Predicting the alloying element yield in a ladle furnace using principal component analysis and deep neural network

The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.

Steady State Heat Transfer of Ladle Furnace During Steel Production Process

The heat transfer analysis was performed for an industrial ladle furnace （LF） with a capacity of 55-57 t in Turkey. The heat losses by conduction, convection and radiation from outer and bottom surfaces, top and electrodes of LF were determined in detail. Finally, some suggestions about decreasing heat losses were presented.

Ladle Furnace Temperature Prediction Model Based on Large-scale Data With Random Forest

In ladle furnace, the prediction of the liquid steel temperature is always a hot topic for the researchers. The most of the existing temperature prediction models use small sample set. Today, the precision of them can not satisfy practical production. Fortunately, the large sample set is accumulated from the practical production process. However, a large sample set makes it difficult to build a liquid steel temperature model. To deal with the issue, the random forest method is preferred in this paper, which is a powerful regression method with low complexity and can be designed very quickly. It is with the parallel ensemble structure,uses sample subsets,and employs a simple learning algorithm of sub-models. Then, the random forest method is applied to establish a temperature model by using the data sampled from the production process. The experiments show that the random forest temperature model is more precise than other temperature models.

Mass Balance Modeling for Electric Arc Furnace and Ladle Furnace System in Steelmaking Facility in Turkey

In the electric arc furnace （EAF） steel production processes, scrap steel is principally used as a raw material instead of iron ore. In the steelmaking process with EAF, scrap is first melted in the furnace and then the desired chemical composition of the steel can be obtained in a special furnace such as ladle furnace （LF）. This kind of furnace process is used for the secondary refining of alloy steel. LF furnace offers strong heating fluxes and enables precise temperature control, thereby allowing for the addition of desired amounts of various alloying elements. It also provides outstanding desulfurization at high-temperature treatment by reducing molten steel fluxes and removing deoxidation products. Elemental analysis with mass balance modeling is important to know the precise amount of required alloys for the LF input with respect to scrap composition. In present study, chemical reactions with mass conservation law in EAF and LF were modeled altogether as a whole system and chemical compositions of the final steel alloy output can be obtained precisely according to different scrap compositions, alloying elements ratios, and other input amounts. Besides, it was found that the mass efficiency for iron element in the system is 95.93%. These efficiencies are calculated for all input elements as 8. 45% for C, 30.31% for Si, 46.36% for Mn, 30.64% for P, 41.96% for S, and 69.79% for Cr, etc. These efficiencies provide valuable ideas about the amount of the input materials that are vanished or combusted for 100 kg of each of the input materials in the EAF and LF system.

CaCO_3 film synthesis from ladle furnace slag: morphological change, new material properties, and Ca extraction efficiency

A rapidly air-cooled ladle furnace slag(RA-LFS), which is a type of steelmaking slag discharged from a steel mill, was used to synthesize CaCO_3 film. The CaCO_3 film with 35 cm^2 of surface area was synthesized under atmospheric conditions, and the surface morphology of the CaCO_3 films was changed by using additives(CaCl_2 and ethylene glycol). Especially, the addition of CaCl_2 changed the surface morphology of CaCO_3 film with pore and induced new material properties, such as water adsorption. The(012) face of CaCO_3 film(calcite) was rapidly decreased by the addition of CaCl_2. The major components of RA-LFS were calcium(type of CaO, 53.9 wt%) and aluminum(type of Al_2 O_3, 37.9 wt%), and the major crystal phases of RA-LFS were C_3 S, C_(12) A_7, and C_3 A. The calcium extraction efficiency of RA-LFS was significantly increased after the CaCO_3 film synthesis. The material properties(hardness and elastic modulus) and the thermal characteristics of the CaCO_3 films were analyzed by nano-indentation and thermogravimetry–differential thermal analysis. The synthesized CaCO_3 films from RA-LFS and Ca(OH)_2(reagent) showed similarities in terms of their material properties and the decomposition temperature.

Development of an improved CBR model for predicting steel temperature in ladle furnace refining

In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation(CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network(BPNN)model in the ranges of [-3, 3] and [-7, 7], respectively. It was found that the mean absolute error(MAE) and root-mean-square error(RMSE)values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.

Element yield rate prediction in ladle furnace based on improved GA-ANFIS

The traditional prediction methods of element yield rate can be divided into experience method and data-driven method.But in practice,the experience formulae are found to work only under some specific conditions,and the sample data that are used to establish data-driven models are always insufficient.Aiming at this problem,a combined method of genetic algorithm(GA) and adaptive neuro-fuzzy inference system(ANFIS) is proposed and applied to element yield rate prediction in ladle furnace(LF).In order to get rid of the over reliance upon data in data-driven method and act as a supplement of inadequate samples,smelting experience is integrated into prediction model as fuzzy empirical rules by using the improved ANFIS method.For facilitating the combination of fuzzy rules,feature construction method based on GA is used to reduce input dimension,and the selection operation in GA is improved to speed up the convergence rate and to avoid trapping into local optima.The experimental and practical testing results show that the proposed method is more accurate than other prediction methods.

