To ensure the uniformity of the gas flow in the sintering material layer, improve the sintering efficiency, and reduce the production energy consumption, it is of great significance to predict the permeability index of the original material layer in advance. However, how to achieve accurate prediction in line with the actual production environment has always been a challenge. Based on this, deep learning was combined with finite element numerical simulation, and an integrated prediction method with high interpretability and controllability was proposed. This method used the wavelet threshold denoising technology jointly improved based on complete ensemble empirical mode decomposition with adaptive noise (CEEN) to process the original data, so as to improve the data quality. Subsequently, a temporal convolutional network-long short-term memory (TCN-LSTM) model was constructed and trained for permeability prediction. Comparative analysis showed that the proposed model has a higher prediction accuracy than other comparative models, with the coefficient of determination R2 as high as 95%. In the experimental simulation stage, taking a 360 m2 sintering machine of a certain steel plant as the research object, the COMSOL finite element software was used to establish a physical model for process simulation. The results showed that the variation curve of the permeability of the material layer along the depth direction is highly consistent with the measured results, with a relative error of approximately 3.90 and the R2 of 92.38%. In addition, based on the results of finite element numerical simulation, when using the TCN-LSTM model for prediction, the difference between the predicted value and the simulated value is small, with an average relative error of only 4.92% and the R2 of 97.29%, showing a high degree of fitting and matching. Therefore, the method of combining finite element numerical simulation with CEEN-TCN-LSTM can accurately predict the permeability index of the material layer, effectively meeting the dual needs of predicting the permeability in advance and monitoring the change process of the material layer in actual production and providing technical support for the optimization of the sintering process and the production of high-quality sinter.

Traditional relying on manual experience to assess the tuyere status consumes significant human resources. In the era of intelligent blast furnaces and intensified smelting, this approach struggles to meet the demands for accuracy and real-time assessment, posing challenges to safety and efficiency of blast furnace production. Tuyere images exhibit high feature similarity, and the number of samples is often limited. Therefore, if a simple convolution operation is only used, it will be difficult to discern differences across various images. To address this challenge and cater to the requirements of intelligent tuyere status recognition across different steel enterprises, we designed a novel deep neural network algorithm called ES-SFRNet (Enhanced Sequential: Feature Fusion and Recognition Network), building upon our prior research. The algorithm concurrently modeled tuyere images alongside relevant time series data, comprising three components: Feature pre-extraction, Tuyere status recognition, and Generalization & Robustness. The first two modules focus on feature extraction and fusion of tuyere images, while leveraging edge detection information from the image, we developed a mathematical index Ar (Area Ratio) to serve as an auxiliary criterion for tuyere status recognition. Given the model's future scalability and multi-scenario application, the final module focuses on knowledge integration and parameter control. Test results reveal an overall accuracy rate of 99.3% for the ES-SFRNet algorithm, effectively capturing key parameters to facilitate on-site operations. In comparison to other mainstream object detection algorithms, our algorithm framework excels in tuyere image feature extraction and recognition, which can offer broad applications to Chinese blast furnace ironmaking industry.

To address the issues of insufficient accuracy and poor real-time performance in sinter bed permeability prediction, this paper proposes a prediction model based on an improved variational mode decomposition (VIVID) and convolutional neural network-gated recurrent unit (CNN-GRU) hybrid approach. The model employs VMD combined with wavelet threshold denoising to preprocess the raw data, decomposing the complex sequence into multiple intrinsic mode functions (IMFs) with distinct frequency characteristics, followed by signal reconstruction using wavelet thresholding. Based on this, a CNN-GRU hybrid prediction model is constructed by leveraging the spatial feature extraction capability of CNN and the temporal modeling advantage of GRU. After model training and hyperparameter optimization, experimental results show that the VMD-CNN-GRU model outperforms the comparison models in MAPE, RMSE, and MAE metrics, achieving an R-2 value of 96% demonstrating superior prediction accuracy and stability. This provides an effective forecasting method for controlling and optimizing sinter bed permeability.

