| 基于粒子群优化的时变系统辨识 |
| |
| 引用本文： | 柯晶,李威武,钱积新.基于粒子群优化的时变系统辨识[J].系统工程与电子技术,2003,25(10):1256-1259. |
| |
| 作者姓名： | 柯晶 李威武 钱积新 |
| |
| 作者单位： | 1. 山东大学控制科学与工程学院,山东,济南,250061
2. 浙江大学系统工程研究所,浙江,杭州,310027 |
| |
| 摘 要： | 提出了一种基于粒子群优化的时变系统辨识方法。其基本思想是将时变系统的辨识问题转化为非线性连续函数的在线优化问题 ,然后利用粒子群优化获得系统参数的最优估计。仿真结果显示 ,该方法对于时变参数具有很强的跟踪能力 ,与采用遗传算法的系统辨识方法相比 ,有实现简单、运算量小等特点。
|
| 关 键 词： | 系统辨识 参数估计 优化 |
| 文章编号： | 1001-506X(2003)10-1256-04 |
| 修稿时间： | 2002年9月11日 |
Identification of Time-Varying Systems Based on Particle Swarm Optimization |
| |
| KE Jing,LI Wei-wu,QIAN Ji-xin.Identification of Time-Varying Systems Based on Particle Swarm Optimization[J].System Engineering and Electronics,2003,25(10):1256-1259. |
| |
| Authors: | KE Jing LI Wei-wu QIAN Ji-xin |
| |
| Institution: | KE Jing~1,LI Wei-wu~2,QIAN Ji-xin~2 |
| |
| Abstract: | A method based on particle swarm optimization for identification of time-varying systems is proposed. The basic idea is that the identification of time-varying systems is converted to an on-line optimization of continuous nonlinear functions, and then the particle swarm optimization is utilized to find an optimal estimation of the system parameters. Simulation results show that the proposed method has a good tracking ability to the variations of the parameter. Compared with the system identification using the genetic algorithm, the proposed method is easy to be implemented and requires less computational resources. |
| |
| Keywords: | System identification Parameter estimation Optimization |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
