Parameter estimation and modeling of nonlinear systems based on using particle swarm optimization algorithm
| Autor: | Jun-Ping Cheng, 鄭俊平 |
|---|---|
| Rok vydání: | 2014 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 102 This thesis uses the particle swarm optimization (PSO) to solve the problem of parameter estimation and modeling of nonlinear systems. The proposed algorithm is based on the velocity and the position updating formulas to achieve the system optimization. The algorithm initially consists of a large number of particles which forms an initial population, and it is necessary to record the global best particle and the individual best particle in the population. In this thesis, the PSO algorithm firstly is applied to the parameter estimation of a nonlinear Genesio-Tesi chaotic system. To verify the robustness of the proposed method, various initial population cases are examined under some measurement noise conditions. Simulation results show that the PSO is a simple and effective method for the parameter estimation problem of the nonlinear chaotic system. Moreover, the proposed method is then applied to the system modeling of the synchronous buck converter. Three different kinds of fitness functions are considered, including the integral of absolute error (IAE), the integral of squared error (ISE), and the integral of absolute error multiplied by the time (ITAE). The design purpose is to force the model output to approximate the actual output by minimizing the above three fitness functions. It is clear from the simulation results that the proposed method is rather satisfied on the system modeling of the synchronous buck converter. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|