A Recurrent Neural Network With Explicitly Definable Convergence Time for Solving Time-Variant Linear Matrix Equations
Author:
- 22 March 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 14 (12) , 5289-5298
Abstract
Time-variant linear matrix equations (TVLMEs) are ubiquitous in engineering. To solve TVLMEs, various zeroing neural network (ZNN) models have been developed. These ZNNs globally converge to the solution of TVLMEs either in infinity long time or in finite time. However, even the convergence time of a finite-time convergent ZNN is implicit and closely dependent on the initial condition of a problem. This may reduce its applicability to time-critical applications in practice. To overcome this problem, this paper for the first time accelerates a ZNN to fixed-time convergence using a novel activation function. The convergence time of the proposed ZNN can be antecedently defined as an explicit parameter. Theoretically, its fixed-time convergence and robustness properties are rigorously proved. Comparative numerical results substantiate the superior convergence and robustness performance of the fixed-time convergent ZNN for TVLMEs solving. Additionally, the fixed-time convergent ZNN is applied to motion planning of a redundant robotic arm.Keywords
This publication has 16 references indexed in Scilit:
- Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equationsNeural Networks, 2018
- Fixed-time synchronization of delayed memristor-based recurrent neural networksScience China Information Sciences, 2017
- The accelerated gradient based iterative algorithm for solving a class of generalized Sylvester-transpose matrix equationApplied Mathematics and Computation, 2016
- A finite-time convergent neural dynamics for online solution of time-varying linear complex matrix equationNeurocomputing, 2015
- Finite-time and fixed-time stabilization: Implicit Lyapunov function approachAutomatica, 2015
- A discontinuous recurrent neural network with predefined time convergence for solution of linear programming2014
- Finite-Time Stability and Its Application for Solving Time-Varying Sylvester Equation by Recurrent Neural NetworkNeural Processing Letters, 2014
- FPGA Implementation of the C-Mantec Neural Network Constructive AlgorithmIEEE Transactions on Industrial Informatics, 2013
- Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation FunctionNeural Processing Letters, 2012
- Nonlinear Feedback Design for Fixed-Time Stabilization of Linear Control SystemsIEEE Transactions on Automatic Control, 2011