基于数学分析和邓氏相关的COREX工艺铁水中Si、S含量BP神经网络预测

IF 0.9 4区材料科学 Q3 METALLURGY & METALLURGICAL ENGINEERING

Metallurgical Research & Technology Pub Date : 2021-01-01 DOI:10.1051/metal/2021073

Heng Zhou, Yifan Hu, Bingjie Wen, Shengli Wu, M. Kou, Yinsheng Luo

{"title":"基于数学分析和邓氏相关的COREX工艺铁水中Si、S含量BP神经网络预测","authors":"Heng Zhou, Yifan Hu, Bingjie Wen, Shengli Wu, M. Kou, Yinsheng Luo","doi":"10.1051/metal/2021073","DOIUrl":null,"url":null,"abstract":"In COREX operation, the Si and S contents in hot metal are relatively high and easy-fluctuating, which is one of the problems affecting the practical operation. Accurate predictions of Si and S contents can provide theoretical references for stabilizing the fluctuations and decreasing the contents of Si and S in hot metal. Therefore, the present work established the prediction model of Si and S contents in hot metal in COREX based on BP neural network. The results show that the root-mean-square errors between the predicted value and actual value for Si and S are 0.098 and 0.0037, respectively. They are 0.070 and 0.0040 when the time-sequence lapse method is adopted, which turns out to be better. Therefore, the model is accurate and reliable to predict the Si and S contents in hot metal in COREX.","PeriodicalId":18527,"journal":{"name":"Metallurgical Research & Technology","volume":"206 1","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"BP neural network prediction for Si and S contents in hot metal of COREX process based on mathematical analysis and Deng’s correlation\",\"authors\":\"Heng Zhou, Yifan Hu, Bingjie Wen, Shengli Wu, M. Kou, Yinsheng Luo\",\"doi\":\"10.1051/metal/2021073\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In COREX operation, the Si and S contents in hot metal are relatively high and easy-fluctuating, which is one of the problems affecting the practical operation. Accurate predictions of Si and S contents can provide theoretical references for stabilizing the fluctuations and decreasing the contents of Si and S in hot metal. Therefore, the present work established the prediction model of Si and S contents in hot metal in COREX based on BP neural network. The results show that the root-mean-square errors between the predicted value and actual value for Si and S are 0.098 and 0.0037, respectively. They are 0.070 and 0.0040 when the time-sequence lapse method is adopted, which turns out to be better. Therefore, the model is accurate and reliable to predict the Si and S contents in hot metal in COREX.\",\"PeriodicalId\":18527,\"journal\":{\"name\":\"Metallurgical Research & Technology\",\"volume\":\"206 1\",\"pages\":\"\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Metallurgical Research & Technology\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1051/metal/2021073\",\"RegionNum\":4,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Metallurgical Research & Technology","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1051/metal/2021073","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}

引用次数: 4

摘要

在COREX操作中，铁水中Si、S含量较高且易波动，是影响实际操作的问题之一。准确的Si和S含量预测可以为稳定金属热中Si和S含量的波动和降低含量提供理论参考。因此，本文建立了基于BP神经网络的COREX铁水中Si、S含量预测模型。结果表明，Si和S的预测值与实际值的均方根误差分别为0.098和0.0037。采用时序递进法时分别为0.070和0.0040，效果较好。因此，该模型预测COREX铁水中Si、S含量准确可靠。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

BP neural network prediction for Si and S contents in hot metal of COREX process based on mathematical analysis and Deng’s correlation

In COREX operation, the Si and S contents in hot metal are relatively high and easy-fluctuating, which is one of the problems affecting the practical operation. Accurate predictions of Si and S contents can provide theoretical references for stabilizing the fluctuations and decreasing the contents of Si and S in hot metal. Therefore, the present work established the prediction model of Si and S contents in hot metal in COREX based on BP neural network. The results show that the root-mean-square errors between the predicted value and actual value for Si and S are 0.098 and 0.0037, respectively. They are 0.070 and 0.0040 when the time-sequence lapse method is adopted, which turns out to be better. Therefore, the model is accurate and reliable to predict the Si and S contents in hot metal in COREX.

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

Metallurgical Research & Technology METALLURGY & METALLURGICAL ENGINEERING-

CiteScore

1.70

自引率

9.10%

发文量

审稿时长

4.4 months

期刊介绍： Metallurgical Research and Technology (MRT) is a peer-reviewed bi-monthly journal publishing original high-quality research papers in areas ranging from process metallurgy to metal product properties and applications of ferrous and non-ferrous metals and alloys, including light-metals. It covers also the materials involved in the metal processing as ores, refractories and slags. The journal is listed in the citation index Web of Science and has an Impact Factor. It is highly concerned by the technological innovation as a support of the metallurgical industry at a time when it has to tackle severe challenges like energy, raw materials, sustainability, environment... Strengthening and enhancing the dialogue between science and industry is at the heart of the scope of MRT. This is why it welcomes manuscripts focusing on industrial practice, as well as basic metallurgical knowledge or review articles.