Development of a prototype of an intelligent system for predicting the quality of dairy manufacture

The technological process of the churning process in continuous butter manufacture were considered. The qualitative indicator of the water content of butter was modeled on the basis of a set of industrial data using an artificial neural network (ANN). The prototype of an intelligent system for predi...

Full description

Saved in:

Bibliographic Details
Published in:	2022 IEEE 11th International Conference on Intelligent Systems (IS) pp. 1 - 6
Main Authors:	Smitiukh, Yaroslav, Samoilenko, Yuliia, Kostiuk, Yuliia, Kryvoruchko, Olena, Stepashkina, Kateryna
Format:	Conference Proceeding
Language:	English
Published:	IEEE 12-10-2022
Subjects:	an intelligent system artificial neural network Artificial neural networks control system Dairy products information support Predictive models Process control Productivity Prototypes Simulation technological process
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The technological process of the churning process in continuous butter manufacture were considered. The qualitative indicator of the water content of butter was modeled on the basis of a set of industrial data using an artificial neural network (ANN). The prototype of an intelligent system for predicting of the water content of butter allows to increase the information support of the operator-technologist. The proposed model predicts the water content of butter with an error of less than 2%. The input variables of the forecast model prototype are cream fat content, cream ripening temperature, cream supply temperature, frequency of revolutions of the stirrer of the whipping device, and consumption of the normalizing component. Further research is aimed at the development of a decision support information system for dairy manufacture and should be integrated into the subsystem of automated control of the technological process to ensure proper functioning in real time.
ISSN:	2767-9802
DOI:	10.1109/IS57118.2022.10019699