Hybrid model for BOF oxygen blowing time prediction based on oxygen balance mechanism and deep neural network

The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.

Numerical Simulation of Decarburization in a Top-Blown Basic Oxygen Furnace

An improved mathematical model to describe the decarburization process in basic oxygen furnaces for steelmaking is presented in this work. This model takes into account those factors or parameters that determine the bath-oxygen impact area, such as the cavity depth, the lance height, the number of nozzles and the nozzles diameter. In the thermal issue, the model includes the targeted carbon content and temperature. The model is numerically solved, and is validated using reported data plant. The oxygen flow rate and the lance height are varied in the numerical simulations to study their effect on the carbon content and decarburization rate.

Slag Splashing in a Basic Oxygen Furnace under Different Blowing Conditions

The influence of three different blowing conditions on the slag splashing process in a basic oxygen furnace for steelmaking is analyzed here using two-dimensional transient Computational Fluid Dynamics simulations. Four blowing conditions are considered in the computer runs: top blowing, combined blowing using just a bottom centered nozzle, combined blowing using two bottom lateral nozzles, and full combined blowing using the three top and the three bottom nozzles. Computer simulations show that full combined blowing provides greater slag splashing than conventional top blowing.

Prediction of lime utilization ratio of dephosphorization in BOF steelmaking based on online sequential extreme learning machine with forgetting mechanism

The machine learning models of multiple linear regression(MLR),support vector regression(SVR),and extreme learning ma-chine(ELM)and the proposed ELM models of online sequential ELM(OS-ELM)and OS-ELM with forgetting mechanism(FOS-ELM)are applied in the prediction of the lime utilization ratio of dephosphorization in the basic oxygen furnace steelmaking process.The ELM model exhibites the best performance compared with the models of MLR and SVR.OS-ELM and FOS-ELM are applied for sequential learning and model updating.The optimal number of samples in validity term of the FOS-ELM model is determined to be 1500,with the smallest population mean absolute relative error(MARE)value of 0.058226 for the population.The variable importance analysis reveals lime weight,initial P content,and hot metal weight as the most important variables for the lime utilization ratio.The lime utilization ratio increases with the decrease in lime weight and the increases in the initial P content and hot metal weight.A prediction system based on FOS-ELM is applied in actual industrial production for one month.The hit ratios of the predicted lime utilization ratio in the error ranges of±1%,±3%,and±5%are 61.16%,90.63%,and 94.11%,respectively.The coefficient of determination,MARE,and root mean square error are 0.8670,0.06823,and 1.4265,respectively.The system exhibits desirable performance for applications in actual industrial pro-duction.

10B21冷镦钢BOF-LF过程钢渣渣化行为研究

在钢铁长流程冶炼过程中,各环节稳定高质量生产都离不开炉渣的重要作用,流程性成渣过程的深入研究对强冶降本、提质增效和资源回用影响显著。本文以10B21冷镦钢生产为背景,研究钢渣在BOF-LF过程的渣化行为。结果表明,经过BOF-LF过程,从化学成分角度,钢渣的二元碱度(CaO/SiO_(2))陡升,而三元碱度(CaO/(SiO_(2)+Al_(2)O_(3)))和全碱度([(CaO)+(MgO)+(MnO)+(FeO)]/[(SiO_(2))+(Al_(2)O_(3))+(P_(2) O_(5))])均呈现下降趋势。从矿物组成分析,转炉渣的主要矿相为CaO、Ca_(2)SiO_(4)、(Mg,Fe)O、Ca_(2)Fe_(2)O_(5)、Ca 2(Al,Fe)_(2)O_(5),而精炼渣的矿物组成主要为CaO、Ca_(6)Al_(7)O_(16)、Ca_(2)SiO_(4)、FeB。从显微组织形貌分析,观察到转炉渣样以板条状、珊瑚状形貌的硅酸二钙为主体矿相,其余各矿相在渣中无序分布。在精炼渣中,可观察到含玻璃化分层结构,生成的硅酸二钙和钙铝酸盐呈现聚集性分布。结合熔渣结构的理论计算,钢渣的NBO/T值由转炉渣的8.34下降到精炼渣的2.93,解离程度呈现下降趋势。

