Since entering the new century, China's iron and steel technology has developed rapidly, and the issue of blast furnace life has been increasingly valued by researchers. Furnace cylinder activity is considered to be the key factor affecting the life and stable anterograde of blast furnace, so reasonable prediction of furnace activity is of great significance to guide blast furnace production and improve blast furnace smelting efficiency. This paper proposes a furnace cylinder activity prediction model based on the GRA-SSA-LSSVM model. The pre-treated production data is used to obtain the quantified activity index of blast furnace cylinder by relevant formulas. Then the feature variables were selected by grey relational analysis combined with mechanism analysis. In order to further improve the prediction accuracy of the model, a furnace cylinder activity prediction model based on Sparrow search algorithm (SSA) optimized least square support vector machine (LSSVM) was proposed based on the above content, and the effectiveness of the predictive model was simulated and analyzed. The results show that the accuracy of predicting the cylinder activity using this method is high, which can meet the needs of guiding the actual production.

The sintering technology of iron and steel enterprises in China has reached a certain level. However, due to serious resource and environmental issues, how to achieve the greening of the sintering process, the intelligence of the equipment, the high quality of the products and the acceleration of the digital transformation based on intelligent decision-making and control are still key issues to be solved by the iron and steel industry. Based on the historical data of massive sintering production, this study establishes a big data platform for the whole sintering process to realise the reasonable storage and effective organisation of massive data. A sinter quality cascade prediction system, including the sinter bed permeability prediction model, burning through point (BTP) prediction model and sinter quality prediction model and a detailed software structure design are given for the application of the system. The development and application of the system are beneficial for realising the important development goals of low pollution, high yield and high quality in sinter production.

In blast furnace smelting, the silicon content in molten iron is an important indicator of the temperature trend of the blast furnace. Due to the multi scale, non-linear, large time delay and strong coupling characteristics of the blast furnace smelting process, the control effect of silicon content in hot metal is often not ideal. Therefore, finding an effective and accurate method for controlling silicon content in hot metal is very important for blast furnace smelting. Based on this, this paper proposes a prediction and control model for silicon content in hot metal of blast furnace based on GRA–LSTM–BAS. Based on this, this paper proposes a prediction and control model for silicon content in hot metal of blast furnace based on GRA–LSTM–BAS. Firstly, the original data set is processed using wavelet analysis and normalisation processing methods. Secondly, the gray relational analysis (GRA) method is used to analyse the correlation between the input variables of the model to determine the input parameters of the model. Subsequently, a long short-term memory (LSTM) prediction model was established to obtain silicon content values at future times through feedback correction. The model was trained and tested by on-site collected data and compared with the support vector machine (SVM) model. The results show that the LSTM model can quickly and accurately predict the silicon content in hot metal, and has a good guiding significance for actual blast furnace production. Finally, the control model for silicon content in molten iron is optimised iteratively by combining the beetle antennae search algorithm (BAS algorithm). Feedback and update of the results in the model are done in real time according to errors, forming a closed-loop controller to maintain the silicon content in molten iron at an appropriate level and achieve optimal control of the silicon content.

As one of the important links in the traditional long process steel production process, the sinter yield and quality of the sintering process directly affect the efficiency of ironmaking production. As an important index to detect the sintering production status, the sintering end point is very important for optimizing the production process and improving the product quality. Predicting the sintering end point can help the production planning and scheduling work, and make the production process more orderly and efficient. Accurate endpoint prediction helps to optimize production schedules and ensure the right raw materials and energy inputs to meet the quality requirements of a specific products. A prediction model of BTP based on GA-BP was proposed in this paper. Based on the production data of an iron and steel enterprise, the anomalies in the production data were processed. Then the genetic algorithm (GA) was used to set the initial value and threshold of the neural network (BP), and a GA-BP prediction model was designed. The results show that the prediction accuracy of the GA-BP model for the sintering end point can reach more than 95 %. The sintering prediction ability is further optimized, which effectively suppresses the fluctuation of the sintering end point, improves the calculation accuracy of the sintering end point, assists the field staff to adjust the operating parameters in advance, and stabilizes the sintering production. It has important theoretical significance and practical value in production practice.

With the development of artificial intelligence, digital empowerment to help the intelligent transformation of blast furnaces and achieve the "30-60" target has become a major research objective. As one of the important indicators of blast furnace production, the reasonable prediction for hot metal temperature could help to master the operating status of furnace conditions and reduce the energy consumption in time. Therefore, a molten iron temperature model based on PSO-LSTM is proposed in this paper. Firstly, for the characteristics of blast furnace data such as long time lag and the abnormal values difficultly judge, the handling for sample data is completed by using the big data method. Secondly, the selection for parameters based on the complementary of process and big data techniques is used to improve the interpretation of model input variables. Finally, a PSO-LSTM prediction model was established by the LSTM algorithm, and the prediction capability is analysed from four perspectives include mean absolute error (MAE) and root mean square error (RMSE) and so on. The results show that the prediction accuracy of hot metal temperature is up to 95.6%, which has certain implications for production guidance.

