基于e-FCNN的电弧炉终点温度预报
Prediction of end-point temperature in electric arc furnace based on e-FCNN
陆泓彬 1朱红春 1姜周华 2李花兵 2杨策1
作者信息
- 1. 东北大学冶金学院,辽宁沈阳 110819
- 2. 东北大学冶金学院,辽宁沈阳 110819;东北大学轧制技术及连轧自动化国家重点实验室,辽宁沈阳 110819
- 折叠
摘要
发展电弧炉炼钢短流程是实现钢铁工业绿色发展的重要战略途经,电弧炉炼钢的终点控制决定了出钢质量和冶炼效率,尤其是终点温度控制.建立电弧炉终点温度预测模型,提前预测终点温度,有助于及时调整冶炼工艺,实现快速、高效的出钢操作.电弧炉终点温度预测模型主要分为机理模型和数据驱动模型,数据驱动模型是目前的主要研究方向,但现有的数据驱动模型建模过程依赖大量历史数据,难以适用于在小样本数据条件下实现终点温度的准确预报.对此,紧密结合冶金机理,以人工智能算法为核心,建立了高适应性的电弧炉终点温度预报模型.通过冶金机理和皮尔逊数据相关性分析得到了模型的输入参数.以FCNN算法为基础,引入提前停止策略,提出了e-FCNN算法,防止了FCNN算法的过拟合现象,并基于e-FCNN算法建立了电弧炉终点温度预报模型.仿真结果表明,终点温度预报误差在±5 ℃以内,e-FCNN模型的命中率可以达到93.33％.另外,在小样本历史数据条件下,使用超参数随机网格搜索,建立了CART、RF、ε-SVR和v-SVR终点温度预报模型,结果表明,基于e-FCNN终点温度预报模型的精度明显优于其他机器学习模型.使用e-FCNN模型连续跟踪实际生产的30炉次,预报误差为±6 ℃时,命中率达到了96.7％,可以有效指导生产.未来,进一步提升机理和数据驱动的结合程度是电弧炉终点温度预报模型的发展方向.
Abstract
The development of the EAF steelmaking short process is an important strategic way to realize the green development of the iron and steel industry.The end-point control of EAF steelmaking determines the quality of tap-ping and smelting efficiency,especially the end-point temperature control.The establishment of the prediction model to achieve the EAF end-point temperature prediction in advance helps to adjust the smelting process in time and real-ize the fast and efficient tapping operation.The EAF end-point temperature prediction model is mainly divided into the mechanism model and the data-driven model.Data-driven modeling is the main research direction at present,but the modeling process usually relies on a large amount of historical data,and it is difficult to achieve accurate end-point temperature prediction under small sample data conditions.Therefore,tightly combined with the metallurgical mechanism,with artificial intelligence algorithms as the core,established a highly adaptive EAF end-point tempera-ture prediction model.The input parameters of the model were obtained by metallurgical mechanism and Pearson da-ta correlation analysis.Based on the FCNN algorithm,the early stopping strategy was introduced,the e-FCNN al-gorithm was proposed to prevent the overfitting phenomenon of the FCNN algorithm,and the end-point temperature prediction model of the EAF was established based on the e-FCNN algorithm.Simulation results show that the e-FCNN model end-point temperature prediction error is within±5 ℃ with a hit rate of 93.33％.In addition,CART,RF,e-SVR,and v-SVR models were developed using hyperparametric random grid search under the condi-tion of small-sample historical data,and the results show that the accuracy of the e-FCNN model is significantly bet-ter than others.Using the e-FCNN model to continuously track the actual production of 30 heats,the hit rate rea-ches 96.7％when the prediction error is within±6 ℃,which can effectively guide the production.In the future,further improvement of the combination of mechanism and data-driven is the development direction of EAF end-point temperature prediction models.
关键词
电弧炉/终点预报/终点温度/机器学习/小样本Key words
electric arc furnace/end-point prediction/end-point temperature/machine learning/small sample引用本文复制引用
基金项目
"十四五"重点研发计划资助项目(2022YFC3901403)
中央高校基本科研业务专项资金资助项目(N2225046)
出版年
2024
NETL
NSTL
万方数据