Prediction model for corrosion rate of low-alloy steels under atmospheric conditions using machine learning algorithms

This work constructed a machine learning(ML)model to predict the atmospheric corrosion rate of low-alloy steels(LAS).The material properties of LAS,environmental factors,and exposure time were used as the input,while the corrosion rate as the output.6 dif-ferent ML algorithms were used to construct the proposed model.Through optimization and filtering,the eXtreme gradient boosting(XG-Boost)model exhibited good corrosion rate prediction accuracy.The features of material properties were then transformed into atomic and physical features using the proposed property transformation approach,and the dominant descriptors that affected the corrosion rate were filtered using the recursive feature elimination(RFE)as well as XGBoost methods.The established ML models exhibited better predic-tion performance and generalization ability via property transformation descriptors.In addition,the SHapley additive exPlanations(SHAP)method was applied to analyze the relationship between the descriptors and corrosion rate.The results showed that the property transformation model could effectively help with analyzing the corrosion behavior,thereby significantly improving the generalization ability of corrosion rate prediction models.

Effect of temperature and time on the precipitation ofκ-carbides in Fe-28Mn-10Al-0.8C low-density steels:Aging mechanism and its impact on material properties

In low-density steel,κ-carbides primarily precipitate in the form of nanoscale particles within austenite grains.However,their precipitation within ferrite matrix grains has not been comprehensively explored,and the second-phase evolution mechanism during aging remains unclear.In this study,the crystallographic characteristics and morphological evolution ofκ-carbides in Fe-28Mn-10Al-0.8C(wt%)low-density steel at different aging temperatures and times and the impacts of these changes on the steels’microhardness and properties were comprehensively analyzed.Under different heat treatment conditions,intragranularκ-carbides exhibited various morpho-logical and crystallographic characteristics,such as acicular,spherical,and short rod-like shapes.At the initial stage of aging,acicularκ-carbides primarily precipitated,accompanied by a few spherical carbides.κ-Carbides grew and coarsened with aging time,the spherical carbides were considerably reduced,and rod-like carbides coarsened.Vickers hardness testing demonstrated that the material’s hardness was affected by the volume fraction,morphology,and size ofκ-carbides.Extended aging at higher temperatures led to an increase in carbide size and volume fraction,resulting in a gradual rise in hardness.During deformation,the primary mechanisms for strengthening were dislocation strengthening and second-phase strengthening.Based on these findings,potential strategies for improving material strength are proposed.

Critical precipitation behavior of MnTe inclusions in resulfurized steels during solidification

Te treatment is an effective method for modifying sulfide inclusions,and MnTe precipitation has an important effect on thermal brittleness and steel corrosion resistance.In most actual industrial applications of Te treatment,MnTe precipitation is unexpected.The critical precipitation behavior of MnTe inclusions was investigated through scanning electron microscopy,transmission electron microscopy,machine learning,and first-principles calculation.MnTe preferentially precipitated at the container mouth for sphere-like sulfides and at the interface between MnS grain boundaries and steel matrix for rod-like sulfides.The MnS/MnTe interface was semicoherent.A composition transition zone with a rock-salt structure exhibiting periodic changes existed to maintain the semicoherent interface.The critical precipitation behavior of MnTe inclusions in resulfurized steels involved three stages at varying temperatures.First,Mn(S,Te)precipitated during solidification.Second,MnTe with a rock-salt structure precipitated from Mn(S,Te).Third,MnTe with a hexagonal NiAs structure transformed from the rock-salt structure.The solubility of Te in MnS decreased with decreasing temperature.The critical precipitation behavior of MnTe inclusions in resulfurized steels was related to the MnS precipitation temperature.With the increase in MnS precipitation temperature,the critical Te/S weight ratio decreased.In consideration of the cost-effectiveness of Te addition for industrial production,the Te content in resulfurized steels should be controlled in accordance with MnS precipitation temperature and S content.

