Process metallurgy and data-driven prediction and feedback of blast furnace heat indicators

The prediction and control of furnace heat indicators are of great importance for improving the heat levels and conditions of the complex and difficult-to-operate hour-class delay blast furnace(BF)system.In this work,a prediction and feedback model of furnace heat indicators based on the fusion of data-driven and BF ironmaking processes was proposed.The data on raw and fuel materials,process op-eration,smelting state,and slag and iron discharge during the whole BF process comprised 171 variables with 9223 groups of data and were comprehensively analyzed.A novel method for the delay analysis of furnace heat indicators was established.The extracted delay variables were found to play an important role in modeling.The method that combined the genetic algorithm and stacking efficiently im-proved performance compared with the traditional machine learning algorithm in improving the hit ratio of the furnace heat prediction model.The hit ratio for predicting the temperature of hot metal in the error range of±10℃ was 92.4%,and that for the chemical heat of hot metal in the error range of±0.1wt%was 93.3%.On the basis of the furnace heat prediction model and expert experience,a feedback model of furnace heat operation was established to obtain quantitative operation suggestions for stabilizing BF heat levels.These sugges-tions were highly accepted by BF operators.Finally,the comprehensive and dynamic model proposed in this work was successfully ap-plied in a practical BF system.It improved the BF temperature level remarkably,increasing the furnace temperature stability rate from 54.9%to 84.9%.This improvement achieved considerable economic benefits.

Coke behavior with H_(2)O in a hydrogen-enriched blast furnace:A review

Hydrogen-enriched blast furnace ironmaking has become an essential route to reduce CO_(2)emissions in the ironmaking process.However,hydrogen-enriched reduction produces large amounts of H_(2)O,which places new demands on coke quality in a blast furnace.In a hydrogen-rich blast furnace,the presence of H_(2)O promotes the solution loss reaction.This result improves the reactivity of coke,which is 20%-30%higher in a pure H_(2)O atmosphere than in a pure CO_(2)atmosphere.The activation energy range is 110-300 kJ/mol between coke and CO_(2)and 80-170 kJ/mol between coke and H_(2)O.CO_(2)and H_(2)O are shown to have different effects on coke degradation mechanisms.This review provides a comprehensive overview of the effect of H_(2)O on the structure and properties of coke.By exploring the interactions between H_(2)O and coke,several unresolved issues in the field requiring further research were identified.This review aims to provide valuable insights into coke behavior in hydrogen-rich environments and promote the further development of hydrogen-rich blast furnace ironmaking processes.

Extraction of Valuable Metals from Titanium-bearing Blast Furnace Slag by Acid Leaching

To realize the resource utilization of the valuable metals in the titanium-containing blast furnace slag,the process route of “hydrochloric acid leaching-electrolysis-carbonization and carbon dioxide capture-preparation of calcium carbonate” was proposed.In this study,the influences of process conditions on the leaching rates of calcium,magnesium,aluminum,and iron and the phases of the leaching residue were investigated for the leaching process.The experimental results show that the HCl solution could selectively leach the elements from the titanium-containing blast furnace slag.The better leaching conditions are the HCl solution concentration of 4 mol/L,the leaching time of 30 min,the ratio of liquid volume to solid gas of 10 mL/g,and the stirring paddle speed of 300 r/min.Under the conditions,the leaching rates of calcium,magnesium,aluminum,and iron can reach 85.87%,73.41%,81.35%,and 59.08%,and the leaching rate of titanium is 10.71%.The iron and the aluminum are removed from the leachate to obtain iron-aluminum water purification agents,and the magnesium is removed from the leachate to obtain magnesium hydroxide.The leaching residue phase is dominated by perovskite,followed by magnesium silicate and tricalcium aluminate,and the titaniumrich material could be obtained from the leaching residue by desiliconization.

Numerical investigation of sinusoidal pulsating gas intake to intensify the gas-slag momentum transfer in the top-blown smelting furnace

The variation characteristics of bubble morphology and the thermal-physical properties of bubble boundary in the top-blown smelting furnace were explored by means of the computational fluid dynamics method.The essential aspects of the fluid phase(e.g.,splashing volume,dead zone of copper slag,and gas penetration depth)were explored together with the effect of sinusoidal pulsating gas intake on the momentum-transfer performance between phases.The results illustrated that two relatively larger vortices and two smaller vortices appear in the bubble waist and below the lance,respectively.The expansion of larger ones as well as the shrinking of smaller ones combine to cause the contraction of the bubble waist.Compared to the results of the case with a fixed gas injection velocity(V_(g)=58 m/s),the splashing volume and dead zone volume of the slag under the V_(g)=58+10sin(2πt)condition are reduced by 24.9%and 23.5%,respectively,where t represents the instant time.Gas penetration depth and slag motion velocity of the latter are 1.03 and 1.31 times high-er than those of the former,respectively.

