Particle swarm optimisers for the designing of parametric adjustment laws in discrete-time adaptive systems

A large variety of linear/nonlinear adaptive systems in continuous/discrete time can be represented by using error models, which facilitates their analysis. In addition, a solution found for a particular error model constitutes an universal strategy which can be applied to any system represented through that error model. In this paper, we present a novel methodology based on particle swarm optimisers for online parametric adjustment in discrete-time adaptive systems represented by type 1, 2, and 3 error models, which provides stability properties and high performance compared with traditional techniques. Successful applications in combined and direct model reference adaptive control via detailed simulations are provided.