In the traditional blast furnace (BF) ironmaking process in China, a notable deviation exists between the theoretical and actual yield of hot metal, leading to unexpected iron loss and restricting the improvement of production capacity, which cannot adapt to the increasingly intensified smelting rhythm. Focusing on a BF in a Chinese steel enterprise, a deep neural network algorithm was designed to model the impact of multiple parameters on actual yield of hot metal in a single BF smelting cycle, successfully accomplishing the theoretical computation and real-time prediction of yield of hot metal for subsequent, unknown BF smelting cycle. Test results show that the proposed algorithm demonstrates an impressive prediction accuracy of 86.7

As important metallurgical performance indicators for evaluating the quality of sinter ore, the low-temperature reduction pulverization index, drop temperature, maximum differential pressure, and total characteristic value of sinter ore, their level directly affects the stability of the blast furnace production. Aiming at the problems of serious lag in sinter pyrometallurgical property detection and inaccurate prediction by single model, a sinter metallurgical performance index prediction model (CNN-BIGRU-Attention) integrating convolutional neural network, bidirectional gated recurrent unit, and Attention mechanism is proposed based on data-driven ideas. Firstly, data preprocessing is carried out on the 21 important parameters collected that affect the target variables, secondly, the parameters that have a greater impact on the target variables are screened by XGBoost and cross-validation algorithms, while the ablation and comparison experiments are carried out afterward. The experimental results show that compared with the traditional single-algorithm model, the CNN-BIGRU-Attention model has the best integrated prediction effect, and the hit rate (Acc) of the four metallurgical performance indicators is excellent, which is as high as 93.52

This is an article in the field of metallurgical engineering. With the increasing attention of iron and steel enterprises to pollutant emission, non blast furnace ironmaking process has gradually become a hot issue. At present, the industrialized non blast furnace ironmaking technology in China is mainly Corex process of Baogang and HIsmelt process of Shandong Molong. It is also a hot process of non blast furnace ironmaking technology in China. This article expounds the processes of Corex process and HIsmelt process, compares the technical indexes, advantages and disadvantages of the two processes, discusses the research status of the two processes in China, and looks forward to their development direction in combination with the characteristics of each process.

The quality of molten iron not only has a significant impact on the strength, toughness, smelting cost and service life of cast iron but also directly affects the satisfaction of users. The establishment of timely and accurate blast furnace molten iron quality prediction models is of great significance for the improvement of the production efficiency of blast furnace. In this paper, Si, S and P content in molten iron is taken as the important index to measure the quality of molten iron, and the 989 sets of production data from a No.1 blast furnace from August to October 2020 are selected as the experimental data source, predicting the quality of molten iron by the I-GWO-CNN-BiLSTM model. First of all, on the basis of the traditional data processing method, the missing data values are classified into correlation data, temporal data, periodic data and manual input data, and random forest, the Lagrangian interpolation method, the KNN algorithm and the SVD algorithm are used to complete them, so as to obtain a more practical data set. Secondly, CNN and BiLSTM models are integrated and I-GWO optimized hyperparameters are used to form the I-GWO-CNN-BiLSTM model, which is used to predict Si, S and P content in molten iron. Then, it is concluded that using the I-GWO-CNN-BiLSTM model to predict the molten iron quality can obtain high prediction accuracy, which can provide data support for the regulation of blast furnace parameters. Finally, the MCMC algorithm is used to analyze the influence of the input variables on the Si, S and P content in molten iron, which helps the steel staff control the quality of molten iron in a timely manner, which is conducive to the smooth running of blast furnace production.

This is an essay in the field of environmental engineering.The experiment adopts the impregnation method,and uses FeCl3 as the modifier to modify the activated carbon to study its desulfurization ability.The effects of modifier concentration,roasting temperature,and reaction temperature on the desulfurization performance of modified activated carbon were experimentally studied.Studies have shown that as the concentration of the modified solution increases,the Fe2O3 attached to the surface of the activated carbon increases,the specific surface area and total pore volume of the modified activated carbon decrease,and the average pore size increases;as the roasting temperature increases,the amount of Fe2O3 attached to the surface of the activated carbon continues.When the roasting temperature exceeds 300 ℃,the pore structure of the activated carbon surface will be sintered,which will reduce the desulfurization performance of the modified activated carbon;as the reaction temperature increases,the adsorption performance of FeCl3/AC-0.15 first increases and then decreases.When the concentration of FeCl3 modified solutionis 0.15 mol/L,the calcination temperature is 300 ℃,and the reaction temperature is 60 ℃,the desulfurization efficiency of modified activated carbon is the highest.

