Application of Artificial Neural Networks for Process Identification and Control

During the development of intelligent systems inspired by biological neural system, in the last two decades the researchers from various scientific fields have created neural networks for solving a series of problems from pattern recognition, prediction, diagnostic, software sensor, modelling and identification, control and optimization. In this paper a review of neural network application in the field of chemical engineering with emphasis on identification and process control is given. The neural networks have been proven usefull in the applications which include complex chemical and biochemical reactions. In such a processes use of standard methods of process modelling and control structure are frequently not suitable. The ability of neural network to model dynamics of nonlinear process makes them an important tool for implementation in model-based control. Due to intensively theory development and many practical applications, there are numerous neural network structures and algorithms. In this paper neural networks are categorized under three major control schemes: model-base predictive control, inverse model-based control, and adaptive control. The major applications are summarized. It reveals prospect of using neural networks in process identification and control. The future of neural network application lies not only in their explicite use, but in cross connecting to other advanted technnologies as well. Fusion of neural networks and fuzzy logic in the form of neural-fuzzy network is one of the possibilites. Other important field is hibrid modelling and identification methods which supplement simplified mechanistic models. Software sensors and their application, especially in controlling of bioprocesses, present a very promising field.