基于大数据技术的高炉铁水硅含量预测

铁水硅含量是炉缸热制度的化学热表示方式,也是表征炉温和铁水质量的重要参数.选取某钢铁厂4号高炉实时数据库和检化验数据库2019年的30个输入参数,通过数据处理和特征值筛选,最终选取17个参数进行模型预测,共计8760组.通过构建Adaboost模型、决策树模型和随机森林模型对2 h后的铁水中硅含量进行预测,发现Adab...     

热管换热器用于高炉热风炉余热回收

热管换热器是一种新型的高效换热装置。本文介绍了热管换热器在高炉热风炉余热回收中的应用，运行实践表明效果良好，可在我国冶金系统中推广，以提高高炉热风炉的热效率。     

承钢2500 m^3高炉热平衡测算与节能探讨

以承钢3座2 500 m^3高炉为研究对象,用第一总热平衡测试法进行了高炉热平衡测算.结果表明：承钢2 500 m3高炉近年来节能主要是降低了冷却软熔带带走热量约0.29 GJ/tFe,减少煤气带走热量约0.12 GJ/tFe,降低瓦斯灰带走热量约0.04 GJ/tFe.从测算结果可以看出,因高炉工艺优化吨铁耗风量降低后,收入项中热风带入的热量减少约0.4 GJ/tFe,碳素氧化带入的热量减少约0.12 GJ/tFe.介绍了承钢高炉近年采用的节能技术及应用效果,根据热平衡测算结果和目前的前沿节能技术,提出了承钢高炉进一步降低能耗的措施.     

Model of Hot Metal Silicon Content in Blast Furnace Based on Principal Component Analysis Application and Partial Least Square

 In blast furnace (BF) iron-making process, the hot metal silicon content was usually used to measure the quality of hot metal and to reflect the thermal state of BF. Principal component analysis (PCA) and partial least-square (PLS) regression methods were used to predict the hot metal silicon content. Under the conditions of BF relatively stable situation, PCA and PLS regression models of hot metal silicon content utilizing data from Baotou Steel No6 BF were established, which provided the accuracy of 884% and 892%. PLS model used less variables and time than principal component analysis model, and it was simple to calculate. It is shown that the model gives good results and is helpful for practical production.     

长寿高炉炉缸冷却系统的深入探讨

合理的炉缸冷却制度是保证高炉长寿的重要基础,从传热学的角度上对高炉冷却系统进行了深入探讨,分析了高炉炉缸传热数学模型的局限性,根据一维径向传热模型计算表明,增大冷却水流量可降低冷却水温差,但对增强炉缸冷却强度效果甚微。分析了冷却水对高炉炉缸的重要作用在于提高临界热流强度,防止出现核态沸腾和膜态沸腾。在炉缸结构一定的条件下,炉缸导出的热量主要取决于铁水的流动状态及铁水温度,最后给出炉缸砖衬出现缝隙的判定条件。     

基于参数优化SVR方法预测高炉煤气利用率

高炉煤气利用率是反映高炉能耗的重要指标,其预测控制对炼铁过程的节能降耗具有重要意义.利用某高炉在线采集的数据对煤气流温度分布和高炉煤气利用率的关系进行研究.首先,对高炉煤气利用率数据和能够实时反映煤气流分布的炉喉十字测温数据中的缺失值进行多重插补填充,并利用分位点计算煤气流分布的经验分布函数,得到测温数据的小时分布概率...     

