NEURAL NETWORK CONTROLLER CHARACTERISTICS WITH REGARD TO ADAPTIVE-CONTROL

The paper aims at clarifying the NN controller characteristics by comparison with the adaptive control theory. At first, this paper clarifies the classification of the NN controller architecture and the dynamic NN structure. Next, comparison between the NN controller and the adaptive controller clarifies that the framework of a linear two-layer NN type controller is the same as that of the adaptive control and the nonlinear three-layer NN (PDP type) is a nonlinear extension of the adaptive control. The paper also deals with the stability characteristics of the NN control system. Finally, NN controller experiments are demonstrated using a force control servomechanism. Experimental results suggest that the nonlinear sigmoid function of the NN can compensate for the nonlinear plant effect.