Genetic Algorithm and Elman Network Used For Tuning The Parameters Of The PID Neural Controller Based Model Reference

Abstract

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