International Journal of Engineering and Technology

In the domain of industry process control, the model identification and predictive control of nonlinear systems are always difficult problems .The main aim of this paper is to establish a reliable model for nonlinear process. In many applications, lack of process knowledge and/or a suitable dynamic simulator precludes the derivation of fundamental model. This necessitates the development of empirical nonlinear model from dynamic plant data. This process is known as ‘Nonlinear System Identification’. Artificial neural networks are the most popular frame-work for empirical model development .The model is implemented by training a Multi-Layer Perceptron Artificial Neural network (MLP-ANN) with inputoutput experimental data. Satisfactory agreement between identified and experimental data is found and results shown that the neural model successfully predicts the evolution of the product composition. Trained data available from nonlinear system using Model Predictive Control (MPC) algorithm. The Simulation result illustrates the validity and feasibility of the MPC algorithm.