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.

State of the art in applications of machine learning in steelmaking process modeling

With the development of automation and informatization in the steelmaking industry,the human brain gradually fails to cope with an increasing amount of data generated during the steelmaking process.Machine learning technology provides a new method other than production experience and metallurgical principles in dealing with large amounts of data.The application of machine learning in the steelmaking process has become a research hotspot in recent years.This paper provides an overview of the applications of machine learning in the steelmaking process modeling involving hot metal pretreatment,primary steelmaking,secondary refining,and some other aspects.The three most frequently used machine learning algorithms in steelmaking process modeling are the artificial neural network,support vector machine,and case-based reasoning,demonstrating proportions of 56%,14%,and 10%,respectively.Collected data in the steelmaking plants are frequently faulty.Thus,data processing,especially data cleaning,is crucially important to the performance of machine learning models.The detection of variable importance can be used to optimize the process parameters and guide production.Machine learning is used in hot metal pretreatment modeling mainly for endpoint S content prediction.The predictions of the endpoints of element compositions and the process parameters are widely investigated in primary steelmaking.Machine learning is used in secondary refining modeling mainly for ladle furnaces,Ruhrstahl–Heraeus,vacuum degassing,argon oxygen decarburization,and vacuum oxygen decarburization processes.Further development of machine learning in the steelmaking process modeling can be realized through additional efforts in the construction of the data platform,the industrial transformation of the research achievements to the practical steelmaking process,and the improvement of the universality of the machine learning models.

Nucleation and growth control for iron-and phosphorus-rich phases from a modified steelmaking waste slag

Recovering the iron(Fe)and phosphorus(P)contained in steelmaking slags not only reduces the environmental burden caused by the accumulated slag,but also is the way to develop a circular economy and achieve sustainable development in the steel industry.We had pre-viously found the possibility of recovering Fe and P resources,i.e.,magnetite(Fe_(3)O_(4)) and calcium phosphate(Ca_(10)P_(6)O_(25)),contained in steel-making slags by adjusting oxygen partial pressure and adding modifier B_(2)O_(3).As a fundamental study for efficiently recovering Fe and P from steelmaking slag,in this study,the crystallization behavior of the CaO-SiO_(2)-FeO-P_(2)O_(5)-B_(2)O_(3) melt has been observed in situ,using a confocal scanning laser microscope(CLSM).The kinetics of nucleation and growth of Fe-and P-rich phases have been calculated using a classical crys-tallization kinetic theory.During cooling,a Fe_(3)O_(4) phase with faceted morphology was observed as the 1st precipitated phase in the isothermal interval of 1300-1150℃,while Ca_(10)P_(6)O_(25),with rod-shaped morphology,was found to be the 2nd phase to precipitate in the interval of 1150-1000℃.The crystallization abilities of Fe_(3)O_(4) and Ca_(10)P_(6)O_(25) phases in the CaO-SiO_(2)-FeO-P_(2)O_(5)-B_(2)O_(3) melt were quantified with the in-dex of(T_(U)−T_(I))/T_(I)(where T_(I) represents the peak temperature of the nucleation rate and TU stands for that of growth rate),and the crystalliza-tion ability of Fe_(3)O_(4) was found to be larger than that of Ca_(10)P_(6)O_(25) phase.The range of crystallization temperature for Fe_(3)O_(4) and Ca_(10)P_(6)O_(25) phases was optimized subsequently.The Fe_(3)O_(4) and Ca_(10)P_(6)O_(25) phases are the potential sources for ferrous feedstock and phosphate fertilizer,respectively.