Cross-upgrading of biomass hydrothermal carbonization and pyrolysis for high quality blast furnace injection fuel production:Physicochemical characteristics and gasification kinetics analysis

The paper proposes a biomass cross-upgrading process that combines hydrothermal carbonization and pyrolysis to produce high-quality blast furnace injection fuel.The results showed that after upgrading,the volatile content of biochar ranged from 16.19%to 45.35%,and the alkali metal content,ash content,and specific surface area were significantly reduced.The optimal route for biochar pro-duction is hydrothermal carbonization-pyrolysis(P-HC),resulting in biochar with a higher calorific value,C=C structure,and increased graphitization degree.The apparent activation energy(E)of the sample ranges from 199.1 to 324.8 kJ/mol,with P-HC having an E of 277.8 kJ/mol,lower than that of raw biomass,primary biochar,and anthracite.This makes P-HC more suitable for blast furnace injection fuel.Additionally,the paper proposes a path for P-HC injection in blast furnaces and calculates potential environmental benefits.P-HC of-fers the highest potential for carbon emission reduction,capable of reducing emissions by 96.04 kg/t when replacing 40wt%coal injec-tion.

A Novel Sensing Imaging Equipment Under Extremely Dim Light for Blast Furnace Burden Surface:Starlight High-Temperature Industrial Endoscope

Blast furnace(BF)burden surface contains the most abundant,intuitive and credible smelting information and acquiring high-definition and high-brightness optical images of which is essential to realize precise material charging control,optimize gas flow distribution and improve ironmaking efficiency.It has been challengeable to obtain high-quality optical burden surface images under high-temperature,high-dust,and extremelydim(less than 0.001 Lux)environment.Based on a novel endoscopic sensing detection idea,a reverse telephoto structure starlight imaging system with large field of view and large aperture is designed.Combined with a water-air dual cooling intelligent self-maintenance protection device and the imaging system,a starlight high-temperature industrial endoscope is developed to obtain clear optical burden surface images stably under the harsh environment.Based on an endoscope imaging area model,a material flow trajectory model and a gas-dust coupling distribution model,an optimal installation position and posture configuration method for the endoscope is proposed,which maximizes the effective imaging area and ensures large-area,safe and stable imaging of the device in a confined space.Industrial experiments and applications indicate that the proposed method obtains clear and reliable large-area optical burden surface images and reveals new BF conditions,providing key data support for green iron smelting.

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.

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.

Production Practice of Solid Waste Desulfurizer Disposal in European Metallurgical Furnace

In order to realize the OY Smelting Furnace disposal of solid waste,municipal waste,form a model of steel enterprises and urban integration,through the production practice of smelting furnace,analyzes the mechanism of solid waste disposal,and proposed the disposal of solid waste desulfurization agent and disposal method:According to the theory to guide the actual production process,the test ton of iron with 10-15kg of desulfurizer in the production process does not affect the quality of molten iron and slag quality.

Analysis and Prospect of Waste Heat Utilization from Blast Furnace Slag Flushing

Estimating the residual heat of blast furnace slag flushing in China,classifying and introducing the current proposed methods of slag flushing waste heat utilization,and listing existing cases.In order to better save energy and water in the slag flushing process of blast furnaces,an ideal comprehensive cascade utilization system scheme for annual recovery of waste heat is proposed.Based on the measured waste heat data of a steel plant,design calculations are carried out to further analyze the economic feasibility of the new scheme and provide reference for its promotion and application.

ZG-12超低磷钢90 t BOF-RH-CC工艺的生产实践

对钢厂采用90 t转炉冶炼超低磷钢(%/:<0.03C,<0.010P,<0.015S,<0.06Mn,<0.02Cr,<0.02Ni),转炉终点钢液温度偏低、过氧化严重,需经过LF升温精炼等问题,进行了工艺优化试验研究,结果表明:转炉(0.018%~0.025%P)出钢过程中使用石灰和精炼渣,形成二元碱度为7、<0.5%P_(2)O_(5)炉渣,可使钢包钢水脱磷率达到75%,成品磷含量低于0.010%,冶炼时间缩短3~4 min。同时,转炉吹炼终点钢液温度升高,钢包脱磷率呈降低趋势,转炉最佳终点温度为1630~1655℃。通过采用钢包精炼脱磷技术,超低磷钢冶炼流程缩短为转炉吹炼→RH处理→连铸,减少LF精炼工序。