基于WGKSOM-DRCA自适应即时学习的转炉炼钢终点碳温软测量方法

转炉炼钢终点碳温的准确预测是实现转炉终点控制的关键。针对转炉生产过程数据存在波动性大和非线性特点引起传统即时学习度量的算法学习集质量低,进而削弱模型预测性能的问题,提出了一种基于加权高斯核自组织映射动态相关成分分析(WGKSOM-DRCA)自适应即时学习软测量建模方法用于转炉炼钢终点碳温预测。首先,采用引入标签信息的WGK度量准则构造WGKSOM聚类算法引导聚类方向,提高算法的聚类质量并降低类簇数据波动性对于建模的影响;其次,利用高斯后验概率计算待测样本的隶属度并通过引入动态因子构建DRCA度量策略,从而实现自适应的样本选择,进一步提升待测样本对应的局部算法学习集质量并用于局部模型训练,最终输出终点碳温的预测结果。实验表明,所提算法在转炉炼钢终点碳温预测上相对于其他算法有更好的表现,在±0.02%的预测误差范围,碳含量的预测精度为92%,在±10℃的误差范围,温度的预测精度为93.5%。

采用BOF-LF-CC工艺试制20 Mn VB钢

借鉴国内钢厂电炉工艺生产 2 0MnVB钢的成功经验 ,设计出 2 0MnVB钢的内控成分并强化转炉终点控制、LF加钛保硼工艺、低过热度浇注、合理的轧钢工艺等 ,实现了BOF LF

Numerical investigation of basic oxygen furnace slag modification with gas bottom-blowing and SiO_(2) modifier

To avoid the volume expansion of basic oxygen furnace (BOF) slag for use in building materials, a hot slag modification process was proposed to reduce free CaO (f-CaO) in the molten slag. A transient 3D numerical model of BOF molten slag modification by SiO_(2) particles was established. The flow and heat transfer of molten slag, movement and dissolution of the modifier, and concentration distribution of f-CaO in slag during the modification of BOF were studied. The distribution of f-CaO concentration is inhomogeneous all over the molten slag. The mixing effect at the slag surface is weaker than that at the half-height plane of the slag. To consume the f-CaO below 2.0 wt.% in the slag, the optimum quantity of the SiO_(2) modifier is 10.0% of the mass of the slag. The fine SiO_(2) particles help attain a lower final mass fraction of f-CaO and a higher SiO_(2) utilization ratio.

A process model for BOF process based on bath mixing degree

The process model for BOF process can be applied to predict the liquid steel composition and bath temperature during the whole steelmaking process. On the basis of the traditional three-stage decarburization theory, the concept of mixing degree was put forward, which was used to indicate the effect of oxygen jet on decarburization. Furthermore, a more practical process model for BOF steelmaking was developed by analyzing the effect of silicon, manganese, oxygen injection rate, oxygen lance height, and bath temperature on decarburization. Process verification and end-point verification for the process model have been carried out, and the verification results show that the predic- tion accuracy of carbon content reaches 82.6% （the range of carbon content at the end-point is less than 0. 1wt%） and 85.7% （the range of carbon content at end-point is 0. 1wt% -0.7wt%） when the absolute error is less than 0.02wt% and 0.05wt%, respectively.