Intelligent optimization method for the dynamic scheduling of hot metal ladles of one-ladle technology on ironmaking and steelmaking interface in steel plants

The one-ladle technology requires an efficient ironmaking and steelmaking interface. The scheduling of the hot metal ladle in the steel plant determines the overall operational efficiency of the interface. Considering the strong uncertainties of real-world production environments, this work studies the dynamic scheduling problem of hot metal ladles and develops a data-driven three-layer approach to solve this problem. A dynamic scheduling optimization model of the hot metal ladle operation with a minimum average turnover time as the optimization objective is also constructed. Furthermore, the intelligent perception of industrial scenes and autonomous identification of disturbances, adaptive configuration of dynamic scheduling strategies, and real-time adjustment of schedules can be realized. The upper layer generates a demand-oriented prescheduling scheme for hot metal ladles. The middle layer adaptively adjusts this scheme to obtain an executable schedule according to the actual supply–demand relationship. In the lower layer, three types of dynamic scheduling strategies are designed according to the characteristics of the dynamic disturbance in the model:real-time flexible fine-tuning, local machine adjustment, and global rescheduling. Case test using 24 h production data on a certain day during the system operation of a steel plant shows that the method and system can effectively reduce the fluctuation and operation time of the hot metal ladle and improve the stability of the ironmaking and steelmaking interface production rhythm. The data-driven dynamic scheduling strategy is feasible and effective, and the proposed method can improve the operation efficiency of hot metal ladles.

Decarbonization options of the iron and steelmaking industry based on a three-dimensional analysis

Decarbonization is a critical issue for peaking CO_(2) emissions of energy-intensive industries,such as the iron and steel industry.The decarbonization options of China’s ironmaking and steelmaking sector were discussed based on a systematic three-dimensional low-carbon analysis from the aspects of resource utilization(Y),energy utilization(Q),and energy cleanliness which is evaluated by a process general emission factor(PGEF)on all the related processes,including the current blast furnace(BF)-basic oxygen furnace(BOF)integrated process and the specific sub-processes,as well as the electric arc furnace(EAF)process,typical direct reduction(DR)process,and smelting reduction(SR)process.The study indicates that the three-dimensional aspects,particularly the energy structure,should be comprehensively considered to quantitatively evaluate the decarbonization road map based on novel technologies or processes.Promoting scrap utilization(improvement of Y)and the substitution of carbon-based energy(improvement of PGEF)in particular is critical.In terms of process scale,promoting the development of the scrap-based EAF or DR-EAF process is highly encouraged because of their lower PGEF.The three-dimensional method is expected to extend to other processes or industries,such as the cement production and thermal electricity generation industries.

Phosphate enrichment mechanism in CaO–SiO_2–FeO–Fe_2O_3–P_2O_5 steelmaking slags with lower binary basicity

The addition of silica to steelmaking slags to decrease the binary basicity can promote phosphate enrichment in quenched slag samples. In this study, we experimentally investigated phosphate enrichment behavior in CaO-SiO2-FeO-Fe203-P205 slags with a P205 content of 5.00% and the binary basicity B ranging from 1.0 to 2.0, where the （%Fe/O）/（%CaO） mass percentage ratio was maintained at 0.955. The experimental results are explained by the defined enrichment degree c, of solid solution 2CaO·SiO2-3CaO·P205 （C2S-C3P）, where R_C2S-C3P is a component of the developed ion and molecule coexistence theory （IMCT）-Ni model for calculating the mass action concentrations Ni of structural units in the slags on the basis of the IMCT. The asymmetrically inverse V-shaped relation be- tween phosphate enrichment and binary basicity B was observed to be correlated in the slags under applied two-stage cooling conditions. The maximum content of PROs in the C2S-C3P solid solution reached approximately 30.0% when the binary basicity B was controlled at 1.3.

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.