基于BoF和迹变换多特征融合的图像纹理分类研究

针对BoF模型缺少几何特征、结构特征的表达,对纹理图像特征描述不充分等问题,提出一种基于BoF和迹变换多特征融合的图像纹理分类方法。首先通过关键点检测的方法获取纹理图像的碎片化图像,然后提取碎片化图像的迹变换特征和SIFT特征,通过特征交叉编码的方式和动态鉴别能量的方法,获取迹变换特征和SIFT特征的融合特征并进行特征单词优选,再以BoF模型进行特征编码,最后输入到支持向量机(SVM)中进行训练、预测和分类。实验在OutexTC10/TC12000和KTHTIPS纹理数据集上分别取得了100%、99.87%和97.6%的识别精度,结果表明该设计方法对具有几何特征、结构特征的纹理图像可以获得较好的分类效果,有效地提高了纹理分类的识别性能。

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.

Synthesis,Characterization of NaA Zeolite from Blast Furnace Slag(BFS)via Alkaline Fusion and Hydrothermal Treatment

A blast furnace slag zeolite(BFSZ)material was successfully synthesized from BFS by alkaline fusion and hydrothermal treatment.Via the analyses of XRD,FT-IR,FE-SEM,XRF,CEC and BET surface area measurement,when zeolite was synthesized at a crystallization temperature of 100℃with initial Si/Al ratio of 1:1,the main composition in the product is Na-A zeolite.Under the above conditions,the BFSZ was synthesized with CEC of 3.06 meq/g and maximum BET surface area of 37.55 m^(2)·g^(-1).Moreover,the incorporating of BFS-derived minor metals(such as Mg,Fe,and Ca)are found to be of little importance for the synthesis of BFSZ.Thus the obtained BFSZ material has a great adsorption performance for removing Mn^(2+),Cu^(2+),and NH_(4)^(+)ions diluted in water,owing to the higher CEC.

Minimax entropy-based co-training for fault diagnosis of blast furnace

Due to the problems of few fault samples and large data fluctuations in the blast furnace(BF)ironmaking process,some transfer learning-based fault diagnosis methods are proposed.The vast majority of such methods perform distribution adaptation by reducing the distance between data distributions and applying a classifier to generate pseudo-labels for self-training.However,since the training data is dominated by labeled source domain data,such classifiers tend to be weak classifiers in the target domain.In addition,the features generated after domain adaptation are likely to be at the decision boundary,resulting in a loss of classification performance.Hence,we propose a novel method called minimax entropy-based co-training(MMEC)that adversarially optimizes a transferable fault diagnosis model for the BF.The structure of MMEC includes a dual-view feature extractor,followed by two classifiers that compute the feature's cosine similarity to representative vector of each class.Knowledge transfer is achieved by alternately increasing and decreasing the entropy of unlabeled target samples with the classifier and the feature extractor,respectively.Transfer BF fault diagnosis experiments show that our method improves accuracy by about 5%over state-of-the-art methods.

Efficient Use of Steel Slag in Alkali-Activated Blast Furnace Slag Based Geopolymer

Energy shortage and the emission of greenhouse gases have become a global problem of urgent concern.Therefore,there is an urgent need to develop a low carbon building material.Geopolymers have become a hot topic due to their environmental sustainability and the feasibility of immobilizing industrial waste.In this paper,steel slag(SS)fines were investigated as auxiliary materials of blast furnace slag(BFS)based geopolymer.The hydration heat properties,flowability,compressive strength,sorptivity coefficient,X-ray diffraction(XRD),and scanning electron microscopy(SEM)of the geopolymer pastes were determined.The results showed that the incorporation of SS weakened the reactivity of the BFS-based geopolymer paste and improved the flow values of the paste.The compressive strength of the geopolymer with 20%SS content reached 117 MPa at 28 d.The geopolymer specimens with high compressive strength showed a low sorptivity coefficient.The microscopic results showed that the addition of the appropriate amount of SS reduced the cracks,improved the density of the geopolymer,and produced a geopolymer composite with excellent mechanical properties.

