Open AccessFractional order chaotic system control based on feedback and multiple least square support vector machines
Author(s) -
Rui Wang,
Hong Yang
Publication year - 2011
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.60.070508
Subject(s) - control theory (sociology) , nonlinear system , computer science , robustness (evolution) , support vector machine , chaotic , equilibrium point , fractional order system , compensation (psychology) , principal component analysis , cluster analysis , mathematics , artificial intelligence , fractional calculus , control (management) , physics , psychology , biochemistry , chemistry , quantum mechanics , psychoanalysis , gene
According to the stability of fractional order linear systems theory, the system is decomposed into stable linear parts and the corresponding nonlinear parts. The active controller is designed to compensate the nonlinear parts, and the fractional order chaotic system is suppressed to an equilibrium point. In order to improve the compensation ability of active controller, a multiple least square support vector machine (M-LS-SVM) regression model is presented based on feedback. The subtractive clustering is adopted to divide the input space into several sub-spaces, and sub-models are built by a LS-SVM in each sub-space. In order to minimize the severe correlation among sub-models and to improve the accuracy and the robustness of the model, the sub-models are combined by principal component regression (PCR).The experiment result shows that by using the method the compensation accuracy and the system response indices can be improved.