ADAPTIVE NEURO-GENETIC CONTROL OF CHAOS APPLIED TO THE ATTITUDE-CONTROL PROBLEM

Conventional adaptive control techniques have, for the most part, been based on methods for linear or weakly non-linear systems. More recent ly, neural network and genetic algorithm controllers have started to b e applied to complex, non-linear dynamic systems. The control of chaot ic dynamic systems poses a series of especially challenging problems. In this paper, and adaptive control architecture using neural networks and genetic algorithms is applied to a complex, highly nonlinear, cha otic dynamic system: the adaptive attitude control problem (for a sate llite), in the presence of large, external forces (which left to thems elves led the system into a chaotic motion). In contrast to the OGY me thod, which uses small control adjustments to stabilize a chaotic syst em in an otherwise unstable but natural periodic orbit of the system, the neuro-genetic controller may use large control adjustments and pro ves capable of effectively attaining any specified system state, with no a priori knowledge of the dynamics, even in the presence of signifi cant noise.