NEURAL GENERALIZED PREDICTIVE CONTROL

Abstract

A Model Predictive Control (MPC) which relies on the predictive Control using a multilayer feed forward neural network as the plants linear model is presented here. If we use Newton-Raphson as the optimization algorithm, the number of iterations required for convergence is considerably reduced from other techniques. This thesis presents a thorough derivation of the Generalized Predictive Control and Neural Generalized Predictive Control with Newton- Raphson as cost function minimization algorithm. Taking three separate systems, performances of the system has been tested. Simulation results illustrate the effect of neural network on Generalized Predictive Control. The performance evaluation of this three system configurations has been given in terms of ISE and IAE.