Application of variable-filtrating technique on fuzzy-reasoning neural network system predicting BOF end-point carbon content

Artificial intelligence techniques have been used to predict basic oxygen furnace(BOF) end-points. However,the main challenge is to effectively reduce the input nodes as too many input nodes in neural network increase complexity,decrease accuracy and slow down the training speed of the network.Simply picking-up variables as input usually influence validity of model.It is quite necessary to develop an effective method to reduce the number of input nodes whereby to simplify the network and improve model performance.In this study,a variable-filtrating technique combining both metallurgical mechanism model and partial least-squares(PLS ) regression method has been proposed by taking the advantages of both of them,i.e.qualitive and quantative relationships between variables respectively.Accordingly,a fuzzy-reasoning neural network(FNN) prediction model for basic oxygen furnace(BOF) end-point carbon content based on this technique has been developed.The prediction results showed that this model can effectively improve the hit rate of end-point carbon content and increase network training speed.The successful hit rate of the model can reach up to 94.12%with about 0.02% error range.

HMPT-BOF-RH-CSP process for SPHE substrate of cold rolled deep drawing steel

Based on hot metal pretreatment （HMPT）-basic oxygen furnace （BOF）-Rheinstahl Heraeus （RH）-compact strip production （CSP） process, parameters controlling on cold rolling deep drawing substrate SPHE were investigated during smelting and rolling process by composition design and technology control. The influence of parameters on chemical compositions, mechanical properties and microstructure was revealed by scanning electron microscope （SEM）. The results show that, 1） main chemical components in SPHE are w（C）_〈40×10^-6, w（Si）_〈 0.01%, w（S）_〈0.009%, w（N）〈20×10^-6, w（O）〈_ 25×10^-6; 2） main mechanical properties of the SPHE are Crs=274 MPa, 00=334 MPa, A=48.9%; 3） main performances of deep drawing quality （DDQ） grade steel produced by SPHE are as follows, transversely crs=167 MPa, 00=298 MPa, n=0.219, r=2.46; vertically σs=166 MPa, 00=298 MPa, n=0.226, r=2.39; in 45° direction σ=171 MPa, 00=308 MPa, n=0.214, t=2.26; 4） microstrueture of DDQ is ferrite, average grain size is Grade 7.5, and inclusion size is 3-10μm.

氧气转炉煤气全干法显热回收系统中CO爆燃与防爆研究

氧气转炉煤气一般在850°C左右时采用喷水/水雾法降温除尘,导致煤气50%的显热被浪费.为了充分利用转炉炼钢过程中富含CO煤气的余热资源,新方法取消了喷水工艺,采用转炉煤气全干法显热回收系统,但是该技术在转炉煤气前烧与后烧阶段存在煤气爆炸的风险.针对转炉全干法系统的安全稳定运行需求,通过实验和理论计算研究了CO当量比、混合气初始温度和含水量等因素对CO爆燃特性的影响.结果表明:CO爆燃的最大压力和火焰速度随着混合气体中CO当量比的减小呈现减少的趋势,但当CO当量比小于0.368时,则对火焰速度的影响不大.在实验CO当量比范围内,爆燃压力最大值为0.65 MPa,最大爆燃速度约为750 m/s;混合气体初始温度升高导致爆燃过程中产生的最大爆燃压力降低,与此同时火焰速度会相对增加,进而影响火焰传播时间.含水量增加会导致CO爆燃的最大爆燃压力的增加,但含水量到达0.463%后继续增大则对最大爆燃压力影响不大;最后,通过分析CO爆燃特性和实际生产过程,提出了燃烧控制与强化以及煤气爆炸遏制等防爆方法和技术,从而有效降低爆燃带来的损失.

