A neural network-based self-tuning PID controller is presented. The scheme of
the controller is based on using a modified Elman recurrent neural network as a selftuner
for (PID) controller. The proposed method has the advantage of not necessarily
using a combined structure of identification and decision, common in a standard selftuning
controller, because it uses a genetic algorithm based model reference. The paper
explains the algorithm for a general case, and then presents a specific application on
non-linear dynamical plant.