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.

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.

Synthesis of nanostructured Mg_2FeH_6 hydride and hydrogen sorption properties of complex

Reactive mechanical alloying(RMA)was carried out in a planetary ball mill for the synthesis of ternary hydride Mg2FeH6 for hydrogen storage.The formation mechanism of Mg2FeH6 in RMA process and the sorption properties of the products were investigated.The results show that Mg2FeH6 has a yield ratio around 80%,and a grain size below 10 nm in the powder synthesized by milling 3Mg+Fe mixture for 150 h under the hydrogen pressure of 1 MPa.The synthesized powder possesses a high hydrogen capacity and good sorption kinetics,and absorbs 4.42%(mass fraction)of hydrogen within 200 s at 623 K under the hydrogen pressure of 4.0 MPa.In releasing hydrogen at 653 K under 0.1 MPa,it desorbs 4.43%(mass fraction)of hydrogen within 2 000 s.The addition of Ti increases the hydrogen desorption rate of the complex in the initial 120 s of the desorption process.

Hydrogen sorption properties of nanocrystalline Mg_2FeH_6-based complex and catalytic effect of TiO_2

The diversities of hydrogen sorption properties of Mg2FeH6-based complexes with and without TiO2 were investigated. Mg2FeH6-based complexes with and without TiO2 were synthesized respectively by reactive mechanical alloying,and hydrogen sorption properties of the complexes were examined by Sieverts-type apparatus. The results show that the sample without TiO2 releases 4.43 % (mass fraction) hydrogen in 1.5 ks at 653 K under 0.1 MPa H2 pressure and absorbs 90% of the total 4.43 % (mass fraction) hydrogen absorbed in 85 s at 623 K under 4.0 MPa H2 pressure. But for the sample with TiO2 addition under the same condition,it only needs 400 s to release all of the stored hydrogen and 60 s to absorb 90% of the total hydrogen absorbed. The activation energies for desorption process of the samples with and without TiO2 are determined to be 71.2 and 80.3 kJ/(mol.K),respectively. The improvement in hydrogen sorption rate and and reduction in activation energy can be attributed to the addition of TiO2.

AlN Precipitates and Microstructure in Non-oriented Electrical Steels Produced by Twin-roll Casting Process

Aluminum nitride （AIN） precipitates and microstructure of 4 wt.% （Si＋AI） non-oriented electrical steel were investigated. The 2.0 mm thick cast strips with three different silicon/aluminum （Si/AI） ratios were produced by twin-roll casting process, then the strips were reheated, warm rolled, cold rolled and annealed. The microstructure and AIN precipitates were characterized using optical microscopy, scanning electron microscopy and transmission electron microscopy. The results showed that with the increase of Si/AI ratio, on the one hand, the casting microstructure changed from columnar grains to equiaxed grains, and the uniformity of annealed microstructure was improved; On the other hand, the number of AIN precipitates in cast strips reduced meanwhile the distribution became dispersed. By the reheat treatment, the size and distribution of the AIN precipitates can be changed. Moreover, the grain size of the annealed strips is in the range of 20-50 #m, at the same time, many AIN precipitates were located at grain boundaries. Therefore, controlling the Si/AI ratio is a simple method to obtain desired microstructure. Then AIN precipitates in non-oriented electrical steel prepared by twin-roll casting process hinder markedly the recrystallized grains growth, A compatible reheat treatment can be an approach worth exploring to control the behavior of AIN precipitates.

