Explainable machine learning model for predicting molten steel temperature in the LF refining process

Accurate prediction of molten steel temperature in the ladle furnace(LF)refining process has an important influence on the quality of molten steel and the control of steelmaking cost.Extensive research on establishing models to predict molten steel temperature has been conducted.However,most researchers focus solely on improving the accuracy of the model,neglecting its explainability.The present study aims to develop a high-precision and explainable model with improved reliability and transparency.The eXtreme gradient boosting(XGBoost)and light gradient boosting machine(LGBM)were utilized,along with bayesian optimization and grey wolf optimiz-ation(GWO),to establish the prediction model.Different performance evaluation metrics and graphical representations were applied to compare the optimal XGBoost and LGBM models obtained through varying hyperparameter optimization methods with the other models.The findings indicated that the GWO-LGBM model outperformed other methods in predicting molten steel temperature,with a high pre-diction accuracy of 89.35%within the error range of±5°C.The model’s learning/decision process was revealed,and the influence degree of different variables on the molten steel temperature was clarified using the tree structure visualization and SHapley Additive exPlana-tions(SHAP)analysis.Consequently,the explainability of the optimal GWO-LGBM model was enhanced,providing reliable support for prediction results.

Exploration and Practice of Nitrogen Addition Process for LF Refining Ladle Bottom Blowing Nitrogen Steel Liquid

This article discusses and analyzes the law of nitrogen increase in liquid steel and the main factors affect-ing the nitrogen increasing of molten steel,through the way of adding nitrogen to molten steel by bottom blowing nitrogen gas in LF refining process.It is considered that the main factors affecting the nitrogen increasing instability of molten steel are the initial temperature of LF refining,nitrogen relative element,surface active elements[O]and[S]of steel liquid,and bottom blowing rate of ladle.The large-scale production practice shows that T[O]not more than 50×10-6 and[S]is not more than 0.020 in LF refining at the initial temperature of not less than 1570.The liquid steel nitrogen enrichment test is carried out by ladle bottom blowing nitrogen gas after 20 min of refining,the flow rate is set as(6.0~7.0)NL/min per ton,and it is turned to 2 NL/min at 6 min before the end of refining,the nitrogen increasing rate of liquid steel is basically stable at(5~6)×10-6 per minute.

Refinement Mechanism of Microstructure of Undercooled Nickel Based Alloys

Through the use of purification and recirculation superheating techniques on molten glass,the Ni65Cu33Co2 alloy was successfully undercooled to a maximum temperature of 292 K.High-speed photography was employed to capture the process of interface migration of the alloy liquid,allowing for an analysis of the relationship between the morphological characteristics of the alloy liquid solidification front and the degree of undercooling.Additionally,the microstructure of the alloy was examined using metallographic microscopy,leading to a systematic study of the microscopic morphological characteristics and evolution laws of the refined structure during rapid solidification.The research reveals that the grain refining mechanism of the Ni-Cu-Co ternary alloy is consistent with that of the binary alloy(Ni-Cu).Specifically,under low undercooling conditions,intense dendritic remelting was found to cause grain refinement,while under high undercooling conditions,recrystallization driven by accumulated stress and plastic strain resulting from the interaction between the liquid flow and the primary dendrites caused by rapid solidification was identified as the main factor contributing to grain refinement.Furthermore,the study highlights the significant role of the Co element in influencing the solidification rate and reheat effect of the alloy.The addition of Co was also found to facilitate the formation of non-segregated solidification structure,indicating its importance in the overall solidification process.

Study on the Application of Refined Nursing Care in The Care for Elderly Patients with Reflux Esophagitis

Objective: To investigate the application effect of refined nursing care in the care for elderly patients with reflux esophagitis. Methods: Following the difference in nursing style, 84 cases of elderly patients with reflux esophagitis admitted to our hospital from May 2022 to May 2023 were randomly grouped into a control group and a research group, with 42 cases each. The control group was given conventional nursing care and the research group was given refined nursing care. The psychological state and treatment adherence of the two groups of patients after the nursing intervention were compared. Results: After the nursing intervention, the self-rating anxiety scale (SAS) and self-rating depression scale (SDS) scores of the research group were lower than those of the control group (P < 0.05). The treatment compliance of the research group was better than the control group (P < 0.05). Conclusion: The implementation of refined nursing care for elderly patients with reflux esophagitis exhibited a significant effect on improving the patient’s psychological state, treatment compliance, and rehabilitation.