Thermodynamic calculation on the smelting slag of direct recycling of electric arc furnace stainless steelmaking dust

Thermodynamic calculation on the smelting slag of direct recycling of electric arc furnace stainless steelmaking dust was presented. An induction furnace was used to simulate electric arc furnace smelting to recover the metals from the dust. The elements of iron, chromium and nickel in the ingot and the components of metal oxides in the slag were analyzed. The thermodynamic model for FeO Cr 2O 3 MgO SiO 2 slag was set up and the active concentrations of substances in the slag at 1 550 ℃ were determined by thermodynamic calculation according to the experimental data. The results show that the apparent equilibrium constant and quantitative distribution of chromium between slag and steel are unstable and affected by the mass ratios of pellets to start iron and metal reducing agent to the pellets. In order to get satisfactory chromium recovery from the direct recycling of electric arc furnace stainless steelmaking dust, it is important to ensure the mass ratio of pellets to the steel below 0.20 and the mass ratio of metal reducing agent to pellets over 0.18 in practical smelting runs.

Recycling of ironmaking and steelmaking slags in Japan and China

The mass production of steel is inevitably accompanied by large quantities of slags.The treatment of ironmaking and steelmaking slags is a great challenge in the sustainable development of the steel industry.Japan and China are two major steel producing countries that have placed a large emphasis on developing new technologies to decrease slag emission or promote slag valorization.Slags are almost completely reused or recycled in Japan.However,due to stagnant infrastructural investments,future applications of slags in conventional sectors are expected to be difficult.Exploring new functions or applications of slags has become a research priority in Japan.For example,the utilization of steelmaking slags in offshore seabeds to create marine forests is under development.China is the top steel producer in the world.The utilization ratios of ironmaking and steelmaking slags have risen steadily in recent years,driven largely by technological advances.For example,hot stage processing of slags for materials as well as heat recovery techniques has been widely applied in steel plants with good results.However,increasing the utilization ratio of basic oxygen furnace slags remains a major challenge.Technological innovations in slag recycling are crucial for the steel industries in Japan and China.Here,the current status and developing trends of utilization technologies of slags in both countries are reviewed.

Thermo-analytical study on stainless steelmaking dust

Thermo-gravimetric analyzer (TGA) was used to determine the thermal behavior of stainless steelmaking dust and FTIR was used to detect the components of off-gas. The TGA results indicate that three mass loss/gain stages exist in the thermal process. The mass loss of the dust in the first stage results from the evaporation of moisture and the reaction between dissociated carbon and metal oxides in the dust. The evaporation of moisture within the dust happens at 90-350 ℃ and the formation of carbon dioxide happens at 250-470 ℃. The mass gain of the dust in the second stage results from the oxidation of metals in the dust by the oxygen at 470-950 ℃. The third stage is a slow mass loss process, and some metals in the dust are evaporated into the atmosphere in this stage. The evaporation of metals is carried out mainly at 900-1 200 ℃ and the dust is sintered at high temperature over 1 200 ℃.

A review of carbon dioxide disposal technology in the converter steelmaking process

In last decade,the utilization of CO?resources in steelmaking has achieved certain metallurgical effects and the technology is maturing.In this review,we summarized the basic reaction theory of CO2,the CO2 conversion,and the change of energy-consumption when CO2 was introduced in converter steelmaking process.In the CO2-O2 mixed injection(COMI)process,the CO2 conversion ratio can be obtained as high as 80%or more with a control of the CO2 ratio in mixture gas and the flow rate of CO2,and the energy is saving and even the energy consumption can be reduced by 145.65 MJ/t under certain operations.In addition,a complete route of CO2 disposal technology is proposed combining the comparatively mature technologies of CO2 capture,CO2 compression,and liquid CO2 storage to improve the technology of CO2 utilization.The results are expected to form a large-scale,highly efficient,and valuable method to dispose of CO2.

