A Variable-Gain Finite-Time Convergent Recurrent Neural Network for Time-Variant Quadratic Programming With Unknown Noises Endured

A variable-gain finite-time convergent and noise-enduring zeroing neural network (VGFTNE-ZNN) is for the first time proposed for time-variant convex quadratic programming (QP). Differing from the existing finite-time convergent ZNNs with constant or variable design gains (i.e., CGFT-ZNN and VGFT-ZNN) that have limited noise-handling capabilities, the proposed VGFTNE-ZNN can endure additive noises by dynamically adjusting its design gains in finite time. Design gains of the unpolluted VGFTNE-ZNN are allowed to be constant when the QP problem is solved, whereas the design gain of the existing unpolluted VGFT-ZNN unrealistically increases to infinity when time evolves to infinity. Unlike existing polluted ZNNs with known noises involved, more practical unknown noises are successfully handled by the VGFTNE-ZNN. The finite-time convergence and noise-endurance properties of the VGFTNE-ZNN are mathematically proved based on the Lyapunov theory. Numerical verifications are comparatively performed with the superiorities of the VGFTNE-ZNN substantiated as compared with the existing CGFT-ZNN and VGFT-ZNN.

[1]  Liping Yin,et al.  Finite-Time Reentry Attitude Control Based on Adaptive Multivariable Disturbance Compensation , 2015, IEEE Transactions on Industrial Electronics.

[2]  P. T. Thach,et al.  Optimization on Low Rank Nonconvex Structures , 1996 .

[3]  Andrey Polyakov,et al.  Finite-time and fixed-time stabilization: Implicit Lyapunov function approach , 2015, Autom..

[4]  Zhang Yi,et al.  Convergence Analysis of Recurrent Neural Networks , 2003, Network Theory and Applications.

[5]  Zhijun Zhang,et al.  Varying-Parameter RNN Activated by Finite-Time Functions for Solving Joint-Drift Problems of Redundant Robot Manipulators , 2018, IEEE Transactions on Industrial Informatics.

[6]  Yunong Zhang,et al.  Time-Varying Quadratic Programming by Zhang Neural Network Equipped with a Time-Varying Design Parameter γ(t) , 2011, ISNN.

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

[8]  Ya-Xiang Yuan,et al.  Optimization Theory and Methods: Nonlinear Programming , 2010 .

[9]  Shuai Li,et al.  Solving Time-Varying System of Nonlinear Equations by Finite-Time Recurrent Neural Networks With Application to Motion Tracking of Robot Manipulators , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  Xiaolin Hu,et al.  A New Recurrent Neural Network for Solving Convex Quadratic Programming Problems With an Application to the $k$-Winners-Take-All Problem , 2009, IEEE Transactions on Neural Networks.

[11]  Nguyen V. Thoai,et al.  Solution Methods for General Quadratic Programming Problem with Continuous and Binary Variables: Overview , 2013, Advanced Computational Methods for Knowledge Engineering.

[12]  Sitian Qin,et al.  A recurrent neural network with finite-time convergence for convex quadratic bilevel programming problems , 2017, Neural Computing and Applications.

[13]  Alireza Nazemi,et al.  A Gradient-Based Neural Network Method for Solving Strictly Convex Quadratic Programming Problems , 2014, Cognitive Computation.

[14]  Salah Laghrouche,et al.  Adaptive-Gain Second Order Sliding Mode Observer Design for Switching Power Converters , 2013, ArXiv.

[15]  Yan-Wu Wang,et al.  Solving time-varying quadratic programs based on finite-time Zhang neural networks and their application to robot tracking , 2014, Neural Computing and Applications.

[16]  Gene H. Golub,et al.  Numerical solution of saddle point problems , 2005, Acta Numerica.

[17]  Shuai Li,et al.  Design and Analysis of FTZNN Applied to the Real-Time Solution of a Nonstationary Lyapunov Equation and Tracking Control of a Wheeled Mobile Manipulator , 2018, IEEE Transactions on Industrial Informatics.

[18]  H. Tuy.  Convex analysis and global optimization , 1998 .

[19]  Andrey Polyakov,et al.  Nonlinear Feedback Design for Fixed-Time Stabilization of Linear Control Systems , 2012, IEEE Transactions on Automatic Control.

[20]  Yunong Zhang,et al.  Zeroing Dynamics, Gradient Dynamics, and Newton Iterations , 2015 .

[21]  Jonas Schweiger.  Exploiting structure in non-convex quadratic optimization and gas network planning under uncertainty , 2017 .

[22]  Shuai Li,et al.  A New Varying-Parameter Convergent-Differential Neural-Network for Solving Time-Varying Convex QP Problem Constrained by Linear-Equality , 2018, IEEE Transactions on Automatic Control.

[23]  MengChu Zhou,et al.  Modified Primal-Dual Neural Networks for Motion Control of Redundant Manipulators With Dynamic Rejection of Harmonic Noises , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[24]  Shuai Li,et al.  Zeroing Neural Dynamics for Control Design: Comprehensive Analysis on Stability, Robustness, and Convergence Speed , 2019, IEEE Transactions on Industrial Informatics.

[25]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[26]  Xuyang Lou,et al.  A novel neural network for solving convex quadratic programming problems subject to equality and inequality constraints , 2016, Neurocomputing.

[27]  Long Jin,et al.  Robot Manipulator Redundancy Resolution , 2017 .

[28]  Weibing Li,et al.  A Recurrent Neural Network With Explicitly Definable Convergence Time for Solving Time-Variant Linear Matrix Equations , 2018, IEEE Transactions on Industrial Informatics.

[29]  Alireza Nazemi,et al.  A Capable Neural Network Framework for Solving Degenerate Quadratic Optimization Problems with an Application in Image Fusion , 2018, Neural Processing Letters.

[30]  Zdenek Dostl.  Optimal Quadratic Programming Algorithms: With Applications to Variational Inequalities , 2009 .

[31]  Long Jin,et al.  A Velocity-Level Bi-Criteria Optimization Scheme for Coordinated Path Tracking of Dual Robot Manipulators Using Recurrent Neural Network , 2017, Front. Neurorobot..

[32]  Jian Yang,et al.  A new recurrent neural network with noise-tolerance and finite-time convergence for dynamic quadratic minimization , 2018, Neurocomputing.