Fluctuations in the sintering process have a significant impact on the overall performance and outcomes of sintering production. It is crucial to gain a comprehensive understanding of the sintering operation in a timely manner in order to minimise process fluctuations and ensure the stability of sinter production. In this paper, a sintering process evaluation model is presented, which is based on the analytic hierarchy process-entropy weight method-technique for order preference by similarity to an ideal solution (AHP-EWM-TOPSIS) and is constructed using data from a steel plant sintering production process. Firstly, the evaluation indices input to the system are selected by combining the principle of the sintering process and actual production requirements. The subjective and objective weights of the indices are then calculated using the AHP-EWM method, and the weights are combined through the principle of minimum discriminatory information to construct the set of weighted indices. Subsequently, the sintering process was evaluated by the TOPSIS model, and the results of this evaluation were compared with the actual fluctuation situation at the sintering site. This was done by combining the model results with the differential level method. It was found that the model can accurately reflect the fluctuation situation that occurs in the sintering process. Furthermore, the comprehensive matching rate reached 95.42%, which demonstrates that the model is capable of accurately evaluating the operation of the sintering process. The statistical analysis of historical data provides a basis for the optimised operation of the sintering production process by summarising the optimal range of each parameter when the sintering operates efficiently. Ultimately, a sintering process evaluation system is constructed through the use of computer technology, thereby facilitating the transformation of sintering production into an intelligent system. The model is capable of rapidly ascertaining the actual status of the sintering process in real time. The established system is designed to facilitate the optimisation of sintering production operations and to promote long-term stability in sintering.

Thermodynamic calculations and thermal analysis tests were performed to investigate the thermodynamic and kinetic behaviors of the carbothermal reduction of vanadium-titanium magnetite w(C)/w(O) and basicity on the carbothermal reduction process of vanadium-titanium magnetite based on the HIsmelt process. Thermodynamic analysis showed that the addition of basicity promoted the reduction of vanadium-titanium magnetite, and the reaction onset temperature gradually increased with the decrease of the valence states of the elements V, Ti and Fe in the product. Increasing the amount of carbon assigned to the system gradually increased the mass fractions of metal Fe and Fe3C and raised the mass fractions of Ti, V and their low valence compounds at equilibrium. Increasing the basicity had less effect on the Fe, V and Ti fractions of the equilibrium system. The results of kinetic tests showed that the maximum reduction degree and maximum reaction rate of the reduction reaction by increasing w(C)/w(O) and basicity increased, the apparent activation energy and the finger front factor decreased, and the reaction mechanism function of the non-isothermal kinetic reduction process was f(α) = (3/2)(1−α)4/3[(1−α)−1/3−1] −1 belonging to the three-dimensional Z-L-T diffusion model.

Blast furnace ironmaking plays an important role in modern industry and the development of the economy. A reasonable ingredient scheme is crucial for energy efficiency and emission reduction in blast furnace production. Determining the right blast furnace ingredients is a complicated process; therefore, this study examines the optimization of the ingredient ratio. In this paper a model of the blast furnace ingredients is established by considering cost of per ton iron, CO2 emissions, and the theoretical coke ratio as the objective functions; ingredient parameters, process parameters, main and by-product parameters as variables; and the blast furnace smelting theory and equilibrium equation as constraints. Then, the model is solved by using an improved grey wolf optimization algorithm and an improved multi-objective grey wolf optimization algorithm. Using the data collected from the steel mill, the conclusion is that multi-objective optimization can consider the indexes of each target, so that the values of all the targets are excellent; we also compared the multi-objective solution results with the original production scheme of the steel mill, and we found that using the blast furnace ingredient scheme optimized in this study can reduce the cost of iron per ton, CO2 emissions per ton, and the theoretical coke ratio in blast furnace production by 350 CNY/t, 1000 kg/t, and 20 kg/t, respectively, compared with the original production plan. Thus, steel mill decision makers can choose the blast furnace ingredients according to different business strategies and the actual needs of steel mills can be better met.

针对某钢厂铁前数据库中烧结物料的预警空值与预警模型不完善问题,提出了一种烧结矿性能预警模型.将传统烧结工艺理论与大数据技术相结合,对原厂烧结生产数据进行预处理并搭建相应的烧结数据仓库,运用RFE(递归特征消除)对生产参数进行特征选择、重要性排序与相关性分析,然后运用DNN算法构建烧结矿化学成分与质量指标的预测模型,预测V2 O5、CaO/SiO2、TFe和FeO的R2 分别达到0.965 8、0.824 7、0.846 2 和 0.871 1,预测筛分指数和转鼓指数的R2 分别达到 0.899 和 0.875,满足预测精度需求,并将预测结果结合预警区间对烧结矿性能进行预警.

