利用机器学习方法对制糖厂的生产效率进行建模

N. Lutska, L. Vlasenko, N. Zaiets, V. Lysenko
{"title":"利用机器学习方法对制糖厂的生产效率进行建模","authors":"N. Lutska, L. Vlasenko, N. Zaiets, V. Lysenko","doi":"10.1109/CSIT56902.2022.10000571","DOIUrl":null,"url":null,"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.","PeriodicalId":282561,"journal":{"name":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Modeling the Productivity of a Sugar Factory using Machine Learning Methods\",\"authors\":\"N. Lutska, L. Vlasenko, N. Zaiets, V. Lysenko\",\"doi\":\"10.1109/CSIT56902.2022.10000571\",\"DOIUrl\":null,\"url\":null,\"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.\",\"PeriodicalId\":282561,\"journal\":{\"name\":\"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)\",\"volume\":\"133 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CSIT56902.2022.10000571\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSIT56902.2022.10000571","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

今天相关的是工业企业的数字化,这是引入MES/MOM的进化延续。同时,各种目的的数学模型的构建起着重要的作用,是数字孪生发展的主要组成部分。Digital Twin为基于这些模型的企业生产流程提供了一种新的理念,旨在提高单个部门和整个企业的效率。为了提高企业的利润,必须保证工艺流程的计划生产率,其最终指标是糖的产量。考虑到企业中有大量的物质流,只有操作技术人员工作的生产流才会在工作中被挑选出来。在专家评估的基础上,为选定的流程分配了对糖生产总体性能影响的加权值。这使得建立一个数学模型来预测输入流的糖产量成为可能。该模型的结构和参数由机器学习方法确定。这是一个前馈神经网络MLP 7-23-23-1,其预测精度误差小于1%。该模型可用于对企业的工艺条件进行建模、修正和预测,从而提高糖厂的整体生产率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Modeling the Productivity of a Sugar Factory using Machine Learning Methods
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信