Loading [MathJax]/extensions/TeX/ietmacros.js
Modeling the Productivity of a Sugar Factory using Machine Learning Methods | IEEE Conference Publication | IEEE Xplore

Modeling the Productivity of a Sugar Factory using Machine Learning Methods


Abstract:

Relevant today is the digitalization of industrial enterprises, which is an evolutionary continuation of the introduction of MES/MOM. At the same time, an important role ...Show More

Abstract:

Relevant today is the digitalization of industrial enterprises, which is an evolutionary continuation of the introduction of MES/MOM. At the same time, an important role is played by the construction of mathematical models for various purposes, which are the main component of the Digital Twin development. Digital Twin provides a new philosophy for conducting enterprise production processes based on these models, which is aimed at improving the efficiency of both individual sectors and the enterprise as a whole. To increase the profit of the enterprise, it is necessary to ensure the planned productivity of technological processes, the final indicator of which is the yield of sugar. Taking into account that a significant number of material flows operate at the enterprise, only production flows with which the operator-technologist works are singled out in the work. The selected flows, based on expert assessments, were assigned weighted values of the impact on the overall performance of the sugar production. This made it possible to build a mathematical model that predicts the yield of sugar from input flows. The structure and parameters of this model are determined by machine learning methods. This is a feed-forward neural network MLP 7-23-23-1, which provides forecast accuracy with an error of less than 1%. The model can be used to model, correct, and predict the process conditions of an enterprise, which will increase the overall productivity of the sugar factory.
Date of Conference: 10-12 November 2022
Date Added to IEEE Xplore: 02 January 2023
ISBN Information:

ISSN Information:

Conference Location: Lviv, Ukraine

References

References is not available for this document.