Prediction of hot metal temperature based on data mining

Accurately and continuously monitoring the hot metal temperature status of the blast furnace (BF) is a challenging job. To solve this problem, we propose a hot metal temperature prediction model based on the AdaBoost integrated algorithm using the real production data of the BF. We cleaned the raw d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jun Zhao, Xin Li, Song Liu, Kun Wang, Qing Lyu, Erhao Liu
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	hot metal temperature adaboost algorithm k-means clustering correlation coefficient Technology T Chemical technology TP1-1185 Chemicals: Manufacture, use, etc. TP200-248
Acceso en línea:	https://doaj.org/article/89c4372aac0a47f7b81cc2a1af27941c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:89c4372aac0a47f7b81cc2a1af27941c
record_format	dspace
spelling	oai:doaj.org-article:89c4372aac0a47f7b81cc2a1af27941c2021-12-05T14:10:50ZPrediction of hot metal temperature based on data mining2191-032410.1515/htmp-2021-0020https://doaj.org/article/89c4372aac0a47f7b81cc2a1af27941c2021-04-01T00:00:00Zhttps://doi.org/10.1515/htmp-2021-0020https://doaj.org/toc/2191-0324Accurately and continuously monitoring the hot metal temperature status of the blast furnace (BF) is a challenging job. To solve this problem, we propose a hot metal temperature prediction model based on the AdaBoost integrated algorithm using the real production data of the BF. We cleaned the raw data using the data analysis technology combined with metallurgical process theory, which mainly included data integration, outliers elimination, and missing value supplement. The redundant features were removed based on Pearson’s thermodynamic diagram analysis, and the input parameters of the model were preliminarily determined by using recursive feature elimination method. We built the hot metal temperature prediction model using the AdaBoost ensemble algorithm on a dataset with selected features as well as derived features by using K-mean clustering tags. The results show that the performance of the hot metal temperature prediction model with K-means clustering tags has been further improved, and the accurate monitoring and forecast of molten iron temperature has been achieved. The model can achieve an accuracy of more than 90% with an error of ±5°C.Jun ZhaoXin LiSong LiuKun WangQing LyuErhao LiuDe Gruyterarticlehot metal temperatureadaboost algorithmk-means clusteringcorrelation coefficientTechnologyTChemical technologyTP1-1185Chemicals: Manufacture, use, etc.TP200-248ENHigh Temperature Materials and Processes, Vol 40, Iss 1, Pp 87-98 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	hot metal temperature adaboost algorithm k-means clustering correlation coefficient Technology T Chemical technology TP1-1185 Chemicals: Manufacture, use, etc. TP200-248
spellingShingle	hot metal temperature adaboost algorithm k-means clustering correlation coefficient Technology T Chemical technology TP1-1185 Chemicals: Manufacture, use, etc. TP200-248 Jun Zhao Xin Li Song Liu Kun Wang Qing Lyu Erhao Liu Prediction of hot metal temperature based on data mining
description	Accurately and continuously monitoring the hot metal temperature status of the blast furnace (BF) is a challenging job. To solve this problem, we propose a hot metal temperature prediction model based on the AdaBoost integrated algorithm using the real production data of the BF. We cleaned the raw data using the data analysis technology combined with metallurgical process theory, which mainly included data integration, outliers elimination, and missing value supplement. The redundant features were removed based on Pearson’s thermodynamic diagram analysis, and the input parameters of the model were preliminarily determined by using recursive feature elimination method. We built the hot metal temperature prediction model using the AdaBoost ensemble algorithm on a dataset with selected features as well as derived features by using K-mean clustering tags. The results show that the performance of the hot metal temperature prediction model with K-means clustering tags has been further improved, and the accurate monitoring and forecast of molten iron temperature has been achieved. The model can achieve an accuracy of more than 90% with an error of ±5°C.
format	article
author	Jun Zhao Xin Li Song Liu Kun Wang Qing Lyu Erhao Liu
author_facet	Jun Zhao Xin Li Song Liu Kun Wang Qing Lyu Erhao Liu
author_sort	Jun Zhao
title	Prediction of hot metal temperature based on data mining
title_short	Prediction of hot metal temperature based on data mining
title_full	Prediction of hot metal temperature based on data mining
title_fullStr	Prediction of hot metal temperature based on data mining
title_full_unstemmed	Prediction of hot metal temperature based on data mining
title_sort	prediction of hot metal temperature based on data mining
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/89c4372aac0a47f7b81cc2a1af27941c
work_keys_str_mv	AT junzhao predictionofhotmetaltemperaturebasedondatamining AT xinli predictionofhotmetaltemperaturebasedondatamining AT songliu predictionofhotmetaltemperaturebasedondatamining AT kunwang predictionofhotmetaltemperaturebasedondatamining AT qinglyu predictionofhotmetaltemperaturebasedondatamining AT erhaoliu predictionofhotmetaltemperaturebasedondatamining
_version_	1718371676424503296

Prediction of hot metal temperature based on data mining

Ejemplares similares