Neural network adaptive control of a DC drive

A simple scheme for the neural network (NN) adaptive control of the speed of a DC drive is presented. The scheme consists of an NN-based controller, a reference model, and an algorithm for changing the NN weights in order that the speed of the drive tracks that of the model. The scheme is first designed by simulation. The effect of the learning rate on the system stability is explained by means of an analytical approach. The scheme is then implemented in an experimental set-up and tested. The results show the robustness of the control system to parameter variations and disturbances in the drive.<
>