Quantitative evaluation of multi-process collaborative operation in steelmaking–continuous casting sections

The quantitative evaluation of multi-process collaborative operation is of great significance for the improvement of production planning and scheduling in steelmaking–continuous casting sections(SCCSs). However, this evaluation is difficult since it relies on an in-depth understanding of the operating mechanism of SCCSs, and few existing methods can be used to conduct the evaluation, due to the lack of full-scale consideration of the multiple factors related to the production operation. In this study, three quantitative models were developed, and the multiprocess collaborative operation level was evaluated through the laminar-flow operation degree, the process matching degree, and the scheduling strategy availability degree. Based on the evaluation models for the laminar-flow operation and process matching levels, this study investigated the production status of two steelmaking plants, plants A and B, based on actual production data. The average laminar-flow operation(process matching) degrees of SCCSs were obtained as 0.638(0.610) and 1.000(0.759) for plants A and B, respectively, for the period of April to July 2019. Then, a scheduling strategy based on the optimization of the furnace-caster coordinating mode was suggested for plant A. Simulation experiments showed higher availability than the greedy-based and manual strategies. After the proposed scheduling strategy was applied,the average process matching degree of the SCCS of plant A increased by 4.6% for the period of September to November 2019. The multi-process collaborative operation level was improved with fewer adjustments and interruptions in casting.

Phylogeny of Bacteria from Steelmaking Wastes and Their Acidic Enrichment Cultures

Currently, millions of tons of steel are produced worldwide. This has become a serious economic and environmental challenge because the ores used for steel production are nonrenewable resources and the production generates huge amount of waste. In this study, we identified and investigated the ability of bacteria from steelmaking waste with low and high zinc concentration to promote leaching of zinc, when enriched by acidic (pH 2) culture conditions. The bioleaching assays indicated removal of Zn, as in chemical leaching. Bacterial communities from crude and enrichment culture wastes were characterized by the 16S rRNA gene. Phylogenetic analysis of the generated clone libraries revealed predominance of Proteobacteria and Firmicutes. The Actino- bacteria, Bacteroidetes, Cyanobacteria, and Deinococcus-Thermus phyla were also encountered. The clones were most closely related to cultivable heterotrophic bacteria. Different genera were identified including iron redox cycling and leaching bacteria such as Chromobacterium, Aeromonas, Escherichia, Bacillus, and Ochrobactrum. These data add significant new information on bacteria which survive in extremely acidic conditions. They are distantly related to typical acidophiles responsible for the leaching process, which makes them good candidates for future studies on metal bioleaching.

A Compound Cycle for Power Generation by Utilizing Residual Heat of Flue Gas in Electric Steelmaking Process

Electric furnace short process steelmaking is one of the most important steelmaking methods in the world today, and the waste heat recovery potential of electric furnace flue gas is huge.?The research on the recovery of electric furnace flue gas waste heat is of great significance. In order to make better use of this part of the heat,?in this paper, a compound cycle of nitrogen Brayton cycle as a first-order cycle and toluene transcritical Rankine cycle as a second-order cycle is proposed to recover waste heat from furnace flue gas in steelmaking process for power generation. A mathematical model was established with the net output power as the objective function and the initial expansion pressure, the final expansion pressure, the initial expansion temperature and the initial pressure of the second cycle as the independent variables. The effect of multivariate on the net output power of the waste heat power generation cycle is studied, and then, the optimal parameters of the compound cycle are determined. The results show that under the general electric furnace steelmaking process, the power generation efficiency of this new cycle can be increased by 21.02% compared with the conventional cycle.

Thermal solidification of stainless steelmaking dust

Stainless steelmaking dust makes an environmental problem in the disposal or landfills and has been assigned as a hazardous waste by various government regulatory agencies because it leaches heavy metals to the groundwater or rainwater in the concentrations exceeding the environmental guidelines for solid waste disposal.Solidification of the dust is to stabilize the hazardous components into amorphous silica-alumina-based clays.Various mixtures of stainless steelmaking dust and clay were investigated and the softening temperatures of these mixtures were measured.The results indicate that the mixture of stainless steelmaking dust and clay additive with 1:1 ratio has the lowest softening temperature of 1 100 ℃.The clinkers can pass the TCLP leaching test after being thermally treated at the softening temperature for 15 min.A thermal process for the solidification of stainless steelmaking dust with typical clay is developed and the product is desirable for the production of bricks or disposal and landfill.