Strength and plasticity improvement induced by strong grain refinement after Zr alloying in selective laser-melted AlSiMg1.4 alloy

In order to enhance the mechanical properties of the selective laser-melted(SLM) high-Mg content AlSiMg1.4 alloy,the Zr element was introduced.The influence of Zr alloying on the processability,microstructure,and mechanical properties of the alloy was systematically investigated through performing microstructure analysis and tensile testing.It was demonstrated that the SLM-fabricated AlSiMg1.4-Zr alloy exhibited high process stability with a relative density of over 99.5% at various process parameters.Besides,the strong grain refinement induced by the primary Al3Zr particle during the melt solidification process simultaneously enhanced both the strength and plasticity of the alloy.The values for the yield strength,ultimate tensile strength,and elongation of the SLM-fabricated AlSiMg1.4-Zr were(343±3) MPa,(485±4) MPa,and(10.2±0.2)%,respectively,demonstrating good strengthplasticity synergy in comparison to the AlSiMg1.4 and other Al-Si-based alloys fabricated by SLM.

Grain refinement of Mg-Ca alloys by native MgO particles

In Mg-Ca alloys the grain refining mechanism,in particular regarding the role of nucleant substrates,remains the object of debates.Although native MgO is being recognised as a nucleating substrate accounting for grain refinement of Mg alloys,the possible interactions of MgO with alloying elements that may alter the nucleation potency have not been elucidated yet.Herein,we design casting experiments of Mg-xCa alloys varied qualitatively in number density of native MgO,which are then comprehensively studied by advanced electron microscopy.The results show that grain refinement is enhanced as the particle number density of MgO increases.The native MgO particles are modified by interfacial layers due to the co-segregation of Ca and N solute atoms at the MgO/Mg interface.Using aberration-corrected scanning transmission electron microscopy and electron energy loss spectroscopy,we reveal the nature of these Ca/N interfacial layers at the atomic scale.Irrespective of the crystallographic termination of MgO,Ca and N co-segregate at the MgO/Mg interface and occupy Mg and O sites,respectively,forming an interfacial structure of a few atomic layers.The interfacial structure is slightly expanded,less ordered and defective compared to the MgO matrix due to compositional deviations,whereby the MgO substrate is altered as a poorer template to nucleate Mg solid.Upon solidification in a TP-1 mould,the impotent MgO particles account for the grain refining mechanism,where they are suggested to participate into nucleation and grain initiation processes in an explosive manner.This work not only reveals the atomic engineering of a substrate through interfacial segregation but also demonstrates the effectiveness of a strategy whereby native MgO particles can be harnessed for grain refinement in Mg-Ca alloys.

Effect of addition temperature on dispersion behavior and grain refinement efficiency of MgO introduced into Mg alloy

The effect of addition temperature of MgO particles(MgOp)on their dispersion behavior and the efficiency of grain refinement in AZ31 Mg alloy was investigated.In addition,the grain refinement mechanism was systematically studied by microstructure characterization,thermodynamic calculation,and analysis of solidification curves.The results show that the grain size of AZ31 Mg alloy initially decreases and then increases as the MgOp addition temperature is increased from 720 to 810℃,exhibiting a minimum value of 136μm at 780℃.The improved grain refinement efficiency with increasing MgOp addition temperature can be attributed to the reduced Mg melt viscosity and enhanced wettability between MgOp and Mg melt.Furthermore,a corresponding physical model describing the solidification behavior and grain refinement mechanism was proposed.

Evaluation of the Impact of Refined Quality Control Management Model on the Qualified Rate of Disinfection and Sterilization of Surgical Instruments in the Sterilization Supply Center

Objective:To evaluate the application value of a refined quality control management model for a sterilization supply center.Methods:A retrospective analysis was conducted on the work situation of the sterilization supply center from January 2021 to January 2023.The work situation before January 31,2022,was classified as the control group;a routine quality control management model was implemented,and the work situation after January 31,2022,was classified as the observation group.The quality of medical device management and department satisfaction between the two groups were compared.Results:The timely recovery and supply rate,classification and cleaning pass rate,disinfection pass rate,packaging pass rate,sterilization pass rate,and department satisfaction score in the observation group were all higher than those of the control group(P<0.05).Conclusion:Implementing a refined quality control management model in the sterilization supply center can improve the quality management level of medical devices and department satisfaction and is worthy of promotion.

