钢铁钒钛2025，Vol.46Issue(5)：65-74,10.DOI:10.7513/j.issn.1004-7638.2025.05.007
基于机器学习的板坯加热炉性能预测模型研究
Study on performance of Machine-Learning-Based prediction model for slab reheating furnaces
刘勇 1宁榛 2廖哲晗 2朱焱麟 2唐政 1付芹 1邓超1
作者信息
- 1. 攀钢集团攀枝花钢钒有限公司板材厂,四川攀枝花 617061
- 2. 成都先进金属材料产业技术研究院股份有限公司,四川成都 610300
- 折叠
摘要
Abstract
Based on 8 297 data samples from a 1 450 mm hot-strip mill reheating furnace in a Chinese steel plant,XGBoost and LSTM models using four sets of input variables had been developed and used to predict furnace discharge temperature,energy consumption of per ton steel,and oxidation burn rate.It was found out that the LSTM model performed well in predicting furnace discharge temperature and oxidation burn rate,with coefficients of determination(R2)exceeding 0.95.The XGBoost model was su-perior in predicting energy consumption,achieving R2 values above 0.94 and stable prediction trends.Comparative analysis indicated that LSTM was more reliable for predicting time-dependent parameters(such as discharge temperature and oxidation burn),while XGBoost provided higher accuracy for static parameters(such as energy consumption).Further investigation revealed that LSTM effectively cap-tures time-related patterns due to its gated mechanism.In contrast,XGBoost performed better on static features due to its ability to optimize feature combinations.Based on these findings,a hybrid LSTM-XGBoost model was proposed.In this combined model,LSTM deals with time-series data,and XG-Boost processes static data.Applying the combined model to furnace control can further improve pre-diction accuracy.This study provides theoretical guidance and data support for optimizing reheating fur-nace operations and enhancing resource efficiency in the steel industry.关键词
热连轧/加热炉/机器学习/加热工艺优化Key words
hot strip rolling/reheating furnace/machine learning/heating-process optimization分类
矿业与冶金引用本文复制引用
刘勇,宁榛,廖哲晗,朱焱麟,唐政,付芹,邓超..基于机器学习的板坯加热炉性能预测模型研究[J].钢铁钒钛,2025,46(5):65-74,10.
