Optimally-Tuned Cascaded PID Control using Radial Basis Function Neural Network Metamodeling

The University of Tasmania
Publication Type:
Conference Proceeding
Proceedings of the 3rd International Workshop on Artificial Intelligence in Science and Technology, 2009, pp. 1 - 6
Issue Date:
Full metadata record
Dynamic systems are quite often non-linear and require a complex mathematical model. For their optimal control, it has been always a requirement to tune the controller parameters to achieve the best performance. Parameter tuning in complex systems is predominantly a time-consuming task, even with high performance computers. This paper provides an overview of metamodeling and demonstrates how it can be applied to efficiently tune the control parameters of a typically nonlinear and unstable process, the ball and beam system. Here, the metamodel is realized with a radial basis function (RBF) neural network to derive the PID parameters subject to an optimal criterion. The proposed approach is benchmarked with a commonly-used tuning technique.
Please use this identifier to cite or link to this item: