Optimization of pid controllers for a flexible robot manipulator using metamodeling approach

Abstract

Offline optimization of controller parameters for complex robotic system can be time consuming, even with high performance computers. This project demonstrates how Metamodeling techniques can be utilized to tune the controller parameters for a robotic system quickly. The system used in this study is the flexible robot manipulator which is a high order system and intrinsically complex flexible structures. The Radial Basis Function Neural Network metamodel used was able to give a good approximation to the optimum controller parameters in this case.