Application of Artificial Neural Networks in Chemical Process Control
Haonan Wang *
East China University of Science and Technology, Shanghai 200237, China.
Yijia Chen
East China University of Science and Technology, Shanghai 200237, China.
*Author to whom correspondence should be addressed.
Abstract
An important data-driven model is the artificial neural network. Artificial neural networks have been widely used in many domains of chemical processes due to its robustness, fault tolerance, self-adaptive capability, and self-learning ability. For the chemical process with nonlinearity and strong coupling, artificial neural networks can model and control the process well and make up for the lack of traditional PID control technology. As a result, ANN has emerged as a significant positive trend for chemical process control. In this paper, the principle, development history, and common structure of artificial neural networks are first outlined. Then the role of artificial neural networks in chemical process control is introduced in three aspects: improved PID control, improved model predictive control, and for hybrid models. The important effect of artificial neural networks in chemical process control is reflected by comparison. Finally, it is proposed that chemical process control can be more developed by applying more deep learning algorithms and developing multiple neural networks and hybrid models in chemical process control.
Keywords: Artificial neural network, process control, chemical process, model predictive control, hybrid model