高炉炉缸凝铁层的组成分析与导热系数测定

摘要：高炉炉缸内衬表面形成稳定的凝铁层将保护高炉炭砖并延长高炉寿命。利用光学数码显微镜观察统计分析高炉凝铁层生产样品,探究不同焦炭体积占比对凝铁层导热系数的影响。利用元素分析（XRF）、X射线衍射分析（XRD）、扫描电镜(SEM-EDS)等手段分析凝铁层的组成,并观察其微观形貌。利用瞬态平面热源法（TPS）测定凝铁层的导热系数,进一步分析其组成与导热系数之间的关系。结果表明,凝铁层由铁、充满铁水的焦炭、石墨碳、少量渣相组成,凝铁层内部没有气隙。凝铁层生产样品的导热系数测定范围为27.21～97.38W/(m·K),导热系数（λ）与其组成的焦炭面积比（Sc=22%～48%）之间的线性关系为：λ=-257.47Sc +157.65。模拟实验凝铁层的导热系数范围为30.54～53.95W/(m·K),该值远大于目前数学模型中采用的凝铁层导热系数（2～4W/m·K）,随着焦炭粒度的增加,凝铁层的导热系数先增加后减小。凝铁层中导热系数（λ）与焦炭体积分数Vc（Vc=39%～50%）的线性关系为：λ=-80.50Vc +78.56。研究结果进一步明确了凝铁层的物相组成及其导热系数,为高炉长寿的研究指明了方向。     

A Sliding‐window Smooth Support Vector Regression Model for Nonlinear Blast Furnace System

Blast furnace is one of the most complex industrial reactors and remains some unsolved puzzles, such as blast furnace automation, prediction of the inner thermal state, etc. In this work, a sliding‐window smooth support vector regression model is presented to address the issue of predicting the blast furnace inner thermal state, represented by the silicon content in blast furnace hot metal in the context. Different from the traditional numerical prediction models of silicon, the constructed SW‐SSVR model is devoted to predicting the changing trend of silicon and exhibits good performance with high percentage of successful trend prediction, competitive computational speed and timely online service. Additionally, some sharp fluctuation trend in the silicon test data can also be followed well by the SW‐SSVR model, which is always difficult for traditional data–driven based silicon prediction models. All of these indicate that the SW‐SSVR model is a good candidate to predict the change of blast furnace inner thermal state, and may provide a guide for operators to take proper action on operating blast furnace in advance.     

基于不同保温措施下的铁水包热状态模拟分析

在铁钢界面现有模式下的铁水运输过程中,由于铁水包运行周期及保温效果不够理想,导致在高炉接铁时铁包耐材温度低,热状态差,使得铁水在铁水包内的热量损失较大.减小铁水温降能有效防止铁水包结壳结瘤,降低离线烘烤频率,间接提高铁水包周转率;同时在转炉冶炼过程中,低温铁水将严重影响废钢的加入量和吹氧等操作.由此可见,铁水温度控制是钢铁企业节能降耗和高效有序生产的关键因素之一.为了减小铁水温降,本文建立了多种不同保温措施情况下的铁水包传热模型,通过fluent软件对各模型在不同空包时间情况下的温度场进行数值计算,分析不同保温措施及空包时间下热状态对铁水温降的影响规律.分析结果表明:无保温措施的情况下空包时间由5 h缩短至3 h能降低下一周期铁水温降2.2 K·h-1;空包阶段最合理的保温措施为增设6 mm左右绝热层并加包盖,能提高工作层平均温度约155 K,在空包3~5 h内能减小铁水温降3.4~3.7 K·h-1.该结论为铁水包空包阶段采取合理保温措施及不同保温情况下空包运行时间控制提供了理论指导.      

钢铁厂流程结构优化与高炉大型化

高炉是钢厂生产流程中物质、能量最为密集的工艺装置,对钢厂的物质流网络和能量流网络的构建与合理化运行有着重大影响。高炉的功能不仅是通过还原反应过程获得优质的铁水,而且伴随大量的能量转换和信息的输入/输出过程,应当在整个钢铁生产流程结构优化的前提下,综合思考高炉的合理座数、合理容积和合理位置。通过分析国际高炉的发展趋势和首钢京唐钢厂5 576m3高炉与迁安钢厂4 080m3高炉的比较,建设2×5 576m3高炉和3×4 080m3高炉可以得到相近的产量,但前者在节省投资、能源节约和信息控制等方面具有明显优势。由此可以看出,为了优化钢厂生产流程,提高市场竞争力,高炉大型化是一种明显的趋势。但是,并不是追求单座高炉越大越好,更不应盲目追求"最大"。应该在产品结构、物质流结构、能量流结构优化和动态运行优化前提下实施高炉大型化。一般的趋势是一个高效益、低成本生产的钢厂应以2～3座高炉为宜,并由此得到高炉大型化的合理容积、合理座数及其合理位置。这种发展趋势不仅适合于生产薄板的大型联合企业,而且也适合于生产建筑用棒/线材的中、小型钢厂。     