Development of Ti–V–Mo Complex Microalloyed Hot-Rolled 900-MPa-Grade High-Strength Steel

A new Ti-V-Mo complex microalloyed hot-rolled high-strength steel sheet was developed by controlling a thermo-mechanical controlled processing （TMCP） schedule, in particular with variants in coiling temperature. The effects of coiling temperature （CT） on various hardening mechanisms and mechanical properties of Ti-V-Mo complex mi- croalloyed high-strength low-alloy steels were investigated. The results revealed that the steels are mainly strengthened by a combined effect of ferrite grain refinement hardening and precipitation hardening. The variation in simulated coiling temperature causes a significant difference in strength, which is mainly attributed to different precipitation hardening increment contributions. When the CT is 600 ℃, the experimental steel has the best mechanical properties： ultimate tensile strength （UTS） 1000 MPa, yield strength （YS） 955 MPa and elongation （EL） 17%. Moreover, about 82 wt% of the total precipitates are nano-sized carbide particles with diameter of 1-10 nm, which is randomly dispersed in the ferrite matrix. The nano-sized carbide particles led to a strong precipitation hardening increment up to 310 MPa.

Impact Toughness of an NM400 Wear-Resistant Steel

An NM400 wear-resistant steel was hot rolled and then the plates were heat-treated by direct quenching and tempering （DQT） and reheat quenching and tempering （RQT） techniques, respectively. The Charpy impact test was carried out with an instrumented Charpy impact tester. The microstructure and fracture surface were investiga-ted by a combination of optical microscopy, transmission electron microscopy and scanning electron microscopy methods. It was found that the impact toughness of DQT specimen was much higher than that of RQT specimen. The microstructure of both DQT and RQT specimens was characterized by a mixture of tempered lath martensite and lower hainite. The lower bainite in DQT specimen extended into prior austenite grains and the content was higher than that in RQT specimen. The lower bainite in DOT specimen improved the impact toughness by increasing the proportion of large-angle boundaries and relieving the stress concentration at the crack tip. A number of fine and dis-persed carbides in DQT specimen also contributed to the improvement of the impact toughness.

A New Steel Teeming Technology by Using Electromagnetic Induction Heating System in Ladle

In order to overcome the pollution of the tratitional nozzle sand into the molten steel in tundish,a new method is proposed in this paper.In this method,the nozzle sand is substituted with iron-carbon alloy particles which have the same or similar compositions as the liquid steel.During casting processes,iron-carbon alloy forms solidification shell and the sintered layer in the upper nozzle to block the molten steel.When the slide gate is opened,the eletromagnetic induction heating is used to melt them so as to achieve 100%smoothly steel teeming.The electromagnetic induction heating effects were analyzed theoretically in the new slide gate system.Then the new method has been experimentally tested by using self-designed experimental device.The results show that the electromagnetic induction heating can complete the steel teeming within the required time.Furthermore,this steel-teeming technology can further improve the cleanliness of liquid steel.

Effects of Steel Teeming in New Slide Gate System with Electromagnetic Induction

Steel teeming time is a very important parameter in the new slide gate system with electromagnetic induction （called electromagnetic steel teeming system）, and how to shorten this time is a key to realize application of the new system in continuous casting. The effects of power parameters, coil position, nozzle material and other factors on the steel teeming time were investigated by a self-designed electromagnetic steel teeming system in detail. The experimental results show that the relationship between power and steel teeming time is nonlinear. The coil position has great in- fluence on steel teeming time. And the upper nozzle with high permeability can reduce the teeming time. In addition, the steel teeming time becomes minimum when the size of the spherical cast iron particles is 2.0 ram. This research can provide technical references for the industrial application of the new electromagnetic steel teeming system.

Genetic optimization of ladle scheduling in empty-ladle operation stage based on temperature drop control

To optimize ladle scheduling in the empty-ladle operation stage of steel plants,a mathematical scheduling model was established for the empty-ladle operation stage,taking the minimum total waiting time in the empty-ladle operation stage as the optimization goal and setting the equipment assignment uniqueness as the key constraint.An improved genetic algorithm was designed to calculate the mathematical scheduling model.In the operation of the genetic algorithm,the strategy of"ladle temperature drop control"was adopted to solve the problem of equipment conflicts and reduce unreasonable ladle temperature drops to enhance"red-ladle"utilization.Five main production modes operating at 95%capacity in a Chinese steel plant were simulated using the genetic optimization model.The results showed that the genetic optimization model could improve the efficiency of ladle operation and reduce the total waiting time in the empty-ladle operation stage by 868–1147 min.