An Empirical Model of a Multiphase Reactor Based on Artificial Neural Network
Year: 2009
Type: article
Abstract: An empirical model of a multiphase reactor based on artificial neural network has been developed. The multilayer feedforward network with one hidden layer has been used. The effect of the number of neurons in the hidden layer on the process parameters has also been examined. The model determines the system response to changes in the inlet variables. An optimum network architecture possessing good generalization ability has been determined in this study. The reactor model obtained from the network training process can be used in industrial practice for controlling the reactor in real time.
DOI: 10.3303/cet0917207
Authors: Barbara Zakrzewska, Zdzisław Jaworski
Institution: West Pomeranian University of Technology in Szczecin
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2591574419
