UM  > 工商管理學院  > 會計及資訊管理學系
APPROACHES TO MODEL AND CONTROL NONLINEAR SYSTEMS BY RBF NEURAL NETWORKS
XIFAN YAO1; ZHAOTONG LIAN1,2; DONGYUAN GE1; YI HE1
2011
Source PublicationInternational journal of innovative computing, information & control
ISSN1349-4198
Volume7Issue:2Pages:941-954
Abstract

Many systems in reality exhibit nonlinear characteristics and in most cases they cannot be treated satisfactorily using linearized approaches over the full operating range. In this paper, an approximate modeling approach is introduced to overcome the mismatch between the linear/linearized model and the real nonlinear plant by treating the nonlinear system as a linear uncertain system that consists of a linear part and an uncertain part, for which a radial basis function neural network is employed to approximate, and a nonlinear control scheme is proposed using a linear feedback PD (proportional-derivative) controller to work concurrently with a nonlinear radical basis function neural network controller (RBFNNC). The PD controller, designed for the linear part, is used to improve the transient response while maintaining the stability of the system, and the RBFNNC, designed from fuzzy if-then rules with functional equivalence to a fuzzy inference system, is employed to compensate for the system nonlinearity/uncertainty and reduce the steady state error. The proposed modeling approach or control scheme can incorporate prior knowledge in its framework and provide a more transparent insight than the neural black-box approach. The simulation results reveal that the proposed modeling and control scheme for nonlinear systems is effective.

KeywordNonlinear System Uncertain System Modeling Control Neural Network Radical Basis Function Approximation Linearization
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000287278100034
PublisherICIC INT, TOKAI UNIV, 9-1-1, TOROKU, KUMAMOTO, 862-8652, JAPAN
Fulltext Access
Citation statistics
Cited Times [WOS]:7   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF ACCOUNTING AND INFORMATION MANAGEMENT
Corresponding AuthorXIFAN YAO; ZHAOTONG LIAN
Affiliation1.South China University of Technology
2.University of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
XIFAN YAO,ZHAOTONG LIAN,DONGYUAN GE,et al. APPROACHES TO MODEL AND CONTROL NONLINEAR SYSTEMS BY RBF NEURAL NETWORKS[J]. International journal of innovative computing, information & control,2011,7(2):941-954.
APA XIFAN YAO,ZHAOTONG LIAN,DONGYUAN GE,&YI HE.(2011).APPROACHES TO MODEL AND CONTROL NONLINEAR SYSTEMS BY RBF NEURAL NETWORKS.International journal of innovative computing, information & control,7(2),941-954.
MLA XIFAN YAO,et al."APPROACHES TO MODEL AND CONTROL NONLINEAR SYSTEMS BY RBF NEURAL NETWORKS".International journal of innovative computing, information & control 7.2(2011):941-954.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[XIFAN YAO]'s Articles
[ZHAOTONG LIAN]'s Articles
[DONGYUAN GE]'s Articles
Baidu academic
Similar articles in Baidu academic
[XIFAN YAO]'s Articles
[ZHAOTONG LIAN]'s Articles
[DONGYUAN GE]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[XIFAN YAO]'s Articles
[ZHAOTONG LIAN]'s Articles
[DONGYUAN GE]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.