Prediction and optimization of flue pressure in sintering process based on SHAP

Sinter is the core raw material for blast furnaces.Flue pressure,which is an important state parameter,affects sinter quality.In this paper,flue pressure prediction and optimization were studied based on the shapley additive explanation(SHAP)to predict the flue pressure and take targeted adjustment measures.First,the sintering process data were collected and processed.A flue pressure prediction model was then constructed after comparing different feature selection methods and model algorithms using SHAP+extremely random-ized trees(ET).The prediction accuracy of the model within the error range of±0.25 kPa was 92.63%.SHAP analysis was employed to improve the interpretability of the prediction model.The effects of various sintering operation parameters on flue pressure,the relation-ship between the numerical range of key operation parameters and flue pressure,the effect of operation parameter combinations on flue pressure,and the prediction process of the flue pressure prediction model on a single sample were analyzed.A flue pressure optimization module was also constructed and analyzed when the prediction satisfied the judgment conditions.The operating parameter combination was then pushed.The flue pressure was increased by 5.87%during the verification process,achieving a good optimization effect.

Effect of titanium on the sticking of pellets based on hydrogen metallurgy shaft furnace:Behavior analysis and mechanism evolution

Direct reduction based on hydrogen metallurgical gas-based shaft furnace is a promising technology for the efficient and low-carbon smelting of vanadium-titanium magnetite.However,in this process,the sticking of pellets occurs due to the aggregation of metal-lic iron between the contact surfaces of adjacent pellets and has a serious negative effect on the continuous operation.This paper presents a detailed experimental study of the effect of TiO2 on the sticking behavior of pellets during direct reduction under different conditions.Results showed that the sticking index(SI)decreased linearly with the increasing TiO2 addition.This phenomenon can be attributed to the increase in unreduced FeTiO3 during reduction,leading to a decrease in the number and strength of metallic iron interconnections at the sticking interface.When the TiO2 addition amount was raised from 0 to 15wt%at 1100°C,the SI also increased from 0.71%to 59.91%.The connection of the slag phase could be attributed to the sticking at a low reduction temperature,corresponding to the low sticking strength.Moreover,the interconnection of metallic iron became the dominant factor,and the SI increased sharply with the increase in re-duction temperature.TiO2 had a greater effect on SI at a high reduction temperature than at a low reduction temperature.

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.

Mechanism of zinc damaging to blast furnace tuyere refractory

The phenomena of tuyere upward-warp have been found at No.6 blast furnace in Kunming Steel Company China after its blow-in, which has made a great impact on the practical production of the furnace. Thus, a number of efforts have been made to elucidate the mechanism of this phenomenon. The results of investigation and tests revealed that the enrichment and expansion of zinc in the tuyere bricks is the main factor leading to the tuyere upward-warp. The eroding behavior of zinc is that the inner structure of the tuyere bricks turns from dense to loose with entering, enriching and expanding of zinc, which forms spot-like→stripe-like→ditch-like→vein-like→tumorlike eroding passage. Additionally, it is found that the sequence of deleterious ele- ments entering the tuyere refractory is K, Na, Zn and Pb, respectively. Finally, the phenomena and process of zinc crystallization and growth in the refractory have been clearly observed and recorded during this investigation.

Direct reduction swelling behavior of pellets in hydrogen-based shaft furnaces under typical atmospheres

Hydrogen-based shaft furnace process is gaining more and more attention due to its low carbon emission, and the reduction behavior of iron bearing burdens significantly affects its operation. In this work, the effects of reduction degree, temperature, and atmosphere on the swelling behavior of pellet has been studied thoroughly under typical hydrogen metallurgy conditions. The results show that the pellets swelled rapidly in the early reduction stage, then reached a maximum reduction swelling index (RSI) at approximately 40%reduction degree. The crystalline transformation of the iron oxides during the reduction process was the main reason of pellets swelling. The RSI increased significantly with increasing temperature in the range of 850-1050℃, the maximum RSI increased from 6.66%to 25.0%in the gas composition of 100%H_(2). With the temperature increased, the pellets suffered more thermal stress resulting in an increase of the volume. The maximum RSI decreased from 19.78%to 17.35%with the volume proportion of H_(2) in the atmosphere increased from 55%to 100%at the temperature of 950℃.The metallic iron tended to precipitate in a lamellar structure rather than whiskers. Consequently, the inside of the pellets became regular, so the RSI decreased. Overall, controlling a reasonable temperature and increasing the H_(2) proportion is an effective way to decrease the RSI of pellets.

Key issues and progress of industrial big data-based intelligent blast furnace ironmaking technology

Blast furnace (BF) ironmaking is the most typical “black box” process, and its complexity and uncertainty bring forth great challenges for furnace condition judgment and BF operation. Rich data resources for BF ironmaking are available, and the rapid development of data science and intelligent technology will provide an effective means to solve the uncertainty problem in the BF ironmaking process. This work focused on the application of artificial intelligence technology in BF ironmaking. The current intelligent BF ironmaking technology was summarized and analyzed from five aspects. These aspects include BF data management, the analyses of time delay and correlation, the prediction of BF key variables, the evaluation of BF status, and the multi-objective intelligent optimization of BF operations. Solutions and suggestions were offered for the problems in the current progress, and some outlooks for future prospects and technological breakthroughs were added. To effectively improve the BF data quality, we comprehensively considered the data problems and the characteristics of algorithms and selected the data processing method scientifically. For analyzing important BF characteristics, the effect of the delay was eliminated to ensure an accurate logical relationship between the BF parameters and economic indicators. As for BF parameter prediction and BF status evaluation,a BF intelligence model that integrates data information and process mechanism was built to effectively achieve the accurate prediction of BF key indexes and the scientific evaluation of BF status. During the optimization of BF parameters, low risk, low cost, and high return were used as the optimization criteria, and while pursuing the optimization effect, the feasibility and site operation cost were considered comprehensively.This work will help increase the process operator’s overall awareness and understanding of intelligent BF technology. Additionally, combining big data technology with the process will improve the practicality of data models in actual production and promote the application of intelligent technology in BF ironmaking.

Effect mechanism of aluminum occurrence and content on the induration characteristics of iron ore pellets

With the intensified depletion of high-grade iron ores,the increased aluminum content in iron ore concentrates has become unavoidable,which is detrimental to the pelletization process.Therefore,the effect mechanism of aluminum on pellet quality must be identified.In this study,the influence of aluminum occurrence and content on the induration of hematite(H)and magnetite(M)pellets was investigated through the addition of corresponding Al-containing additives,including alumina,alumogoethite,gibbsite,and kaolinite.Systematic mineralogical analysis,combined with the thermodynamic properties of different aluminum occurrences and the quantitative characterization of consolidation behaviors,were conducted to determine the related mechanism.The results showed that the alumina from various aluminum occurrences adversely affected the induration characteristics of pellets,especially at an aluminum content of more than 2.0wt%.The thermal decomposition of gibbsite and kaolinite tends to generate internal stress and fine cracks,which hinder the respective microcrystalline bonding and recrystallization between Fe2O3particles.The adverse effect on the induration characteristics of fired pellets with different aluminum occurrences can be relieved to varying degrees through the formation of liquid phase bonds between the hematite particles.Kaolinite is more beneficial to the induration process than the other three aluminum occurrences because of the formation of more liquid phase,which improves pellet consolidation.The research results can further provide insights into the effect of aluminum occurrence and content in iron ore concentrates on downstream processing and serve as a guide for the utilization of high-alumina iron ore concentrates in pelletization.