A New Artificial Neural Networks Model for Industrial Processes

Artificial Neural Networks (ANNs) have become a popular tool for identification and control of nonlinear dynamical systems. This is due to the fact that ANNs are capable of learning from examples, perform non-linear mappings, and have a special capacity to approximate the dynamics of nonlinear systems in many applications. Building a suitable model of dynamical process in industry represents a challenge for systems engineer. In this paper, we propose the use of neural network for modeling the dynamics of the Tennessee Eastman (TE) chemical process reactor. Four subsystems of the reactor were considered. They are the reactor level, the reactor pressure, the reactor cooling water temperature and the reactor temperature problems. A comparison with the fuzzy models developed in [1], is also introduced