Refined Anam-Net:Lightweight Deep Learning Model for Improved Segmentation Performance of Optic Cup and Disc for Glaucoma Diagnosis

In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR is a reliable measure for the early diagnosis of Glaucoma.In this study,we developed a lightweight DNN model for OC and OD segmentation in retinal fundus images.Our DNN model is based on modifications to Anam-Net,incorporating an anamorphic depth embedding block.To reduce computational complexity,we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network deepens.This modification significantly reduces the number of trainable parameters,making the model lightweight and suitable for resource-constrained applications.We evaluate the performance of the developed model using two publicly available retinal image databases,namely RIM-ONE and Drishti-GS.The results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD segmentation.We used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images,respectively.For OD segmentation using the RIM-ONE we obtain an f1-score(F1),Jaccard coefficient(JC),and overlapping error(OE)of 0.950,0.9219,and 0.0781,respectively.Similarly,for OC segmentation using the same databases,we achieve scores of 0.8481(F1),0.7428(JC),and 0.2572(OE).Based on these experimental results and the significantly lower number of trainable parameters,we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR.

Integrated multi-scale approach combining global homogenization and local refinement for multi-field analysis of high-temperature superconducting composite magnets

Second-generation high-temperature superconducting(HTS)conductors,specifically rare earth-barium-copper-oxide(REBCO)coated conductor(CC)tapes,are promising candidates for high-energy and high-field superconducting applications.With respect to epoxy-impregnated REBCO composite magnets that comprise multilayer components,the thermomechanical characteristics of each component differ considerably under extremely low temperatures and strong electromagnetic fields.Traditional numerical models include homogenized orthotropic models,which simplify overall field calculation but miss detailed multi-physics aspects,and full refinement(FR)ones that are thorough but computationally demanding.Herein,we propose an extended multi-scale approach for analyzing the multi-field characteristics of an epoxy-impregnated composite magnet assembled by HTS pancake coils.This approach combines a global homogenization(GH)scheme based on the homogenized electromagnetic T-A model,a method for solving Maxwell's equations for superconducting materials based on the current vector potential T and the magnetic field vector potential A,and a homogenized orthotropic thermoelastic model to assess the electromagnetic and thermoelastic properties at the macroscopic scale.We then identify“dangerous regions”at the macroscopic scale and obtain finer details using a local refinement(LR)scheme to capture the responses of each component material in the HTS composite tapes at the mesoscopic scale.The results of the present GH-LR multi-scale approach agree well with those of the FR scheme and the experimental data in the literature,indicating that the present approach is accurate and efficient.The proposed GH-LR multi-scale approach can serve as a valuable tool for evaluating the risk of failure in large-scale HTS composite magnets.

Effect of gas blowing nozzle angle on multiphase flow and mass transfer during RH refining process

A three-dimensional mathematical model was developed to investigate the effect of gas blowing nozzle angles on multiphase flow,circulation flow rate,and mixing time during Ruhrstahl-Heraeus(RH) refining process.Also,a water model with a geometric scale of 1:4 from an industrial RH furnace of 260 t was built up,and measurements were carried out to validate the mathematical model.The results show that,with a conventional gas blowing nozzle and the total gas flow rate of 40 L·min^(-1),the mixing time predicted by the mathematical model agrees well with the measured values.The deviations between the model predictions and the measured values are in the range of about 1.3%–7.3% at the selected three monitoring locations,where the mixing time was defined as the required time when the dimensionless concentration is within 3% deviation from the bath averaged value.In addition,the circulation flow rate was 9 kg·s^(-1).When the gas blowing nozzle was horizontally rotated by either 30° or 45°,the circulation flow rate was found to be increased by about 15% compared to a conventional nozzle,due to the rotational flow formed in the up-snorkel.Furthermore,the mixing time at the monitoring point 1,2,and 3 was shortened by around 21.3%,28.2%,and 12.3%,respectively.With the nozzle angle of 30° and 45°,the averaged residence time of 128 bubbles in liquid was increased by around 33.3%.

Impact of early refined nursing program on prognosis of middleaged and elderly patients with cognitive dysfunction combined with cerebral infarction

