Application of a recurrent wavelet fuzzy-neural network in the positioning control of a magnetic-bearing mechanism

被引：19

作者：

Chen, Syuan-Yi ^{[1
]}

Hung, Ying-Chih ^{[2
]}

Hung, Yi-Hsuan ^{[3
]}

Wu, Chien-Hsun ^{[4
]}

机构：

[1] Natl Taiwan Normal Univ, Dept Elect Engn, Taipei, Taiwan

[2] TECO Elect & Machinery Co Ltd, Ind Prod & Syst Automat Grp, Taipei, Taiwan

[3] Natl Taiwan Normal Univ, Dept Ind Educ, Taipei, Taiwan

[4] Natl Formosa Univ, Dept Vehicle Engn, Yunlin, Taiwan

来源：

COMPUTERS & ELECTRICAL ENGINEERING | 2016年 / 54卷

关键词：

Fuzzy Neural Network (FNN); Magnetic Bearing (MB); Particle Swarm Optimization (PSO); Positioning control; PARTICLE SWARM OPTIMIZATION;

D O I：

10.1016/j.compeleceng.2015.11.022

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A new recurrent wavelet fuzzy neural network (RWFNN) with adaptive learning rates is proposed to control the rotor position on the axial direction of a thrust magnetic bearing (TMB) mechanism in this study. First, the dynamic analysis of the TMB with differential driving mode (DDM) is derived. Because the dynamic characteristics and system parameters of the TMB mechanism are high nonlinear and time-varying, the RWFNN, which integrates wavelet transforms with fuzzy rules, is proposed to achieve precise positioning control of the TMB. For the designed RWFNN controller, the online learning algorithm is derived using back-propagation method. Moreover, since the improper selection of learning rates for the RWFNN will deteriorate the control performance, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates of the RWFNN on-line. Numerical simulations show the validity of TMB system using the proposed RWFNN controller with IPSO under the occurrence of uncertainties. (C) 2015 Elsevier Ltd. All rights reserved.

引用

页码：147 / 158

页数：12

共 28 条

[1] System identification and control using adaptive particle swarm optimization [J].

Alfi, Alireza ;

Modares, Hamidreza .

APPLIED MATHEMATICAL MODELLING, 2011, 35 (03) :1210-1221

[2] Using PSO in a spatial domain based image hiding scheme with distortion tolerance [J].

Bedi, Punam ;

Bansal, Roli ;

Sehgal, Priti .

COMPUTERS & ELECTRICAL ENGINEERING, 2013, 39 (02) :640-654

[3] Decentralized PID neural network control for five degree-of-freedom active magnetic bearing [J].

Chen, Syuan-Yi ;

Lin, Faa-Jeng .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2013, 26 (03) :962-973

[4] 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

[5] Linear Output Feedback Control of a Three-Pole Magnetic Bearing [J].

Darbandi, S. Mahdi ;

Behzad, Mehdi ;

Salarieh, Hassan ;

Mehdigholi, Hamid .

IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2014, 19 (04) :1323-1330

[6] Fuzzy Wavelet Neural Network With an Accelerated Hybrid Learning Algorithm [J].

Davanipoor, Mehrnoosh ;

Zekri, Maryam ;

Sheikholeslam, Farid .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2012, 20 (03) :463-470

[7] Basic Characteristics of an Active Thrust Magnetic Bearing With a Cylindrical Rotor Core [J].

Hijikata, Kimio ;

Kobayashi, Shunsuke ;

Takemoto, Masatsugu ;

Tanaka, Yasuhiro ;

Chiba, Akira ;

Fukao, Tadashi .

IEEE TRANSACTIONS ON MAGNETICS, 2008, 44 (11) :4167-4170

[8] Fuzzy wavelet networks for function learning [J].

Ho, DWC ;

Zhang, PA ;

Xu, JH .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2001, 9 (01) :200-211

[9] Nonlinear control of a magnetic bearing system [J].

Hung, JY ;

Albritton, NG ;

Xia, F .

MECHATRONICS, 2003, 13 (06) :621-637

[10]

Kennedy J, 1995, 1995 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS PROCEEDINGS, VOLS 1-6, P1942, DOI 10.1109/icnn.1995.488968

← 1 2 3 →