Far East Journal of Experimental and Theoretical Artificial Intelligence
-->
Abstract: This paper is the report of our study of using
genetic adaptive control systems for
-gain state feedback controllers (LC). In the study, the concept of
derivative-free optimization is employed to resolve the high initial gain
problem of an
-gain state feedback controller for a class of nonlinear systems. A real-value
genetic algorithm with on-line characteristics is designed to search a suitable
control gain of LC under auxiliary searching conditions based on a specific cost
function. Here, the specific cost function is designed based on the Lyapunov
stable theory. Since the controller has the
-gain control properties, the system states are bounded in an assignable region.
Hence, the stability of the initial system is ensured. Because the search space
of the genetic algorithm is defined based on the
-gain attenuation level, the system stability of any searching results is
guaranteed. The search target is to find a suitable set of parameters so that
the system can have good control performance. The simulation results indeed
demonstrate the effectiveness of the proposed approach.
Keywords and phrases: genetic
algorithm, adaptive control, high-gain,
-gain.
