New 5-Step Discrete-Time Zeroing Neuronet for Time-Dependent Matrix Square Root Finding

In this paper, for the purpose of finding square root of a time-dependent matrix, a new discrete-time zeroing neuronet (DTZN) is proposed. Firstly, the problem of square root finding of time-dependent matrix is formulated. Then, an explicit continuous-time zeroing neuronet (CTZN) is derived from the problem formulation equation via vectorization technique. Furthermore, based on Taylor expansion, we present a 5-Step Zhang time-discretization (ZTD) formula. The ZTD is used to approximate the 1st-order derivative of the object, of which the truncational error is proportional to the cube of the sampling period. Finally, the 5-Step DTZN for solving the square root of a time-dependent matrix is acquired by using the presented 5- Step ZTD formula to discretize the CTZN. Theoretical analyses shown stable and convergent performance of the proposed 5- Step DTZN for solving the square root of a time-dependent matrix. Computer experiments results present the stability and convergence of the obtained DTZN for solving square root of time-dependent matrix with the maximum steady-state residual errors proportional to the fourth power of sampling period. By comparison with the DTZNs using Euler formula and the previous 5-Step discretization formula, the proposed 5-Step DTZN has an advantage in residual error. In addition, the influences of step size and sampling period are illustrated by computer experiments results.

[1]  Yunong Zhang,et al.  Superior robustness of power-sum activation functions in Zhang neural networks for time-varying quadratic programs perturbed with large implementation errors , 2011, Neural Computing and Applications.

[2]  Yu Guo,et al.  Adaptive neural network predictive control for nonlinear pure feedback systems with input delay , 2012 .

[3]  Charles R. Johnson,et al.  Uniqueness of matrix square roots and an application , 2001 .

[4]  Dongsheng Guo,et al.  Novel Discrete-Time Zhang Neural Network for Time-Varying Matrix Inversion , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[5]  Ke Chen,et al.  Robustness analysis of a hybrid of recursive neural dynamics for online matrix inversion , 2016, Appl. Math. Comput..

[6]  Long Jin,et al.  Discrete-time Zhang neural network of O(τ3) pattern for time-varying matrix pseudoinversion with application to manipulator motion generation , 2014, Neurocomputing.

[7]  Nicholas J. Higham,et al.  Functions of matrices - theory and computation , 2008 .

[8]  E. Denman,et al.  The matrix sign function and computations in systems , 1976 .

[9]  Long Jin,et al.  Taylor-type 1-step-ahead numerical differentiation rule for first-order derivative approximation and ZNN discretization , 2015, J. Comput. Appl. Math..

[10]  Nicholas J. Higham,et al.  Stable iterations for the matrix square root , 1997, Numerical Algorithms.

[11]  Desmond J. Higham,et al.  Numerical Methods for Ordinary Differential Equations - Initial Value Problems , 2010, Springer undergraduate mathematics series.

[12]  Yunong Zhang,et al.  Zhang Neural Networks and Neural-Dynamic Method , 2011 .

[13]  Lin Xiao.  A finite-time convergent Zhang neural network and its application to real-time matrix square root finding , 2017, Neural Computing and Applications.

[14]  Joe Brewer,et al.  Kronecker products and matrix calculus in system theory , 1978 .

[15]  Dongsheng Guo,et al.  Zhang neural network, Getz-Marsden dynamic system, and discrete-time algorithms for time-varying matrix inversion with application to robots' kinematic control , 2012, Neurocomputing.

[16]  B. Iannazzo,et al.  A note on computing the matrix square root , 2003 .

[17]  Dongsheng Guo,et al.  Zhang neural network and its application to Newton iteration for matrix square root estimation , 2010, Neural Computing and Applications.

[18]  Long Jin,et al.  Superior performance of using hyperbolic sine activation functions in ZNN illustrated via time-varying matrix square roots finding , 2012, Comput. Sci. Inf. Syst..

[19]  Zhigang Zeng,et al.  Multistability of periodic delayed recurrent neural network with memristors , 2012, Neural Computing and Applications.

[20]  Shuai Li,et al.  Predictive Suboptimal Consensus of Multiagent Systems With Nonlinear Dynamics , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[21]  Dongsheng Guo,et al.  Different Zhang functions leading to different ZNN models illustrated via time-varying matrix square roots finding , 2013, Expert Syst. Appl..

[22]  Yunong Zhang,et al.  Proposing and Validation of a New Four-Point Finite-Difference Formula With Manipulator Application , 2018, IEEE Transactions on Industrial Informatics.

[23]  BEATRICE MEINI,et al.  The Matrix Square Root from a New Functional Perspective: Theoretical Results and Computational Issues , 2005, SIAM J. Matrix Anal. Appl..