An advanced neural network topology and learning, applied for identification and control of a DC motor

An improved parallel recurrent neural network with canonical architecture, named Recurrent Trainable Neural Network (RTNN), and a normalized error based dynamic backpropagation learning algorithm are analyzed in topics like stability, convergence and rate of convergence, and applied to a D.C. motor identification and control. The theoretical results obtained are given in theorem proof made via Lyapunov function and the unknown nonlinear dynamics of the motor together with the load are identified by the RTNN. The trained RTNN identifier is combined with a reference signal and a RTNN controllers In a direct adaptive control scheme, so In order to achieve a desired trajectory tracking of the motor position. The applicability of the theoretical study is illustrated by experimental results.