Using Neural Network Controller to Control Chaos in an Hexagonal Governor System with a Spring

In this paper, complex dynamic behaviors of the centrifugal flywheel governor systems are studied. These systems have a rich variety of nonlinear behaviors, which are investigated here by numerically integrating the Lagrangian equations of motion. Periodic and chaotic motions can be clearly distinguished by all of the analytical tools applied here, namely bifurcation diagrams, Lyapunov exponents. The chaotic motion of the system is controlled using neural network controller. We obtain the steady periodic orbit of the system under effectively controlling. It is concluded the hyperbolic tangent function is the best candidate as the threshold function of NNC for controlling the centrifugal flywheel governor system.