The vanadium content of molten iron is an important economic indicator for a vanadium–titanium magnetite smelting blast furnace, and it is of great importance in blast furnace production to be able to accurately predict it and optimize the operation of vanadium extraction. Based on the historical data of a commercial blast furnace, the clean data were obtained by processing the missing data and outlier data for data mining analysis and model development. A combined wavelet-TCN model was used to predict the vanadium content of molten iron. The average Hurst index after wavelet transform was calculated to reduce the complexity of the wavelet transform layer selection and the model computation time. The results show that compared to single models, such as LSTM, LSTM with attention, and TCN, the combined model based on wavelet-TCN (a = 5) had an improvement of about 11~17% in R2, and the prediction accuracy was high and stable, which met the practical requirements of blast furnace production. The factors affecting the vanadium content of molten iron were analyzed, and the measures to increase the vanadium content were summarized. A blast furnace should avoid increasing the titanium dioxide load, increase the vanadium load appropriately, and keep the relevant operating parameters within the appropriate range in order to achieve the optimization of vanadium extraction from molten iron.

The sulphide capacities of CaO-SiO2-Al2O3-MgO-TiO2-FetO slags with high titanium and FetO were measured by gas-slag equilibration technique to reveal the effect of slag composition and temperature on the sulphide capacities of slags. The results showed that sulphide capacities enhanced with the increase of temperature, basicity, FetO, and MgO contents, TiO2 content increased first and then decreased in the range of 10 wt-% to 20 wt-%; the influence became negligible as the TiO2 content exceeded 25 wt-%. MgO significantly increased the sulphide capacities of slag in the range of 6 wt-% to 8 wt-%, continued to increase the MgO content, and the increasing trend of Log CS became slowly; FetO content increased from 3 wt-% to 9 wt-%, sulphide capacities increased slowly, increased dramatically in the range of 9 wt-% to 15 wt-%. Meanwhile, comparing the optical basicity models found Zhang and Tsao's models are close to the experimentally determined values.

The permeability index is one of the important production indicators to monitor the operation of blast furnace. It is crucial to grasp the trends of changes in the new permeability index in time. For the complex vibration spectrum of the permeability index, a prediction model of the permeability index based on the VMD-PSO-BP (variational mode decomposition-particle swarm optimization-back propagation) method was proposed. Firstly, the key factors that affect the permeability index of blast furnace were studied from multiple perspectives. Then, the permeability index was divided into multiple sub-modes based on the difference of frequency bands by the VMD algorithm, and a PSO-BP prediction model was established for each sub-mode. Finally, the prediction results of each sub-mode were summed to obtain the final one. The results show that the composite prediction accuracy by using the VMD algorithm is 3% higher than that of the traditional prediction method, which has better applicability.

In the long process of iron and steel, the sintering process has the largest amount of flue gas emissions, many types of pollutants and high concentrations. The source control of SO2 and NOx in sintering flue gas through digital technology has become a new emission reduction technology. In this study, the BP neural network model (BP-NN) is optimized by using the particle swarm algorithm (PSO) to form the PSO-BPNN model, which effectively improves the characteristics of BP-NN with slow convergence speed and easily falls into local minima, and improves the learning ability and generalization. The test results show that the PSO-BP-NN algorithm not only has fast convergence speed and high prediction accuracy, but also has smaller training and inspection errors. In addition, this model combines process theory and feature engineering selection of parameters, which effectively improves the accuracy of the model and the interpretability of the results based on the linkage of process knowledge, and has certain analytical significance for the source management and post-treatment of sintered flue gas.

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.

A model for predicting the vanadium content in a molten iron blast furnace (BF) was developed to solve the problem of late iron detection during the smelting process of a vanadium and titanium BF. First, based on the whole process data platform of BF ironmaking, the standardized data warehouse of BF smelting was established, and the variables related to vanadium content in molten iron are selected in the model. Clean data were obtained by processing the original data. Afterward, the feature extraction of variables was achieved by feature construction and PCA dimensionality reduction, and the final input feature variables were determined using a combination of multiple feature selection algorithms and production process experience. Finally, the CatBoost model was selected for prediction. The results show that CatBoost achieved better results than XGBoost and long short-term memory (LSTM) models, and all indicators were higher than in these two models. The R2 of CatBoost reached 0.773, and the index of prediction error within ±0.020% reached 89.65%, which met the actual production requirement of a vanadium and titanium commercial BF in China.

