Superior robustness of power-sum activation functions in Zhang neural networks for time-varying quadratic programs perturbed with large implementation errors

A special class of recurrent neural network termed Zhang neural network (ZNN) depicted in the implicit dynamics has recently been introduced for online solution of time-varying convex quadratic programming (QP) problems. Global exponential convergence of such a ZNN model is achieved theoretically in an error-free situation. This paper investigates the performance analysis of the perturbed ZNN model using a special type of activation functions (namely, power-sum activation functions) when solving the time-varying QP problems. Robustness analysis and simulation results demonstrate the superior characteristics of using power-sum activation functions in the context of large ZNN-implementation errors, compared with the case of using linear activation functions. Furthermore, the application to inverse kinematic control of a redundant robot arm also verifies the feasibility and effectiveness of the ZNN model for time-varying QP problems solving.

[1]  Leon O. Chua,et al.  Neural networks for nonlinear programming , 1988 .

[2]  Ke Chen,et al.  Author's Personal Copy Robotics and Autonomous Systems Repetitive Motion of Redundant Robots Planned by Three Kinds of Recurrent Neural Networks and Illustrated with a Four-link Planar Manipulator's Straight-line Example , 2022 .

[3]  Ke Chen,et al.  MATLAB Simulink modeling and simulation of LVI-based primal-dual neural network for solving linear and quadratic programs , 2009, Neurocomputing.

[4]  Hyun Myung,et al.  Time-varying two-phase optimization and its application to neural-network learning , 1997, IEEE Trans. Neural Networks.

[5]  Paul T. Boggs,et al.  Sequential Quadratic Programming , 1995, Acta Numerica.

[6]  Wu Li.  Error Bounds for Piecewise Convex Quadratic Programs and Applications , 1995 .

[7]  N. Grudinin.  Reactive power optimization using successive quadratic programming method , 1998 .

[8]  Yunong Zhang,et al.  O(N 2)-Operation Approximation of Covariance Matrix Inverse in Gaussian Process Regression Based on Quasi-Newton BFGS Method , 2007, Commun. Stat. Simul. Comput..

[9]  Shigetoshi Nara,et al.  A Note on Time Delayed Effect in a Recurrent Neural Network Model , 2003, Neural Computing & Applications.

[10]  Tor Arne Johansen,et al.  Constrained nonlinear control allocation with singularity avoidance using sequential quadratic programming , 2004, IEEE Transactions on Control Systems Technology.

[11]  Ramón Alberto Carrasco,et al.  Application of a Recurrent Neural Network to Space Deversity in SDMA and CDMA Mobile Communication Systems , 2001, Neural Computing & Applications.

[12]  Walter Murray,et al.  Sequential Quadratic Programming Methods for Large-Scale Problems , 1997, Comput. Optim. Appl..

[13]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[14]  Ekkehard W. Sachs,et al.  Inexact SQP Interior Point Methods and Large Scale Optimal Control Problems , 1999, SIAM J. Control. Optim..

[15]  L. Davis,et al.  Sequential quadratic programming method for solution of electromagnetic inverse problems , 2005, IEEE Transactions on Antennas and Propagation.

[16]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[17]  Leon O. Chua,et al.  Nonlinear programming without computation , 1984 .

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

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

[20]  Jun Wang,et al.  RECURRENT NEURAL NETWORKS FOR REAL-TIME COMPUTATION OF INVERSE KINEMATICS OF REDUNDANT MANIPULATORS , 2004 .

[21]  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.

[22]  Peter Sincak,et al.  Machine Intelligence: Quo Vadis? , 2004 .

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

[24]  Pierre Apkarian,et al.  Robust control via sequential semidefinite programming , 2001, Proceedings of the 41st IEEE Conference on Decision and Control, 2002..

[25]  Yunong Zhang,et al.  Improved Zhang neural network model and its solution of time-varying generalized linear matrix equations , 2010, Expert Syst. Appl..