Title: "An Adaptive Neural Network Based On Model Prediction Control "
         

Page(s): 4 - 9
Authors: Betty Elezebeth Samuel,Dr. Latha Parthiban

Abstract

Abstract— Model Predictive Control (MPC) is a powerful model based control technique, which explicitly optimizes the overall performance of a system to be controlled. Also, it employs an explicit prediction model of the plant to optimize future plant behaviour. Artificial Neural Networks (ANNs), originally inspired by the ability of the human beings to perform many complicated tasks with ease, are used as an attractive tool to model complex relationships between inputs and outputs, and applied to various areas. More over neural networks (NNs) are effective models for identifying complex nonlinear and uncertain systems. Therefore neural network is suitable selection to identify complex nonlinear systems for MPC and design of training algorithm is an important task for neural network based model predictive control system. The primary intention of research is to design a model predictive control (MPC) using integration of Levenberg- Marquardt (LM) based back propagation (BP). Keywords — Model Prediction control, Artificial Neural Network, Levenberg Marquardt, back propagation.