Numerical simulation on novel blast furnace operation of combining coke oven gas injection with hot burden charging

A novel blast furnace operation of coke oven gas (COG) injection simultaneously with hot burden charging has been proposed to solve the problem of insufficient heat in the BF shaft zone under the condition of COG injection and make full use of the abundant sensible heat of high temperature burden. In this paper, the novel process has been simulated with a multifluid blast furnace model. The results show that, in comparison with the operation of COG injection only, under the operation of COG injection together with hot burden charging, the temperature in the upper zone of the shaft increases while that in lower zone decreases. Furthermore, the reduction of iron bearing material is improved in the top zone, and the cohesive zone tends to descend and narrow. The coke ratio, fuel ratio and CO₂ emissions of the operation of charging hot pellet and coke with the temperature of 800°C are decreased by 4.0, 4.7 and 5.3% respectively, while the hot metal productivity is increased by 7.14%. Therefore, COG injection combined with hot burden charging operation not only increases temperature in the upper part of the blast furnace but also decreases energy consumption per tonne hot metal.     

高炉铁水温度的多元时间序列建模和预测

针对高炉炉温铁水硅含量为预测对象的不确定性和高炉炉温单变量时间序列模型所含炉温输入信息量少、难以揭示各个变量之间的相互关系及变化规律的特点,以高炉铁水温度为研究对象,建立BP神经网络多元时间序列模型和T-S模糊神经网络多元时间序列模型。应用高炉实际数据做模型检验,结果表明,T-S模糊神经网络多元时间序列模型取得更好的命中率和预测精度。     

高炉炉缸凝铁层导热系数测定及传热模型修正

摘要：高炉炉缸内衬表面形成稳定的凝铁层将延长高炉寿命。采用自制的凝铁层模拟实验装置，在中温高压条件下利用锡与焦炭制备凝铁层模拟样品；通过三维数码显微镜观察统计不同凝铁层模拟样品对应的金属与焦炭的面积比，采用瞬态平面热源法测定导热系数，探究其对凝铁层导热系数的影响。结果表明，凝铁层模拟样品（凝锡层）的导热系数范围是23.58～40.39W/（m·K）；凝铁层样品的导热系数范围为28.05～48.19W/（m·K）；还原凝铁层真实导热系数后，可以确定高炉炉缸区域传热模型中的气隙厚度为0.5～1.0mm。     

Variation in hot metal and slag composition during tapping of blast furnace

Abstract

To determine the quality of the hot metal and the thermal conditions inside the blast furnace, the composition of the hot metal and slag must be known. Obtaining representative metal and slag samples during tapping is thus highly important to blast furnace operation. The study covered in the present report focused on hot metal and slag composition variation during tapping from a commercial blast furnace. From the results, optimal sampling time points for obtaining elemental concentrations that can be taken as representative for the whole tapping sequence were identified. It was furthermore concluded that the reliability of hot metal composition data is significantly improved by averaging elemental concentrations determined from two samples, each taken at a particular time point. One sampling, however, was found to be adequate for slag. Results from the study also showed a fairly strong correlation between amounts of silicon and carbon, sulphur and carbon, and silicon and sulphur in the hot metal, while a weaker correlation between hot metal temperature and each of these elements was observed.     