铁水钒含量作为冶炼钒钛磁铁矿高炉的重要经济指标,对其进行准确预测将对高炉后续提钒增效具有重要生产意义.利用小波-TCN组合时序模型对具有非线性、波动大等特点的高炉铁水钒含量进行预测.首先利用小波变换将原时间序列数据分解成多个噪声段和单个趋势段,然后选用TCN模型对小波变换后的噪声段和趋势段分别进行预测,最后将结果重构得到最终的预测结果.对于选取小波变换层数较复杂的问题,利用赫斯特系数能够表征数据可预测性的特点,提出小波变换后的平均赫斯特系数(H)用于降低模型建立过程中小波变换层数选取的复杂度,从而改进小波-TCN组合时序模型.结果表明,改进后的预测模型对单一变量预测高效且准确,相对非改进模型运算时间减少150％左右.对于赫斯特系数大于0.5的预测数据,利用改进小波-TCN组合时序模型对铁水钒含量进行预测,预测结果数据的R2达到0.967,均优于LSTM、LSTM with Attention和TCN单一预测模型的预测效果;对铁水硅、硫含量和铁水温度数据进行单变量预测,其R2分别为0.953、0.942和0.933.该预测模型可高效准确地对高炉铁水质量单变量进行预测,并可为高炉冶炼过程中所产生的其他波动较大数据的单变量准确、高效预测提供参考方案.基于预测模型进行预测系统功能应用开发,能使操高炉操作人员直观了解高炉出铁质量各参数状况,对高炉出铁质量数据进行提前掌握,促进高炉稳定顺行.

工艺绿色化、装备智能化、产品高质化已成为当前钢铁行业主要发展目标.作为影响烧结矿性能的重要指标之一,FeO的含量不仅影响烧结矿还原性的高低和烧结过程的能耗,而且在一定程度上影响高炉间接还原、燃料比等指标.针对目前研究过程中存在的数据量少、工艺结合不紧密、特征选择方法针对性不强等问题,提出了基于MIV-GA-BP算法的烧结矿FeO含量预报模型.以承钢3号烧结机1年的生产数据作为研究基础,首先选取BP神经网络作为深度学习模型,然后利用遗传算法的特点解决了网络调参难等问题,成功构建了基于遗传算法优化的BP神经网络模型.在特征选取阶段将MIV算法的优越性与工艺理论相结合,选取了拥有更好解释性的参数作为模型的输入,此方法提高了模型预测准确率,成功实现了烧结矿FeO含量的预测.上线测试结果表明,误差允许范围内模型命中率达到87.9％,对现场烧结生产具有更好的指导性.

The effects of the simultaneous injection of MgO and magnesite powder on the combustion of coals, properties of the primary slag, and softening-melting properties of the burden were investigated. There were four aspects to the results that we obtained. First, MgO showed catalytic activity for dehydrogenation and carboxyl group removal from coal; as a result, with increasing MgO, the combustion ratio and pyrolysis ratio of the coal investigated improved. Notably, when the content of MgO increased from 0% to 3.21%, the combustion ratio increased from 67.75% to 75.73%. Secondly, the MgO distribution in the slag sample was close to that in the standard slag after melting for 10 min. After 50 min, the difference in MgO content between the slag and standard slag samples was less than 1%. Thirdly, with an increase in the content of MgO, the short-slag feature of the slag was obvious, the viscosity fluctuated wildly, and the melting temperature increased significantly. It is proposed that the properties of the primary slag could be improved by decreasing the MgO content. Finally, with the increase in the MgO added to the burden, the softening-melting properties of the burden degraded. When the MgO content was 0.86%, ΔPmax was only 2.04 kpa, and S 59 kPa·°C. However, when the MgO content was 2.61%, ΔPmax was 20.00 kPa, and S 1349 kPa·°C. Therefore, the technology of MgO injection into tuyeres with pulverized coal was beneficial for blast furnace operation.

The large quantity of sediment produced in the hearth during vanadium titano-magnetite smelting in a blast furnace (BF) affects the stability of the blast furnace operation. Testing and analysis of the sediment in the hearth of Chengde Iron and Steel Company's BF No.7 revealed that it was mainly concentrated in the location below the tuyere and above the iron notch. Notably, some of the bonding material (sediment) consisted of greater than 50% pig iron, and the pig iron distributed in the slag was granular. It is proposed that a large quantity of TiC and Ti(C,N) are deposited on the surface of the pig iron. These high melting point materials mix with iron drops, preventing the slag from flowing freely, thus leading to the formation of bonding materials. In addition, the viscosity and melting temperature of the slag in the tuyere areas fluctuate greatly, and thus the properties of the slag are unstable. Moreover, the slag contains large quantities of carbon, which results in the reduction of TiO2. The resultant precipitation of Ti is followed by the formation of TiC in the slag, which also leads to an increase in the viscosity of the slag and difficulty in achieving separation of the slag-iron. In fact, all of these factors interact with each other, and as a result, sediment is formed when the operating conditions in the hearth fluctuate.