用神经网络来解释金属加热炉的跨区域相互作用

IF 0.8 4区材料科学 Q4 METALLURGY & METALLURGICAL ENGINEERING

Metallurgist Pub Date : 2025-06-30 DOI:10.1007/s11015-025-01945-0

Andrey V. Fomin, Nikita V. Savostin

{"title":"用神经网络来解释金属加热炉的跨区域相互作用","authors":"Andrey V. Fomin, Nikita V. Savostin","doi":"10.1007/s11015-025-01945-0","DOIUrl":null,"url":null,"abstract":"<div><p>The study focuses on the development of a functional model describing cross-zone interactions within a reheating furnace used prior to rolling. Various methods for the identification of cross-zone interaction model, ranging from regression analysis to neural networks were described. A neural network model that reflects the state of the furnace zones while accounting for their mutual interactions was obtained. The overall regression coefficient (across all zones) was approximately 0.82, with individual zone coefficients ranging from 0.65 to 0.85. Cross-zone interactions were modeled, and the results were validated by expert evaluation.</p></div>","PeriodicalId":702,"journal":{"name":"Metallurgist","volume":"69 2","pages":"314 - 321"},"PeriodicalIF":0.8000,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using neural networks to account for cross-zone interactions in metal reheating furnaces\",\"authors\":\"Andrey V. Fomin, Nikita V. Savostin\",\"doi\":\"10.1007/s11015-025-01945-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The study focuses on the development of a functional model describing cross-zone interactions within a reheating furnace used prior to rolling. Various methods for the identification of cross-zone interaction model, ranging from regression analysis to neural networks were described. A neural network model that reflects the state of the furnace zones while accounting for their mutual interactions was obtained. The overall regression coefficient (across all zones) was approximately 0.82, with individual zone coefficients ranging from 0.65 to 0.85. Cross-zone interactions were modeled, and the results were validated by expert evaluation.</p></div>\",\"PeriodicalId\":702,\"journal\":{\"name\":\"Metallurgist\",\"volume\":\"69 2\",\"pages\":\"314 - 321\"},\"PeriodicalIF\":0.8000,\"publicationDate\":\"2025-06-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Metallurgist\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://link.springer.com/article/10.1007/s11015-025-01945-0\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Metallurgist","FirstCategoryId":"88","ListUrlMain":"https://link.springer.com/article/10.1007/s11015-025-01945-0","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}

引用次数: 0

摘要

该研究的重点是一个功能模型的发展，该模型描述了在轧制前使用的加热炉内的跨区域相互作用。描述了从回归分析到神经网络等多种识别跨区域相互作用模型的方法。建立了反映炉区状态的神经网络模型，同时考虑了炉区之间的相互作用。总体回归系数（所有区域）约为0.82，个别区域系数在0.65至0.85之间。建立了跨区域相互作用模型，并通过专家评价对结果进行了验证。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Using neural networks to account for cross-zone interactions in metal reheating furnaces

查看原文本刊更多论文

Using neural networks to account for cross-zone interactions in metal reheating furnaces

The study focuses on the development of a functional model describing cross-zone interactions within a reheating furnace used prior to rolling. Various methods for the identification of cross-zone interaction model, ranging from regression analysis to neural networks were described. A neural network model that reflects the state of the furnace zones while accounting for their mutual interactions was obtained. The overall regression coefficient (across all zones) was approximately 0.82, with individual zone coefficients ranging from 0.65 to 0.85. Cross-zone interactions were modeled, and the results were validated by expert evaluation.

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

Metallurgist 工程技术-冶金工程

CiteScore

1.50

自引率

44.40%

发文量

151

审稿时长

4-8 weeks

期刊介绍： Metallurgist is the leading Russian journal in metallurgy. Publication started in 1956. Basic topics covered include: State of the art and development of enterprises in ferrous and nonferrous metallurgy and mining; Metallurgy of ferrous, nonferrous, rare, and precious metals; Metallurgical equipment; Automation and control; Protection of labor; Protection of the environment; Resources and energy saving; Quality and certification; History of metallurgy; Inventions (patents).