Mathematical model of metallurgical thermal processes and application

There are lots of physical changes and chemical reactions in the processes of iron and steel making, these processes are quite complex in the aspect of heat transfer.The processes of iron and steel making can be approximately divided into three kinds.The first kinds are the processes of fusion metallurgy which involve enormous chemical reactions,such as blast furnace,converter,electric furnace and coke oven.The second kinds are the processes of heating and cooling which are mainly the physical changes,such as walking-beam reheating furnace,annular heating furnace and car-type furnace.The third kinds are the processes of heat treatment which mainly adjust metallurgical structure of metal,such as roller hearth heat treatment furnace, strip continuous heat treatment vertical/horizontal furnace and HPH bell-type annealing furnace.Every process can only be finished in particular thermal equipment.And all the physical and chemical processes mentioned above must obey first principles of engineering thermodynamics,heat & mass transfer,hydromechanics, combustion,metallurgy physical chemistry etc,and which can be summarized as principle of heat transfer,mass transfer,momentum transfer and chemistry reaction.In this paper,based on first principle of heat and mass transfer in iron and steel making processes,a series of mathematical models of thermal equipments and processes are presented.Such as the model of hot-blast stoves,coke oven,CDQ-boiler system,sintering, reheating furnace,soaking furnace,annular heating furnace,roller hearth heat treatment furnace,strip continuous heat treatment vertical/horizontal furnace,HPH bell-type annealing furnace,control cooling of medium plate,burner,heat exchanger and regenerative burner etc.The on-line application of the model is based on experimental certification of the mathematical model.And finally the computer optimization system of metallurgical thermal process is obtained.     

韶钢2号高炉降低生铁含硅量的实践

韶钢２号高炉近年来通过改善原燃烧质量、确保炉况稳定顺行、提高煤气利用率,使生铁含硅量不断降低。为了进一步降低生铁含硅量,必须继续做好原料管理和操作管理工作。     

焦炭热性能对高炉操作影响的研究进展

通过调研国内外焦炭热性能对高炉操作影响的研究进展,发现日本炼铁界对焦炭反应性关注度较高,且观点较一致:在确保焦炭冷、热态强度的前提下,较高反应性的焦炭有利于抑制风口部位焦炭的粉化和改善高炉炉内矿石还原速度,利于低成本冶炼;国内对焦炭反应性对高炉操作影响机理方面的探讨较日本少,观点与日本不同,认为焦炭具有较低的反应性和高强度利于高炉操作。建议更为全面深入研究热性能对高炉操作的影响,并在生产实践中进行探索,以求在领域内达成共识。     

高炉铁水硅含量自组织预测中的模式量化

研究了高炉铁水硅含量自组织经验进化预测模型中的模式量化问题。在模式量化方案中,采用高炉过程变量时间序列数据的均值、梯度值和波动值作为数据的特征最来进行特征提取,将可预测率、命中率、趋势命中率等判据用于评判预测效果,并用天津铁厂1号高炉的过程数据进行了离线检验。结果表明：基于过程变量的特征提取方法可用于具有均匀时间间隔的高炉过程数据的特征提取。正确运用该方法可使铁水硅含量自组织预测模型的预测命中率提高10％左右。     

基于Xgboost的高炉透气性指数预测模型

高炉透气性指数是高炉监控指标的一项重要参数,及时掌控高炉透气性指数的变化趋势并对其进行准确预测,对辅助操作者保持高炉的稳定顺行十分必要。基于某高炉现场实际生产数据,对原始数据存在异常值、缺失值等问题进行处理。利用Spearman、MIC(最大信息系数)和随机森林特征消除等特征选择方法对标准化后的数据选取特征变量,选用Xgboost模型进行预测。结果表明,Xgboost相较于随机森林和线性回归模型具有较大优势,模型在误差±1.5%范围内的准确率达到94.27%,能够准确预测下一小时透气性指数,及时指导高炉生产,保证高炉稳定顺行。     

数学模型在宝钢高炉操作中的应用

论述了炉况判断GO-STOP模型、TC指数和炉温预报模型、软熔带模型、煤气流分布判断和布料控制模型的原理、建模方法及其在宝钢大型高炉生产操作中的应用情况。宝钢高炉生产不仅采用先进的自动化装备,而且从 1号高炉建设起即先后引进了8个先进的数学模型指导高炉操作。通过长期学习、消化,特别是近几年来对模型的改造和完善,并融人现代智能模型技术,大大提高了模型的精度和应用效果,这些模型为宝钢大型高炉实现长期稳定顺行、主要技术经济指标达到世界先进水平发挥了重要作用。