Solving time-varying quadratic programs based on finite-time Zhang neural networks and their application to robot tracking

被引：117

作者：

Miao, Peng ^{[1
]}

Shen, Yanjun ^{[2
]}

Huang, Yuehua ^{[2
]}

Wang, Yan-Wu ^{[3
]}

机构：

[1] China Three Gorges Univ, Coll Sci, Yichang 443002, Peoples R China

[2] China Three Gorges Univ, Hubei Prov Collaborat Innovat Ctr New Energy Micr, Yichang 443002, Peoples R China

[3] Huazhong Univ Sci & Technol, Sch Automat, Wuhan 430074, Peoples R China

来源：

NEURAL COMPUTING & APPLICATIONS | 2015年 / 26卷 / 03期

基金：

美国国家科学基金会;

关键词：

Time-varying QP problems; Finite-time ZNN; Tunable activation function; Upper bound of convergent time; Robot tracking; SYLVESTER EQUATION; INVERSE; MODEL;

D O I：

10.1007/s00521-014-1744-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, finite-time Zhang neural networks (ZNNs) are designed to solve time-varying quadratic program (QP) problems and applied to robot tracking. Firstly, finite-time criteria and upper bounds of the convergent time are reviewed. Secondly, finite-time ZNNs with two tunable activation functions are proposed and applied to solve the time-varying QP problems. Finite-time convergent theorems of the proposed neural networks are presented and proved. The upper bounds of the convergent time are estimated less conservatively. The proposed neural networks also have superior robustness performance against perturbation with large implementation errors. Thirdly, feasibility and superiority of our method are shown by numerical simulations. At last, the proposed neural networks are applied to robot tracking. Simulation results also show the effectiveness of the proposed methods.

引用

页码：693 / 703

页数：11

共 31 条

[1] Learning from hint for the conservative motion of the constrained industrial redundant manipulators [J].

Assal, Samy F. M. .

NEURAL COMPUTING & APPLICATIONS, 2013, 23 (06) :1649-1660

[2] Finite-time stability of continuous autonomous systems [J].

Bhat, SP ;

Bernstein, DS .

SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2000, 38 (03) :751-766

[3]

Boggs P.T., 1995, ACTA NUMER, V4, P1, DOI DOI 10.1017/S0962492900002518

[4] Robust control via sequential semidefinite programming [J].

Fares, B ;

Noll, D ;

Apkarian, P .

SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2002, 40 (06) :1791-1820

[5] Sequential quadratic programming method for solution of electromagnetic inverse problems [J].

Hu, JL ;

Wu, ZP ;

McCann, H ;

Davis, LE ;

Xie, CG .

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2005, 53 (08) :2680-2687

[6] A New Recurrent Neural Network for Solving Convex Quadratic Programming Problems With an Application to the k-Winners-Take-All Problem [J].

Hu, Xiaolin ;

Zhang, Bo .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2009, 20 (04) :654-664

[7] Constrained nonlinear control allocation with singularity avoidance using sequential quadratic programming [J].

Johansen, TA ;

Fossen, TI ;

Berge, SP .

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2004, 12 (01) :211-216

[8] Adaptive neural controller for space robot system with an attitude controlled base [J].

Kumar, Naveen ;

Panwar, Vikas ;

Borm, Jin-Hwan ;

Chai, Jangbom ;

Yoon, Jungwon .

NEURAL COMPUTING & APPLICATIONS, 2013, 23 (7-8) :2333-2340

[9] O(N2)-operation approximation of covariance matrix inverse in Gaussian process regression based on quasi-Netwon BFGS method [J].

Leithead, W. E. ;

Zhang, Yunong .

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, 2007, 36 (02) :367-380

[10] Decentralized control of collaborative redundant manipulators with partial command coverage via locally connected recurrent neural networks [J].

Li, Shuai ;

Cui, Hongzhu ;

Li, Yangming ;

Liu, Bo ;

Lou, Yuesheng .

NEURAL COMPUTING & APPLICATIONS, 2013, 23 (3-4) :1051-1060

← 1 2 3 4 →