Removal kinetics of phosphorus from synthetic wastewater using basic oxygen furnace slag

Removal kinetics of phosphorus through use of basic oxygen furnace slag（BOF-slag）was investigated through batch experiments. Effects of several parameters such as initial phosphorus concentration, temperature, BOF-slag size, initial p H, and BOF-slag dosage on phosphorus removal kinetics were measured in detail. It was demonstrated that the removal process of phosphorus through BOF-slag followed pseudo-first-order reaction kinetics. The apparent rate constant（kobs） significantly decreased with increasing initial phosphorus concentration, BOF-slag size, and initial p H, whereas it exhibited an opposite trend with increasing reaction temperature and BOF-slag dosage.A linear dependence of kobson total removed phosphorus（TRP） was established with kobs=（3.51 ± 0.11） × 10^-4× TRP. Finally, it was suggested that the Langmuir–Rideal（L–R）or Langmuir–Hinshelwood（L–H） mechanism may be used to describe the removal process of phosphorus using BOF-slag.

Dephosphorization stability of hot metal by double slag operation in basic oxygen furnace

Double slag process was adopted to produce low-phosphorus steel from middle-phosphorus hot metal.To achieve a stable dephosphorization operation,conventional process was modified as follows：the blowing time was extended by approximately 1min by reducing the oxygen supply flow rate;calcium ferrite pellets were added to adjust the slag composition and viscosity;the dumping temperature was lowered by 30-50°C by the addition of calcium ferrite pellets during the double slag process to prevent phosphorus in the slag from returning to the molten steel;and the bottom-blown gas flow was increased during the blowing process.For 40 heats of comparative experiments,the rate of dephosphorization reached 91% and ranged between 87% and 95%;the phosphorus,sulfur,manganese,and oxygen contents calculated according to the compositions of molten steel and slag as well as the temperature of molten steel at the end-point of the basic oxygen furnace process were similar to the equilibrium values for the reaction between the slag and the steel.Less free calcium oxide and metallic iron were present in the final slag,and the surface of the slag mineral phase was smooth,clear,and well developed,which showed that the slag exhibited better melting effects than that produced using the conventional slag process.A steady phosphorus capacity in the slag and stable dephosphorization effects were achieved.

Steel scrap melting model for a dephosphorisation basic oxygen furnace

Dephosphorisation basic oxygen furnaces (deP-BOFs) greatly differ from conventional BOFs in the melting process, especially its many limits on adding scrap. A mathematical model of the steel scrap melting process was established in MATLAB to investigate the mechanism of scrap melting in deP-BOF in terms of coupling effects of the carbon content of the molten steel, temperature, scrap preheating and converter blowing time on the melting rate and size of the steel scraps. The scrap melting rate was influenced by both the heat and mass transfer during the melting process: at 1350℃, when the carbon content was increased from 4.5 to 5.0 mass%, the scrap melting rate increased by 43%;for the carbon content of 4.5 mass%, when the temperature was increased from 1350 to 1400℃, the scrap melting rate increased by 60%. The carbonisation was found to be the restrictive step of the scrap melting process in deP-BOFs with respect to conventional ones. The scrap heating from room temperature to 800℃ reduced the crusting thickness on the scrap surface but there was no obvious influence on the melting rate. The scrap melting size in the deP-BOF was rather limited by its low melting rate and short melting time.

Kinetics and mechanism of hexavalent chromium removal by basic oxygen furnace slag

Basic oxygen furnace slag（BOFS） has the potential to remove hexavalent chromium（Cr（VI））from wastewater by a redox process due to the presence of minerals containing Fe2＋. The effects of the solution p H, initial Cr（VI） concentration, BOFS dosage, BOFS particle size, and temperature on the removal of Cr（VI） was investigated in detail through batch tests. The chemical and mineral compositions of fresh and reacted BOFS were characterized using scanning electron microscope（SEM） equipped with an energy dispersive spectrometer（EDS）system and X-ray diffractometer（XRD）. The results show that Cr（VI） in wastewater can be efficiently removed by Fe2＋released from BOFS under appropriate acidic conditions. The removal of Cr（VI） by BOFS significantly depended on the parameters mentioned above. The reaction of Cr（VI） with BOFS followed the pseudo-second-order kinetic model. Fe2＋responsible for Cr（VI） removal was primarily derived from the dissolution of Fe O and Fe3O4 in BOFS. When H2SO4 was used to adjust the solution acidity, gypsum（Ca SO4·2H2O）could be formed and become an armoring precipitate layer on the BOFS surface, hindering the release of Fe2＋and the removal of Cr（VI）. Finally, the main mechanism of Cr（VI） removal by BOFS was described using several consecutive reaction steps.

