基于大数据挖掘的钒钛高炉综合运行状态评价模型  

Evaluation model for comprehensive operation condition of vanadium and titanium blast furnace based on big data mining

作　　者：李红玮 李欣 刘小杰 刘然 陈树军 吕庆 LI Hongwei;LI Xin;LIU Xiaojie;LIU Ran;CHEN Shujun;LÜQing(College of Metallurgy and Energy,North China University of Science and Technology,Tangshan 063009,Hebei,China;Chengde Vanadium Titanium,HBIS Group,Chengde 067102,Hebei,China)

机构地区：[1]华北理工大学冶金与能源学院,河北唐山063009 [2]河钢集团承德钒钛有限公司,河北承德067102

出　　处：《钢铁》2023年第10期51-66,共16页Iron and Steel

基　　金：国家自然科学基金青年基金资助项目(52004096);河北省省属高等学校基本科研业务费资助项目(JQN2020032)。

摘　　要：高炉炉况的波动严重影响高炉生产过程的铁水产量、质量和能耗。及时全面掌握高炉运行状态情况,减少炉况波动是保持高炉生产稳定顺行的关键。以某钒钛高炉自身历史数据为基础,建立了一种基于大数据挖掘的高炉综合运行状态评价模型。依据高炉炼铁全流程数据仓库资源,采集整合高炉相关生产数据,对原始数据存在的空缺值、异常值等问题进行了数据处理,得到了模型开发所需要的干净数据。结合高炉工艺和专家经验,选取表征高炉综合运行状态的33个评价指标,建立高炉综合运行状态评价指标体系,利用基于博弈论的层次分析法和熵权法的组合赋权及改进的TOPSIS算法建立AHP_EWM_TOPSIS高炉综合运行状态评价模型,对高炉运行状态进行评估和排序。模型的评价结果与实际生产情况进行验证,综合匹配率达到94.49%,能够准确评价高炉综合运行状态情况,并为高炉操作者提供及时有效的高炉运行状态信息。对历史高炉运行状态进行统计分析,得出高炉炉况的演变情况。总结了良好高炉运行状态条件下运行参数的最佳范围,为高炉的生产运行优化提供操作依据和数据支持。模型能够快速判断高炉的实时运行状态情况,辅助高炉生产操作优化,促进高炉的长期稳定运行,实现高炉优质、高产、低耗、长寿的生产目的。The fluctuation of blast furnace conditions have a serious impact on the yield,quality of molten iron and energy consumption in the blast furnace production.A timely and comprehensive overview of blast furnace operating conditions to reduce furnace condition fluctuations is the key to maintaining stable and smooth blast furnace production.Based on the historical data of a vanadium and titanium blast furnace,a comprehensive evaluation model for the blast furnace operation is eastablised with the big data mining.Using the data warehouse of the blast furnace iron-making process,the related production data is collected and integrated,the null values and outliers of the raw data are processed,thus the clean data for the model is obtained.Combined with the process and expert experiences,33 evaluation indexes characterizing the comprehensive operation condition of blast furnace are selected to carry out the evaluation system of the operation indexes for blast furnace.According to the combination weighting of analytic hierarchy process and entropy weight method based on game theory and the improved TOPSIS method,the AHP_EWM_TOPSIS model is established to evaluate the blast furnace operation.The comprehensive matching rate from the evaluation results verified with the actual production reaches 94.49%,which indicates this model could accurately evaluate the comprehensive operation of blast furnace and provide the timely and effective information for the operators.The statistical analysis of the blast furnace operation is carried out to derive the evolution of that.As the blast furance is operated well,the optimum operational parameters are summarised,which could further provide the operational basis and data support for the optimisation of blast furnace production.This model can quickly judge the real-time operation of blast furnace,and optimize the blast furnace production,as a result,the long-term stable operation of the blast furnace is obtained,and the production purposes include high quality,high production,low consum

关 键 词：大数据挖掘 高炉运行状态 TOPSIS评价 钒钛高炉 操作优化 

分 类 号：TF54[冶金工程—钢铁冶金]