高炉喷吹焦炉煤气可以充分发挥氢还原的作用,实现高炉冶炼的低碳绿色发展.为了分析高炉喷吹焦炉煤气的减排能力,以钒钛磁铁矿冶炼高炉的现场生产数据和炉内理化反应为基础建立质能平衡模型,研究焦炉煤气喷吹量对风口理论燃烧温度和炉顶煤气CO2排放量的影响;建立一定约束条件下喷吹焦炉煤气的操作窗口,讨论其降碳减排能力.研究结果表明,在一定的富氧率、焦比、煤比和风温下,随着焦炉煤气喷吹量的增加,风口理论燃烧温度和炉顶煤气CO2排放量均降低.当风温和煤比一定时,通过提高富氧率可以实现喷吹焦炉煤气高炉的热量补偿.随着焦炉煤气喷吹量的增加,富氧率提高、焦比降低.不喷吹焦炉煤气,钒钛磁铁矿高炉在富氧率为3％、焦比为380.0 kg/t(Fe)、煤比为130 kg/t(Fe)、风温为1 200℃操作条件正常运行时,其风口理论燃烧温度为2 075℃、炉顶煤气温度最低为120℃;当焦炉煤气喷吹量为55 m3/t(Fe)时,可以维持与不喷吹焦炉煤气时相同的理论燃烧温度和炉顶煤气温度,相应的富氧率为5.63％、焦比为371 kg/t,炉顶CO2排放量为684 kg/t(Fe);与不喷吹焦炉煤气相比,焦比降低9 kg/t(Fe),炉顶煤气CO2排放量降低27.1 kg/t(Fe).以理论燃烧温度为1 900℃、炉顶温度为110℃为约束条件,计算得到钒钛磁铁矿高炉可接受的焦炉煤气喷吹量可提高至185 m3/t(Fe),此时的富氧率为4.9％;与不喷吹焦炉煤气相比,焦比和炉顶煤气CO2排放量分别降低49.7 kg/t(Fe)和103.0 kg/t(Fe),达到了显著的降碳减排效果.

Under the development background of "carbon peak" and "carbon neutral" proposed by China, the green reform of iron and steel enterprises is imminent. The fossil fuel consumption and CO 2 emission of iron and steel enterprises mainly come from the blast furnace（BF） ironmaking process. The hydrogen-rich smelting technology of BF can effectively reduce the coke consumption and CO 2 emission. The increase of H 2 volume fraction in the BF will greatly change the coke property evolution process. Exploring this change process is particularly important for the stable and smooth production and energy conservation and emission reduction of BF. The effects of hydrogen-rich smelting in BF on coke gasification reaction, microstructure and melting erosion process of slag-iron-coke interface in cohesive zone are reviewed. Different from the traditional BF, the hydrogen-rich smelting of BF increases the weight-loss rate of coke gasification reaction in the low temperature zone, but the gasification process of coke under high temperature conditions mainly occurs on the surface, which inhibits the reduction of coke strength after reaction in the high temperature zone. The corrosion of slag iron in the cohesive zone of BF to coke reduces, and the high ash content in the coke surface layer hinders the occurrence of carburizing reaction. On this basis, the problems to be further studied are prospected, providing reference for hydrogen-rich BF production and coke selection.

目前中国钢铁生产仍以高炉→转炉长流程为主,高炉富氢操作是中国氢冶金发展的重要方向.富氢介质和喷吹方式有很多种,合理有效地选取高炉富氢工艺显得尤为重要.为了确定合适的富氢工艺,基于有氢参与的Rist操作线工具,结合高炉整体与区域热平衡联合计算,提出了"碳消耗-碳排放-焦比-理论燃烧温度操作窗口"概念.对比分析了高炉喷吹焦炉煤气、天然气、氢气在常温与预热条件下的节能减排效果.研究结果表明,随富氢介质喷入量的增加,高炉焦比、理论燃烧温度、碳消耗、CO2排放均呈升高趋势,富氧率对这些指标的影响呈相反规律.在不喷煤的情况下,高炉单喷富氢介质技术虽然可以降低碳素消耗,降低碳排放,但焦比仍然较高.通过比较不同富氢工艺的操作窗口区域大小得出高炉喷煤+纯氢气具有更高的节能减排效果.从操作窗口可以直观地得出不同富氢技术的最大喷吹量和限制性环节.研究结果表明,高炉喷煤+天然气、高炉喷煤+焦炉煤气、高炉喷煤+纯氢气的最大喷吹量分别为128、359和500 m3/t,高炉喷煤+950 ℃预热氢气相比于常温条件节能减排率增加20％左右.

