A hybrid evolutionary algorithm for recurrent neural network control of a three-dimensional tower crane

被引：66

作者：

Duong, Sam Chau ^{[2
]}

Uezato, Eiho ^{[1
]}

Kinjo, Hiroshi ^{[1
]}

Yamamoto, Tetsuhiko ^{[3
]}

机构：

[1] Univ Ryukyus, Fac Engn, Nishihara, Okinawa 9030213, Japan

[2] Univ Ryukyus, Grad Sch Engn & Sci, Nishihara, Okinawa 9030213, Japan

[3] Tokushima Coll Technol, Tokushima, Japan

来源：

AUTOMATION IN CONSTRUCTION | 2012年 / 23卷

关键词：

Hybrid evolutionary algorithm; Recurrent neural network; Tower crane; Underactuated system; Nonlinear system control; PARTICLE SWARM OPTIMIZATION; GENETIC ALGORITHM; STABILITY;

D O I：

10.1016/j.autcon.2011.12.005

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

This paper is concerned with the control of an underactuated three-dimensional tower crane system using a recurrent neural network (RNN) which is evolved by an evolutionary algorithm. In order to improve the performance in evolving the RNN, a hybrid evolutionary algorithm (HEA) which utilizes the operators of a constricted particle swarm optimization (PSO) and a binary-coded genetic algorithm (GA) is proposed. Simulation results show that the proposed HEA has superior performance in a comparison with the canonical algorithms and that the control system works effectively. (C) 2011 Elsevier B.V. All rights reserved.

引用

页码：55 / 63

页数：9

共 31 条

[1] Dynamics and control of cranes: A review [J].

Abdel-Rahman, EM ;

Nayfeh, AH ;

Masoud, ZN .

JOURNAL OF VIBRATION AND CONTROL, 2003, 9 (07) :863-908

[2]

Angeline P. J., 1998, Evolutionary Programming VII. 7th International Conference, EP98. Proceedings, P601, DOI 10.1007/BFb0040811

[3] AN EVOLUTIONARY ALGORITHM THAT CONSTRUCTS RECURRENT NEURAL NETWORKS [J].

ANGELINE, PJ ;

SAUNDERS, GM ;

POLLACK, JB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (01) :54-65

[4]

[Anonymous], LNCIS

[5]

Blajer W., 2006, Journal of Theoretical and Applied Mechanics, V44, P929

[6] Improved DAE formulation for inverse dynamics simulation of cranes [J].

Blajer, Wojciech ;

Kolodziejczyk, Krzysztof .

MULTIBODY SYSTEM DYNAMICS, 2011, 25 (02) :131-143

[7] A real-coded genetic algorithm for training recurrent neural networks [J].

Blanco, A ;

Delgado, M ;

Pegalajar, MC .

NEURAL NETWORKS, 2001, 14 (01) :93-105

[8] The particle swarm - Explosion, stability, and convergence in a multidimensional complex space [J].

Clerc, M ;

Kennedy, J .

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2002, 6 (01) :58-73

[9] Neural networks based control of mobile robots: Development and experimental validation [J].

Corradini, ML ;

Ippoliti, G ;

Longhi, S .

JOURNAL OF ROBOTIC SYSTEMS, 2003, 20 (10) :587-600

[10] Evolutionary algorithms in control systems engineering: a survey [J].

Fleming, PJ ;

Purshouse, RC .

CONTROL ENGINEERING PRACTICE, 2002, 10 (11) :1223-1241

← 1 2 3 4 →