Post-mortem Microstructural Study of Aluminous Refractory Brick Used in Channels of Blast Furnaces

Aluminous refractory materials with high alumina contents are widely used in the steel industry,and the higher the alumina content,the higher the working temperature.Properties such as high refractoriness and thermal shock resistance lead these refractory materials to be used as channel linings of blast furnaces,where they are exposed to the attack by slag,molten steel,working cycles and sudden temperature changes between 25℃(room temperature)and 1520℃(the temperature of molten pig iron).In this work,microstructural changes in post-mortem aluminous refractory bricks were investigated by apparent porosity,X-ray diffraction analysis(XRD),Fourier transform infrared spectroscopy(FTIR),scanning electron microscopy,and X-ray dispersion energy spectrometry(SEM/EDS).The results showed an increase in the apparent porosity and the bulk density and the presence of the phases mullite,sillimanite,alumina,and quartz in the post-mortem brick.Calcium and magnesium were not detected in the microstructure of the post-mortem brick,indicating that slags did not corrode these refractory materials.Therefore,the microstructural changes that occurred in the post-mortem bricks must be due to thermal cycling.In the X-ray diffraction(XRD)test,mullite,sillimanite,quartz,andα-alumina phases were identified.These results indicate that the aluminous refractory was obtained from sillimanite.In infrared spectroscopy(FTIR)it was possible to identify the vibration bands referring to the Si-O and Al-O bonds.The increase in the porosity is a result of cracks caused by work cycles at high temperatures and the temperature gradient to which the refractory was subjected during use.Through the micrograph it was possible to identify the presence of acicular mullite.The absence of magnesium and calcium in the microanalysis results by energy dispersed X-ray spectrometry(EDS)indicates that there was no infiltration by slag or liquid iron.These results indicate that the microstructural changes that occurred in the post-mortem aluminous refractory were of a thermal nature.

CLOF Based Outlier Detection Algorithm of Temperature Data for Ethylene Cracking Furnace

The flue temperature is one of the important indicators to characterize the combustion state of an ethylene cracker furnace,the outliers of temperature data can lead to the false alarm.Conventional outlier detection algorithms such as the Isolation Forest algorithm and 3-sigma principle cannot detect the outliers accurately.In order to improve the detection accuracy and reduce the computational complexity,an outlier detection algorithm for flue temperature data based on the CLOF(Clipping Local Outlier Factor,CLOF)algorithm is proposed.The algorithm preprocesses the normalized data using the cluster pruning algorithm,and realizes the high accuracy and high efficiency outlier detection in the outliers candidate set.Using the flue temperature data of an ethylene cracking furnace in a petrochemical plant,the main parameters of the CLOF algorithm are selected according to the experimental results,and the outlier detection effect of the Isolation Forest algorithm,the 3-sigma principle,the conventional LOF algorithm and the CLOF algorithm are compared and analyzed.The results show that the appropriate clipping coefficient in the CLOF algorithm can significantly improve the detection efficiency and detection accuracy.Compared with the outlier detection results of the Isolation Forest algorithm and 3-sigma principle,the accuracy of the CLOF detection results is increased,and the amount of data calculation is significantly reduced.

基于BOF的数据结构教学模式探索

基于BLOOM和OBE的原理,结合翻转课堂的优势,提出基于BOF的数据结构教学模式,以“二叉树的遍历”为例介绍该模式实施过程,通过课堂教学效果、学习成绩、学习态度、学生认可度等多元化评价说明实施效果。

Development and Application of Multi-phase Nitrides Bonded Silicon Carbide Lintel Blocks for Dry Quenching Furnaces

Multi-phase nitrides bonded silicon carbide lintel blocks were prepared using industrial SiC(SiC≥98 mass%,3-0.5,≤0.5 and≤0.044 mm),Si powder(Si≥98 mass%,≤0.044 mm),and SiO2 micropowder(SiO2≥96 mass%,d50=0.15 pm)as raw materials,and calcium lignosulfonate as the additive,batching,mixing,and molding on a vibration pressure molding machine,drying and then firing at 1420℃for 10 h in high-purity N2.The apparent porosity,the bulk density,the cold modulus of rupture,the hot modulus of rupture,and the linear expansion coefficient of the samples were tested.The phase composition and the microstructure of the samples at different nitriding depths(50,100,and 150 mm)were analyzed by XRD and SEM.The field application effects of the blocks were studied.The results show that:(1)the multi-phase nitrides bonded silicon carbide refractories can dynamically adjust their own phase composition and minimize structural and thermal stresses,improving the service life of key parts of dry quenching furnaces;(2)calcium lignosulfonate can improve the nitriding micro-environment of multi-phase nitrides bonded silicon carbide lintel blocks,successfully increasing the effective nitriding thickness of the blocks to 300 mm;(3)Sinosteel LI RR provides a unique concept in the design of materials and block types as well as the stable and scientific overall structure,promoting the industrialization process of dry quenching furnaces with long service life in China.