Corrosion Mechanism of Ladle Furnace Refining Slag to Fired MgO-CaO Bricks

Corrosion effect of ladle furnace （LF） refining slag on fired MgO-CaO bricks with about 34% CaO was studied by static crucible method,and corrosion mechanism was analyzed by techniques of scan electron micrograph,energy dispersive spectrometer,and X-ray diffraction. The results show that：MgO-CaO bricks exhibit excellent corrosion resistance but poor penetration resistance to LF refining slag; oxidation of （Mg·Fe）O in reaction zone results in volume expansion forming cracks; penetration of 2CaO·Fe2O3 （C2F） from slag to MgO-CaO bricks increases liquid phases which accelerates corrosion of the bricks; a protective layer of 2CaO·SiO2 formed on reaction interface prevents penetration of C2F to the bricks.

Rational argon stirring for a 150-t ladle furnace

Based on the principle of similarity, water modeling experiments were carried out for a 150-t ladle furnace. The rational parameters of argon stirring were determined as the optimized positions of nozzles, top area of the porous brick, and gas flow rate. The following results are obtained： 1） the optimized positions of two nozzles are at 0.333R （R refers to the radius of the ladle at bottom） with an angle of 135°; 2） the top diameter of the porous brick should be 130 mm; 3） the flow rate of gas should be 25.0-30.6 m^3/h. The plant trial shows that the improved process is effective in enhancing the cleanliness of round billets. The total oxygen content, microinclusions, and macroinclusions in round billets are reduced by 12.5%, 8.2%, and 20%, respectively.

Improvement of Service Life of Small Furnace Covers on 150 t Refining Ladles

The factors restricting the life of the refining furnace cover were introduced,including the airflow erosion of the refining dust removal system,the melting loss caused by the arc radiation of the electrode,the chemical erosion and penetration of slag and gas,and the condition of refining slag.The improvement measures are adjusting the material of the small furnace cover from corundum to chrome corundum,using a large shaking table to vibrate,optimizing the size design of the small furnace cover,and appropriately thickening the weak areas in the triangular area.The average service life of the refining furnace cover has been increased from one week to two months,reaching 4 maintenance cycles,which meets the needs of the refining production.

Improvement of the Structure and the Electromagnetic Characteristics of an Induction Ladle Furnace

Based on a numerical analysis of the alternating electromagnetic field in the process of Steel refining with an induction ladle furnace (ILF), the optimization of the structure of ILF and the electromagnetic field for melting is realized in the present work. The optimization of the ILF by outward extension of inner yokes can decrease the magnitic flux leakage obviously, reduce the eddy current energy loss dramatically and then, decrease the total power consumption.

Development and Application of Castables for Ladle Nozzle of Electric Arc Furnace

The castables for ladle nozzle were developed using brown corundum as the main raw material and the right amounts of complex additives . The influence of several additives on the properties such as strength and permanent linear change of the samples was studied . The results showed that applying complex additives improved the strength and the volume stability of the castables greatly. The campaign of the castables for ladle nozzle has increased from about 40 heats to 70 heats.

Numerical modeling of blow refining process of a 300t ladle furnace at Baosteel

Targeting the single tuyere and double tuyere methods of argon blowing for Baosteel＇ s 300 t ladle furnace, the 3D continuity equation, the N-S equation and the turbulent k-ε double-equation were used to model the form of the molten steel flow and the dead areas under six different argon blowing conditions. The different flow field forms and the degree of mixing under different argon blowing methods were compared. The results demonstrate that when large ladles are operated via different methods of argon blowing, the spray from the centre of a single tuyere forms a symmetrical vortex, while when a double tuyere sprays, there is basically no clear vortex. In regards to the amount of argon blowing that will produce the best blend of molten steel, the amount of dead area reduction will not be clearly noticeable if there is an excessive argon blowing amount.

Direct Current Electric Arc-Electroslag Ladle Furnace

In order to solve the high consumption problem of small capacity ladle furnace (LF), the operation principle and control method of the DC are and electroslag heating ladle furnace are introduced. With only one arcing electrode, the distance between the are and the wall of ladle is enlarged, and consequently the consumption of the ladle refractory is decreased. In the invention, a signal electrode is embedded in the refractory lining of the ladle, which contacts directly with the liquid steel and the ladle shell. Two graphite anode ends are submerged in the slag layer. The signal electrode is used as voltage reference during refining process. The electroslag voltage between anode end and liquid steel is applied to control the depth of anode end in the slag layer during the refining process with this ladle furnace.