Strength Activity Index of Air Quenched Basic Oxygen Furnace Steel Slag

Air quenched basic oxygen furnace steel slag （BOF-SS） is processed at very high cooling rate, which is expected to have different cementitious properties from conventional slowly cooled BOF-SS. For this purpose, the strength activity indexes of air quenched and slowly cooled BOF-SS are investigated. The results reveal that, under the specific surface area （S） of 490 m^2/kg, the compressive strength activity index reaches 1.24 after 28 days with replacement of 15% air quenched BOF-SS and reaches 1.05 after 28 days with replacement of 20% air quenched BOF-SS and 30%granulated blast furnace slag （GBFS）. The cementitious activity of air quenched BOF-SS is obviously higher than that of slowly cooled BOF-SS, mainly because it contains more C3 S and glassy phases.

End-point dynamic control of basic oxygen furnace steelmaking based on improved unconstrained twin support vector regression

In order to improve the end-point hit rate of basic oxygen furnace steelmaking,a novel dynamic control model was proposed based on an improved twin support vector regression algorithm.The controlled objects were the end-point carbon content and temperature.The proposed control model was established by using the low carbon steel samples collected from a steel plant,which consists of two prediction models,a preprocess model,two regulation units,a controller and a basic oxygen furnace.The test results of 100 heats show that the prediction models can achieve a double hit rate of 90%within the error bound of 0.005 wt.%C and 15℃.The preprocess model was used to predict an initial end-blow oxygen volume.However,the double hit rate of the carbon con tent and temperature only achieves 65%.Then,the oxygen volume and coolant additi ons were adjusted by the regulation units to improve the hit rate.Finally,the double hit rate after the regulation is reached up to 90%.The results indicate that the proposed dynamic control model is efficient to guide the real production for low carbon steel,and the modeling method is also suitable for the applications of other steel grades.

Memetic algorithms-based neural network learning for basic oxygen furnace endpoint prediction

Based on the critical position of the endpoint quality prediction for basic oxygen furnaces （BOFs） in steelmaking, and the latest results in computational intelligence （C1）, this paper deals with the development of a novel memetic algorithm （MA） for neural network （NN） lcarnmg. Included in this is the integration of extremal optimization （EO） and Levenberg-Marquardt （LM） pradicnt search, and its application in BOF endpoint quality prediction. The fundamental analysis reveals that the proposed EO-LM algorithm may provide superior performance in generalization, computation efficiency, and avoid local minima, compared to traditional NN learning methods. Experimental results with production-scale BOF data show that the proposed method can effectively improve the NN model for BOF endpoint quality prediction.

Thermal and chemical analysis of massive use of hot briquetted iron inside basic oxygen furnace

The integrated steelmaking cycle based on the blast furnace-basic oxygen furnace（BOF）route plays an important role in the production of plain and ultra-low carbon steel,especially for deep drawing operations.BOF steelmaking is based on the conversion of cast iron in steel by impinging oxygen on the metal bath at supersonic speed.In order to avoid the addition of detrimental chemical elements owing to the introduction of uncontrolled scrap and in order to decrease environmental impact caused by the intensive use of coke for the production of cast iron,HBI（hot briquetted iron）can be used as a source of metal and a fraction of cast iron.Forty industrial experimental tests were performed to evaluate the viability of the use of HBI in BOF.The experimental campaign was supported by a thermal prediction model and realized through the estimation of the oxidation enthalpy.Furthermore,the process was thermodynamically analyzed based on oxygen potentials using the off-gas composition and the bath temperature evolution during the conversion as reference data.