BACKGROUND Cerebral infarction is a local or extensive necrosis of brain tissue.Subsequently,the corresponding neurological deficits appear.The incidence of cerebrovascular diseases in China is increasing gradually.After the onset of cerebrovascular disease,the most common sequelae include movement disorders,language disorders,and cognitive dysfunction.AIM To investigate the effect of early refined nursing program on the prognosis of middle-aged and elderly patients with cerebral infarction combined with cognitive dysfunction.METHODS A retrospective study was conducted to divide 60 patients with cerebral infarction and cognitive impairment into an experimental group(n=32)and a control group(n=28).The experimental group received early intensive care every day,and the control group received daily routine care.The scores of the Mini-Mental State Examination(MMSE)and the Trail Making Test(TMT),as well as the latency and amplitude of the event-related potential P300,were used as main indicators to evaluate changes in cognitive function,and changes in BDNF,TGF-β,and GDNF expression were used as secondary indicators.RESULTS Both groups experienced notable enhancements in MMSE scores,with the experi-mental group demonstrating higher scores than the control group(experimental:28.75±2.31;control:25.84±2.87).Moreover,reductions in TMT-A and TMT-B scores were observed in both groups(experimental:TMT-A 52.36±6.18,TMT-B 98.47±10.23;control:TMT-A 61.48±7.92,TMT-B 112.63±12.55),with the experimental group displaying lower scores.P300 Latency decreased(experimental:270.63 ms±14.28 ms;control:285.72 ms±16.45 ms),while amplitude increased(experimental:7.82μV±1.05μV;control:6.35μV±0.98μV)significantly in both groups,with superior outcomes in the experimental cohort.Additionally,the levels of the growth factors BDNF,TGF-β1,and GDNF surged(experimental:BDNF 48.37 ng/mL±5.62 ng/mL,TGF-β152.14 pg/mL±4.28 pg/mL,GDNF 34.76 ng/mL±3.89 ng/mL;control:BDNF 42.58 ng/mL±4.73 ng/mL,TGF-β146.23 pg/mL±3.94 pg/mL,GDNF 30.25 ng/mL±2.98 ng/mL)in both groups,with higher levels in the experimental group.CONCLUSION For middle-aged and elderly patients with cerebral infarction and cognitive dysfunction,early refined nursing can significantly improve their cognitive function and prognosis.

Projection-Based Dimensional Reduction of Adaptively Refined Nonlinear Models

Adaptive mesh refinement (AMR) is fairly practiced in the context of high-dimensional, mesh-based computational models. However, it is in its infancy in that of low-dimensional, generalized-coordinate-based computational models such as projection-based reduced-order models. This paper presents a complete framework for projection-based model order reduction (PMOR) of nonlinear problems in the presence of AMR that builds on elements from existing methods and augments them with critical new contributions. In particular, it proposes an analytical algorithm for computing a pseudo-meshless inner product between adapted solution snapshots for the purpose of clustering and PMOR. It exploits hyperreduction—specifically, the energy-conserving sampling and weighting hyperreduction method—to deliver for nonlinear and/or parametric problems the desired computational gains. Most importantly, the proposed framework for PMOR in the presence of AMR capitalizes on the concept of state-local reduced-order bases to make the most of the notion of a supermesh, while achieving computational tractability. Its features are illustrated with CFD applications grounded in AMR and its significance is demonstrated by the reported wall-clock speedup factors.

A REFINEMENT OF THE SCHWARZ-PICK ESTIMATES AND THE CARATHéODORY METRIC IN SEVERAL COMPLEX VARIABLES

In this article,we first establish an asymptotically sharp result on the higher order Fréchet derivatives for bounded holomorphic mappings f(x)=f(0)+∞∑s=1Dskf(0)(x^(sk))/(sk)!:B_(X)→B_(Y),where B_X is the unit ball of X.We next give a sharp result on the first order Fréchet derivative for bounded holomorphic mappings F(X)=F(0+)∞∑s=KD^(s)f(0)(x^(8)/s!):B_(X)→B_(Y),where B_(X)is the unit ball of X.The results that we derive include some results in several complex variables,and extend the classical result in one complex variable to several complex variables.

From“Car Priority”to“People Priority”: Exploring New Ideas for Refined Road Space Design

Roads are crucial public spaces in cities and serve as a window to showcase the city’s characteristics.They serve not only as a means of urban transportation but also as a crucial spatial carrier for urban communication activities and a significant location for meeting the increasing demands of people for a better quality of life.The current road infrastructure prioritizes the right of way for cars,neglecting the design of sidewalks and green belts within the road’s boundaries,and extension spaces between buildings and boundary lines of roads.There is a pressing need to improve street space in response to the demand for development transformation and the creation of a warmer city.This paper summarizes common problems in current road spaces,draws on the experience of excellent urban road spaces in foreign countries,discusses new ideas for the refined design of road spaces based on the transformation of road planning concepts,and suggests a reference standard for guiding detailed design.Simultaneously,the review of road construction will incorporate the detailed design of road space to enhance the role of planning in guiding and controlling the construction of road works.

