الفهرس Only 14 pages are availabe for public view
 |  | from | 121 |  |  |
| | | from | 121 | | |
Abstract
Swarm intelligence has proven its superiority as an evolutionary computational algorithm in solving real life application problems. Arti{uFB01}cial Bee Colony (ABC) is one of the most recent stochastic optimization algorithm based on the swarm intelligent behavior of honey bee swarm. The stochastic searching characteristic of the ABC leads to some limitations such as the impact of initial population, speed of convergence and limitation in large scaled optimization problems. This thesis proposed a novel real parameter searching methodology for ABC algorithm to overcome those limitations. The methodology is based on the relationship between ABC variants and the nature of its candidate solutions. The experimental results show that the proposed algorithm yield better performance when compared to the classic approaches such as the genetic algorithms (GAs) and the particle swarm optimization (PSO) in tuning optimal PID controllers for a real parameter system such as the robotic arm manipulator. Robotic systems have a complex non-linear dynamics and coupling relations which make accurate and robust control dif{uFB01}culties. The proposed optimization tuning approaches are able to {uFB01}nd an optimal control law without any need to derivatives and nonlinear control knowledge