Electromagnetic responses on microstructures of duplex stainless steels based on 3D cellular and electromagnetic sensor finite element models

Microstructures determine mechanical properties of steels,but in actual steel product process it is difficult to accurately control the microstructure to meet the requirements.General microstructure characterization methods are time consuming and results are not rep-resentative for overall quality level as only a fraction of steel sample was selected to be examined.In this paper,a macro and micro coupled 3D model was developed for nondestructively characterization of steel microstructures.For electromagnetic signals analysis,the relative permeability value computed by the micro cellular model can be used in the macro electromagnetic sensor model.The effects of different microstructure components on the relative permeability of duplex stainless steel(grain size,phase fraction,and phase distribu-tion)were discussed.The output inductance of an electromagnetic sensor was determined by relative permeability values and can be val-idated experimentally.The findings indicate that the inductance value of an electromagnetic sensor at low frequency can distinguish dif-ferent microstructures.This method can be applied to real-time on-line characterize steel microstructures in process of steel rolling.

Review on the plastic instability of medium -Mn steels for identifying the formation mechanisms of Lüders and Portevin -Le Chatelier bands

Plastic instability,including both the discontinuous yielding and stress serrations,has been frequently observed during the tensile deformation of medium-Mn steels(MMnS)and has been intensively studied in recent years.Unfortunately,research results are controversial,and no consensus has been achieved regarding the topic.Here,we first summarize all the possible factors that affect the yielding and flow stress serrations in MMnS,including the morphology and stability of austenite,the feature of the phase interface,and the deformation parameters.Then,we propose a universal mechanism to explain the conflicting experimental results.We conclude that the discontinuous yielding can be attributed to the lack of mobile dislocation before deformation and the rapid dislocation multiplication at the beginning of plastic deformation.Meanwhile,the results show that the stress serrations are formed due to the pinning and depinning between dislocations and interstitial atoms in austenite.Strain-induced martensitic transformation,influenced by the mechanical stability of austenite grain and deformation parameters,should not be the intrinsic cause of plastic instability.However,it can intensify or weaken the discontinuous yielding and the stress serrations by affecting the mobility and density of dislocations,as well as the interaction between the interstitial atoms and dislocations in austenite grains.

Interplay between temperature-dependent strengthening mechanisms and mechanical stability in high-performance austenitic stainless steels

The effects of deformation temperature on the transformation-induced plasticity(TRIP)-aided 304L,twinning-induced plasti-city(TWIP)-assisted 316L,and highly alloyed stable 904L austenitic stainless steels were compared for the first time to tune the mechan-ical properties,strengthening mechanisms,and strength-ductility synergy.For this purpose,the scanning electron microscopy(SEM),electron backscattered diffraction(EBSD),X-ray diffraction(XRD),tensile testing,work-hardening analysis,and thermodynamics calcu-lations were used.The induced plasticity effects led to a high temperature-dependency of work-hardening behavior in the 304L and 316L stainless steels.As the deformation temperature increased,the metastable 304L stainless steel showed the sequence of TRIP,TWIP,and weakening of the induced plasticity mechanism;while the disappearance of the TWIP effect in the 316L stainless steel was also observed.However,the solid-solution strengthening in the 904L superaustenitic stainless steel maintained the tensile properties over a wide temper-ature range,surpassing the performance of 304L and 316L stainless steels.In this regard,the dependency of the total elongation on the de-formation temperature was less pronounced for the 904L alloy due to the absence of additional plasticity mechanisms.These results re-vealed the importance of solid-solution strengthening and the associated high friction stress for superior mechanical behavior over a wide temperature range.

A review on the multi-scaled structures and mechanical/thermal properties of tool steels fabricated by laser powder bed fusion additive manufacturing

The laser powder bed fusion(LPBF) process can integrally form geometrically complex and high-performance metallic parts that have attracted much interest,especially in the molds industry.The appearance of the LPBF makes it possible to design and produce complex conformal cooling channel systems in molds.Thus,LPBF-processed tool steels have attracted more and more attention.The complex thermal history in the LPBF process makes the microstructural characteristics and properties different from those of conventional manufactured tool steels.This paper provides an overview of LPBF-processed tool steels by describing the physical phenomena,the microstructural characteristics,and the mechanical/thermal properties,including tensile properties,wear resistance,and thermal properties.The microstructural characteristics are presented through a multiscale perspective,ranging from densification,meso-structure,microstructure,substructure in grains,to nanoprecipitates.Finally,a summary of tool steels and their challenges and outlooks are introduced.

