System identification using artificial neural network

System identification is one of the important aspects that needed to be considered before the controller design. The main objective of system identification is to know the model of the system. It is essential to understand the process before handling it. Then we can go for controller design which is apt for the system. A number of methods are existing for system identification. In this paper we propose a method to identify the system model. The proposed method involves use of back propagation neural network to predict the output of the system for a given input from the knowledge of past inputs & outputs. The effectiveness of the model identification is tested using experimental data from pressure process station, level process station, and conical tank process.