TY - JOUR
T1 - An improved particle swarm optimization for exponential stabilization of a singular linear time-varying system
AU - Tung, Shen Lung
AU - Juang, Yau Tarng
AU - Lee, Wei Hsun
AU - Chiu, Hung Chih
N1 - Funding Information:
This work was partially supported by the National Science Council of the Republic of China under the contract NSC 98-2221-E-008-092.
PY - 2011/9/15
Y1 - 2011/9/15
N2 - This paper derives an optimization problem for exponential stabilization condition of a singular linear time-varying system governed by the second-order vector differential equations and proposes an improved particle swarm optimization (PSO) method, called the adaptive fuzzy PSO with a constriction factor (AFPSO-cf) algorithm, for solving the optimization problem of exponential stabilization. The proposed AFPSO-cf algorithm adaptively adjusts the accelerating coefficients of PSO by using the fuzzy set theory to improve global searching ability of controller parameters. Compared with the standard particle swarm optimization (SPSO), the PSO with a constriction factor (PSO-cf), the Quadratic Interpolation PSO (QIPSO), the unified PSO (UPSO), the fully informed particle swarm (FIPS) and the comprehensive learning PSO (CLPSO) algorithms, the experiment results show that the proposed method significantly performs better than those algorithms.
AB - This paper derives an optimization problem for exponential stabilization condition of a singular linear time-varying system governed by the second-order vector differential equations and proposes an improved particle swarm optimization (PSO) method, called the adaptive fuzzy PSO with a constriction factor (AFPSO-cf) algorithm, for solving the optimization problem of exponential stabilization. The proposed AFPSO-cf algorithm adaptively adjusts the accelerating coefficients of PSO by using the fuzzy set theory to improve global searching ability of controller parameters. Compared with the standard particle swarm optimization (SPSO), the PSO with a constriction factor (PSO-cf), the Quadratic Interpolation PSO (QIPSO), the unified PSO (UPSO), the fully informed particle swarm (FIPS) and the comprehensive learning PSO (CLPSO) algorithms, the experiment results show that the proposed method significantly performs better than those algorithms.
UR - http://www.scopus.com/inward/record.url?scp=79958009264&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79958009264&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2011.04.173
DO - 10.1016/j.eswa.2011.04.173
M3 - Article
AN - SCOPUS:79958009264
SN - 0957-4174
VL - 38
SP - 13425
EP - 13431
JO - Expert Systems With Applications
JF - Expert Systems With Applications
IS - 10
ER -