基于混合pso_sqp算法同时实现多变量的结构和参数辨识_靳其兵.pdf

DOI ：10.13195/j.cd.2011.09.96.jinqb.005 26 9 2011 9 Vol. 26 No. 9 Control and Decision Sep. 2011 : 1001-0920 (2011) 09-1373-04 PSO-SQP , , , (100029) : . . ; PSO-SQP . , PSO PSO . , , , . : : TP273 : A Hybrid PSO-SQP for simultaneous identification of structure and parameters in a multivariate system JIN Qi-bing, ZHANG Jian, QUAN Ling, CAO Li-ting (Institute of AutomationBeijing University of Chemical Technology Beijing 100029 China Correspondent: ZHANG Jian E-mail zh20181@163.com) Abstract: This paper presents a novel and efficient method to realize both structure and parameter identification in a multivariable system with hybrid particle swarm optimization(PSO) algorithm and the sequential quadratic programming(SQP) algorithm. The conbination of classic mathematical models constitute a system model, so the problem of system structure identification is transformed into a problem of combinatorial optimization. Then by using hybrid PSO algorithm and the SQP algorithm, both structure and parameter identification of the system are realized at the same time. In order to further illustrate the effectiveness of the algorithm, the proposed method is compared with the standard PSO algorithm and the dynamical inertia weight of PSO algorithm. The simulation results show that the proposed hybrid algorithm is reasonable, effective, and has high precision and practicability. Key words: structural identification parameter identification combination optimization hybrid particle swarm optimization sequential quadratic programming 1