Long-term Development Prospects and Suggestions for Domestic Refined Oil Market

Over the past decade,China’s refined oil market has experienced considerable growth and fluctuations.Gasoline consumption has generally followed the growth rate of vehicle equipment,with fluctuations influenced by travel frequency;aviation fuel consumption has seen stable growth following the end of COVID-19,while diesel consumption has been affected by multiple factors including demand and policy.With the rapid development of new energy vehicles and alternative fuels,the gasoline and diesel market has essentially peaked,yet domestic production of refined oil continues to grow,leading to an increasingly prominent oversupply issue.To achieve the dual carbon goals,the Chinese government has introduced a series of policies that have a profound impact on the refined oil market.Facing resource surplus and market demand changes,the refining industry needs to optimize production capacity structure,and oil products retail companies face transformation pressure.The article aims to provide market analysis and recommendations,serving as a reference for relevant enterprises and policymakers.

Exploring the Application of Refined Management in University Financial Management

The refined management of university finances primarily involves optimizing management methods and continuously improving financial management levels.This process helps enhance fund utilization efficiency,optimize resource allocation,ensure the rational use of educational funds,and provide solid financial support for the development of teaching,research,and other university undertakings.This paper explores the application of refined management in university financial management.

Simultaneously removal of P and B from Si by Sr and Zr co-addition during Al–Si low-temperature solvent refining

To remove the key impurity elements,P and B,from primary Si simultaneously,Sr and Zr co-addition to Al-Si alloy systems during solvent refining has been investigated.Sr reacts with Al,Si,and P in the melt to form a P-containing Al_(2)Si_(2)Sr phase and Zr reacts with B to form a ZrB_(2) phase.In the Al-Si-Sr-Zr system,high removal fractions of P and B in the primary Si,with 84.8%-98.4%and 90.7%-96.7%,respectively,are achieved at the same time,respectively.The best removal effect is obtained in the sample with the addition of Sr-32000+Zr-3000μg·kg^(-1),and the removal fractions of P and B in the purified Si reach 98.4%and 96.1%.Compared with the Sr/Zr single-addition,the removal effects of Sr and Zr co-addition on P and B do not show a significant downward trend,indicating that the nucleation and growth of the B/P-containing impurity phases are mutually independent.Finally,an evolution model is proposed to describe the nucleation and the growth stages of Sr/Zr-containing compound phases,which reveals the interaction between the impurity phases and the primary Si.

Effect of Refiner Plate Bar Angle and Pulp Properties on the Low Consistency Refining Efficiency in Terms of Power Consumption

Power consumption is the energy source of the impact on fibers or pulp during low-consistency(LC)pulp refining,and the strength of refining affects refining quality and efficiency.The pulp properties,operating parameters,and bar parameters of the refiner plates are important parameters affecting refining efficiency,which can be defined as the ratio of net to total refining power.In this study,LC refining trials for pulps with different consistencies and fiber lengths were conducted using five isometric straightbar plates with different bar angles to explore the influences of the plate bar angle and pulp properties on the no-load power,impact capacity on fibers and refining efficiency.It was found that the no-load power of the LC refining process decreased with an increase in the plate bar angle while increased when pulp with higher consistency was refined under the same refining conditions.However,the effect of pulp consistency on the no-load power can be neglected when refining is conducted using plates with larger bar angles.Meanwhile,a critical bar angle for straight-bar plates in LC refining may exist,which has the strongest impact on the pulp and highest refining efficiency under the same refining conditions.In addition,the impact capacity of the plate on the pulp and refining efficiency in LC refining can be enhanced by appropriately increasing the pulp consistency and average fiber length when the bar angle of the refiner plate with a sector angle of 40°is less than 30°.Therefore,the efficiency and power consumption of the LC refining process can be adjusted by optimizing the pulp consistency and bar parameters of the refining plates.

Status and Trends of China’s Refining and Petrochemical Industry

China’s refining and petrochemical industry has developed rapidly,with the quality of industry development improving rapidly.The scale of oil refining,ethylene,and PX ranks first in the world,and the quality of refined oil is among the world’s leading levels.However,the industry’s profitability is not strong enough,and there are still technological shortcomings,as well as defects in industry structure and product structure.Under the backdrop of the dual carbon goals,energy transition,electric revolution,and demand differentiation,China’s refining and petrochemical industry will continue to exert efforts in energy conservation and consumption reduction,integrated development with new energy,promotion of oil conversion and the conversion of oil to special products,integration and upgrading of capacity,development of green hydrogen refining and CCUS,diversification of raw materials,circular economy,and other aspects to enhance industrial competitiveness.