method-Based Dual-Arm CMG Scheme With Time-Varying Constraints Applied to Humanoid Robots , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[28]  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.

[29]  Yangming Li,et al.  A class of finite-time dual neural networks for solving quadratic programming problems and its k-winners-take-all application , 2013, Neural Networks.

[30]  Ai-Guo Wu,et al.  Current-estimation-based iterative algorithms for solving periodic Lyapunov matrix equations , 2016 .

[31]  Feng Ding,et al.  Brief Paper - Gradient-based iterative algorithm for a class of the coupled matrix equations related to control systems , 2014 .

[32]  Alireza Hosseini.  A non-penalty recurrent neural network for solving a class of constrained optimization problems , 2016, Neural Networks.

[33]  Xiao Peng,et al.  Global synchronization in finite time for fractional-order neural networks with discontinuous activations and time delays , 2017, Neural Networks.

[34]  Long Jin,et al.  G2-Type SRMPC Scheme for Synchronous Manipulation of Two Redundant Robot Arms , 2015, IEEE Transactions on Cybernetics.

[35]  Long Jin,et al.  Taylor $O(h^{3})$ Discretization of ZNN Models for Dynamic Equality-Constrained Quadratic Programming With Application to Manipulators , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[36]  Lin Xiao.  A finite-time recurrent neural network for solving online time-varying Sylvester matrix equation based on a new evolution formula , 2017 .