烧结生产具有能耗高、污染物排放量大的特点,是钢铁工业节能减排的重点工序.在国家"双碳"背景下,文章在综述现代烧结企业影响返矿率的主要因素的基础上,重点分析了降低返矿率的技术措施,并对有效降低返矿率的新技术进行了展望.经分析指出:原料条件和化学成分、工艺参数、设备和管理水平等是现阶段影响返矿率的主要因素;目前降低返矿率的技术措施主要包括优化铁矿石原料条件及配矿结构,开发智能配矿技术,优化燃料条件,提高料层厚度、优化工艺参数,以及强化设备管理、降低漏风率等;同时指出加快烧结料面富氢、富氧喷吹技术的研发和推广,进一步开发有效的返矿直接入炉冶炼技术,可以为降低返矿率提供新思路.

In response to the problem of rich vanadium-titanium magnetite (VTM) resources in China contrasting with low blast furnace utilization, a HIsmelt process for smelting VTM is proposed. The influence of the process parameters on smelting reduction is analysed under laboratory conditions by simulating smelting reduction. The results show that extending the reaction time reduces the FeO content in the slag by 15.34 wt-%, increasing the reaction temperature reduces the FeO content in the slag by 26.38 wt-%, and increasing the basicity reduces the FeO content in the slag by 11.26 wt-%. The control temperature for smelting VTM using the HIsmelt process is 1425 & DEG;C, with a reduction time of 20-30 min, which is conducive to the transfer of vanadium to the molten iron and the enrichment of titanium in the slag. To ensure vanadium and titanium are efficiently utilized, a basicity control of 0.8 is appropriate.

现阶段,国内炼铁流程仍以"高炉-转炉"流程为主,且面临着高能耗、高污染及自动化程度不强等问题.随着双碳目标和"十四五"规划等政策的推出,高炉冶炼智能化升级转型得到更加广泛的关注.由于高炉生产涉及的调控参数众多且数据体量庞大,加上数据具有非线性、非高斯和滞后性等特点,使得大数据和人工智能技术在高炉智能化转型过程中拥有较大的发展空间和应用前景.首先从高炉智能预测、智能监测、智能评价和大数据平台4个方面详细阐述了高炉智能化的发展现状,并就各方面作了详细的探讨.其次,针对高炉智能化发展中存在的数据孤岛问题、数据噪声问题、模型鲁棒性问题和黑箱问题,提出了初步的解决办法.最后,结合新一代人工智能技术和钢铁生产技术,从高炉炼铁流程的数据共享、信息物理系统、一体化经营管理系统和移动工厂几个角度进一步展望了智能化转型升级的未来发展.

作为评价烧结矿质量的重要指标之一,转鼓指数的高低直接影响着高炉生产的稳定与否.以某钢铁企业烧结生产数据为基础,提出了基于特征工程与图像识别技术的烧结矿转鼓指数预测方法.首先对挑选出的3类28个影响烧结矿转鼓指数的重要指标完成数据预处理;而后通过SVM-RFE算法以及交叉验证算法筛选出对目标变量影响较大的特征参数;最后用卷积神经网络对经过数据特征转化的二维特征图像进行训练,建立了基于卷积神经网络的烧结矿转鼓指数预测模型.结果表明,在误差范围为±1％的情况下该模型命中率高达93.71％.这种将数据特征转化为图像特征的处理方法有效地提高了预测能力,对未来预测式烧结技术的发展具有很好的借鉴意义.

高炉炉况的波动严重影响高炉生产过程的铁水产量、质量和能耗.及时全面掌握高炉运行状态情况,减少炉况波动是保持高炉生产稳定顺行的关键.以某钒钛高炉自身历史数据为基础,建立了一种基于大数据挖掘的高炉综合运行状态评价模型.依据高炉炼铁全流程数据仓库资源,采集整合高炉相关生产数据,对原始数据存在的空缺值、异常值等问题进行了数据处理,得到了模型开发所需要的干净数据.结合高炉工艺和专家经验,选取表征高炉综合运行状态的33个评价指标,建立高炉综合运行状态评价指标体系,利用基于博弈论的层次分析法和熵权法的组合赋权及改进的TOPSIS算法建立AHP_EWM_TOPSIS高炉综合运行状态评价模型,对高炉运行状态进行评估和排序.模型的评价结果与实际生产情况进行验证,综合匹配率达到94.49％,能够准确评价高炉综合运行状态情况,并为高炉操作者提供及时有效的高炉运行状态信息.对历史高炉运行状态进行统计分析,得出高炉炉况的演变情况.总结了良好高炉运行状态条件下运行参数的最佳范围,为高炉的生产运行优化提供操作依据和数据支持.模型能够快速判断高炉的实时运行状态情况,辅助高炉生产操作优化,促进高炉的长期稳定运行,实现高炉优质、高产、低耗、长寿的生产目的.