FactSage Thermodynamic Database for Steelmaking Refractory Research

Thermodynamic databases are very useful to analyze the complex chemical reactions happening in high temperature material processes. An accurate thermodynamic database based on physically sound thermodynamic models can provide thermodynamic calculations of useful phase diagrams and comprehensive chemical reactions related to refractory corrosion in steelmaking processes. In this study,the FactS age thermodynamic database,one of the most comprehensive thermodynamic databases for oxide systems among other commercial software,is reviewed in particular for the steelmaking refractory research,and several applications to refractory corrosion are presented.

An improved cross entropy algorithm for steelmaking-continuous casting production scheduling with complicated technological routes

In order to increase productivity and reduce energy consumption of steelmaking-continuous casting(SCC) production process, especially with complicated technological routes, the cross entropy(CE) method was adopted to optimize the SCC production scheduling(SCCPS) problem. Based on the CE method, a matrix encoding scheme was proposed and a backward decoding method was used to generate a reasonable schedule. To describe the distribution of the solution space, a probability distribution model was built and used to generate individuals. In addition, the probability updating mechanism of the probability distribution model was proposed which helps to find the optimal individual gradually. Because of the poor stability and premature convergence of the standard cross entropy(SCE) algorithm, the improved cross entropy(ICE) algorithm was proposed with the following improvements: individual generation mechanism combined with heuristic rules, retention mechanism of the optimal individual, local search mechanism and dynamic parameters of the algorithm. Simulation experiments validate that the CE method is effective in solving the SCCPS problem with complicated technological routes and the ICE algorithm proposed has superior performance to the SCE algorithm and the genetic algorithm(GA).

An improved artificial bee colony algorithm for steelmaking–refining–continuous casting scheduling problem

Steelmaking–refining–Continuous Casting(SCC) scheduling is a worldwide problem, which is NP-hard. Effective SCC scheduling algorithms can help to enhance productivity, and thus make significant monetary savings. This paper develops an Improved Artificial Bee Colony(IABC) algorithm for the SCC scheduling. In the proposed IABC, charge permutation is employed to represent the solutions. In the population initialization, several solutions with certain quality are produced by a heuristic while others are generated randomly. Two variable neighborhood search neighborhood operators are devised to generate new high-quality solutions for the employed bee and onlooker bee phases, respectively. Meanwhile, in order to enhance the exploitation ability, a control parameter is introduced to conduct the search of onlooker bee phase. Moreover, to enhance the exploration ability,the new generated solutions are accepted with a control acceptance criterion. In the scout bee phase, the solution corresponding to a scout bee is updated by performing three swap operators and three insert operators with equal probability. Computational comparisons against several recent algorithms and a state-of-the-art SCC scheduling algorithm have demonstrated the strength and superiority of the IABC.

A novel Lagrangian relaxation level approach for scheduling steelmaking-refining-continuous casting production

A Lagrangian relaxation(LR) approach was presented which is with machine capacity relaxation and operation precedence relaxation for solving a flexible job shop(FJS) scheduling problem from the steelmaking-refining-continuous casting process. Unlike the full optimization of LR problems in traditional LR approaches, the machine capacity relaxation is optimized asymptotically, while the precedence relaxation is optimized approximately due to the NP-hard nature of its LR problem. Because the standard subgradient algorithm(SSA) cannot solve the Lagrangian dual(LD) problem within the partial optimization of LR problem, an effective deflected-conditional approximate subgradient level algorithm(DCASLA) was developed, named as Lagrangian relaxation level approach. The efficiency of the DCASLA is enhanced by a deflected-conditional epsilon-subgradient to weaken the possible zigzagging phenomena. Computational results and comparisons show that the proposed methods improve significantly the efficiency of the LR approach and the DCASLA adopting capacity relaxation strategy performs best among eight methods in terms of solution quality and running time.