LF精炼炉废钢自动加料系统工程实践

基于对废钢资源高效利用的目的,介绍了某企业开发的LF精炼炉废钢自动上料系统项目,分析了在LF精炼炉添加优质废钢的优势,主要包括可以高效利用废钢资源中的合金元素降低生产成本,提高经济效益;LF精炼炉添加废钢可以调整LF炉钢水重量来稳定连铸生产节奏;同时,对废钢上料系统设备进行了介绍,对钢铁企业开发LF精炼炉高废钢比加料项目提供了一定的参考价值。

LF精炼炉钢包回转台驱动系统设计与分析

LF炉是整个钢铁精炼工艺过程中最为重要的设备,具有脱硫、脱氧,微调钢水成分的作用,对提高钢水品质具有重要作用;是每个钢企生产优钢特钢的必备设备。现有LF精炼炉主要结构型式分为双车式、回转台式以及电极旋转式。回转台式LF炉其特点是利用回转台的自转将钢水从等待工位转运钢水至冶炼工位进行冶炼;回转台式LF炉具有占地面积小,使用安全可靠,维护保养工作量小,效率高等优势。回转台作为LF精炼炉的重要组成设备,对整个精炼炉安全运行有着重要的作用;而回转台的平稳运行又取决于驱动装置设计的可靠性。针对回转台的驱动装置设计进行分析。通过对回转台驱动系统基础数据的计算、电机和减速机的选型,提出一个安全、可靠的设计方案,以便其他设计者进行参考。

LF精炼钢水温度预测模型的开发与应用

针对LF工序终点钢水温度预测的问题,基于XGBoost算法建立了LF精炼钢水温度预测模型。在温度预测模型的离线测试阶段,模型在温度误差±5℃、±10℃时的命中率分别为79.8%、98.5%;模型上线运行一段时间后,统计了某段内的180炉数据,得到模型在温度误差±5℃、±10℃时的命中率分别为86.6%、97.8%。该温度预测模型满足钢厂的实际使用需求。

LF精炼炉双孔差流量底吹模式优化物理模拟

以国内某钢厂LF精炼炉为研究对象构建了1∶4的水模型,对比研究了双孔等流量底吹和双孔差流量底吹两种模式,并采用响应面法构建了弱底吹流量、强底吹流量和液面高度三因素的钢水混匀时间预测模型,运用该模型得出了差流量底吹模式的最优底吹流量方案。结果表明,双孔差流量底吹模式的混匀效果优于双孔等流量底吹模式;构建的差流量底吹模式混匀时间预测模型拟合效果较好;双孔差流量底吹模式下的混匀时间受到强底吹流量和弱底吹流量的交互作用影响;采用所建模型预测混匀时间与实测值误差均在4%以内。验证了双孔差流量底吹模式相较于等流量底吹模式具有更高的混匀效率,表明了基于响应面法对双孔差流量底吹模式的优化是可行的。

Explainable machine learning model for predicting molten steel temperature in the LF refining process

Accurate prediction of molten steel temperature in the ladle furnace(LF)refining process has an important influence on the quality of molten steel and the control of steelmaking cost.Extensive research on establishing models to predict molten steel temperature has been conducted.However,most researchers focus solely on improving the accuracy of the model,neglecting its explainability.The present study aims to develop a high-precision and explainable model with improved reliability and transparency.The eXtreme gradient boosting(XGBoost)and light gradient boosting machine(LGBM)were utilized,along with bayesian optimization and grey wolf optimiz-ation(GWO),to establish the prediction model.Different performance evaluation metrics and graphical representations were applied to compare the optimal XGBoost and LGBM models obtained through varying hyperparameter optimization methods with the other models.The findings indicated that the GWO-LGBM model outperformed other methods in predicting molten steel temperature,with a high pre-diction accuracy of 89.35%within the error range of±5°C.The model’s learning/decision process was revealed,and the influence degree of different variables on the molten steel temperature was clarified using the tree structure visualization and SHapley Additive exPlana-tions(SHAP)analysis.Consequently,the explainability of the optimal GWO-LGBM model was enhanced,providing reliable support for prediction results.

LF钢包用耐火材料的研究进展

随着钢铁产业飞速进步,对钢材品质也有了越来越严苛的要求,钢包从简单的钢水盛装容器转变为具有冶炼功能的多元容器。LF精炼以其设备结构简单、冶金功能丰富及经济效益好等优点,成为冶金过程中不可或缺的环节。钢水、渣及耐火材料三者在整个冶炼过程中是相互作用的。在LF钢包的钢包盖、渣线、包壁、透气砖等位置均需要用到耐火材料。其中渣线位置由于受到的侵蚀最为严重,而且经受了剧烈的温差波动,最常用的耐火材料为MgO-C耐火材料。文章对LF钢包精炼工艺进行了简介,概括了LF钢包各部位对耐火材料的要求和目前使用的耐火材料种类。