Progress in weldability research of duplex stainless steels

Duplex stainless steels(DSSs)show better corrosion resistance with higher strength than traditional austenite stainless steels in many aggressive environments,and can be welded properly with almost every welding processes,if proper heat input is provided.Progresses of research works on weldability of DSSs in recent years are reviewed in this paper.Balance control of ferrite/austenite phases is most important for DSSs welding.The phases balance can be controlled with filler materials,nitrogen addition in shielding gas,heat input,post weld heat treatment,and alternating magnetic field.Too high cooling rate results in not only extra ferrite,but also chromium nitride precipitation.While too low cooling rate or heating repeatedly results in precipitation of secondary austenite and intermetallic compounds.In both situations,mechanical properties and corrosion resistance of the DSS joints deteriorate.Recommended upper and lower limits of heat input and maximum interpass temperature should be observed.

A Physical Core-Loss Model for Laminated Magnetic Sheet Steels

A full-frequency instant core-loss equation built from the induction physical model of magnetic materials, where the iron loss, eddy loss, and hysteresis loss no longer have an integral term, and this new equation provides high simulation accuracy and performs dynamic core loss analysis on non-sinusoidal or pulse magnetic fields. The simulation examples use a high-grade electrical steel sheet 65CS400 by Epstein experimental data covering magnetic field 0.1 - 1.8 T and frequency 50 - 5000 Hz, and the average error of the simulated core loss is less than 4%. Since the simulation is converged by magnetic physical parameters, so the physical relevance of the similar laminated materials can be compared with the coefficient results. .

Effect of Ni content on the weldability of middle-chromium hyperpure ferritic stainless steels 00Cr21Ti

Excellent weldability substantially contributes to the intrinsic quality of steels,while appropriate chemical composition plays a primary role in the essential weldability of steels.The poor weldability of ferritic stainless steels could be improved through modification with minor alloy elements while minimally increasing the cost.Therefore,studying the effect of minor alloy elements on the weldability of steels is of considerable importance.In this study,several steels of middle-chromium hyperpure ferritic stainless 00Cr21Ti with different Ni content(0.3%,0.5%,0.8%,and 1.0%)were developed,and their weldabilities of butt joint samples welded using the metal inert gas welding process,including the influence of welded joints on the microstructure,tensile performance,corrosion resistance,and fatigue property,were investigated.Results show that the steels with w(Ni)≥0.8%exhibit excellent mechanical properties compared with those with low-Ni content steels,further,their impact toughness at normal atmospheric temperature meets the industrial application standard and the fatigue property is similar to that of 304 austenitic stainless steel.Moreover,results show that the corrosion resistance of all the samples is almost at the same level.The results acquired in this study are supposed to be useful for the optimization of the chemical composition of stainless steels aiming to improve weldability.

Advances in machine learning-and artificial intelligence-assisted material design of steels

With the rapid development of artificial intelligence technology and increasing material data,machine learning-and artificial intelligence-assisted design of high-performance steel materials is becoming a mainstream paradigm in materials science.Machine learning methods,based on an interdisciplinary discipline between computer science,statistics and material science,are good at discovering correlations between numerous data points.Compared with the traditional physical modeling method in material science,the main advantage of machine learning is that it overcomes the complex physical mechanisms of the material itself and provides a new perspective for the research and development of novel materials.This review starts with data preprocessing and the introduction of different machine learning models,including algorithm selection and model evaluation.Then,some successful cases of applying machine learning methods in the field of steel research are reviewed based on the main theme of optimizing composition,structure,processing,and performance.The application of machine learning methods to the performance-oriented inverse design of material composition and detection of steel defects is also reviewed.Finally,the applicability and limitations of machine learning in the material field are summarized,and future directions and prospects are discussed.

Development and prospects of molten steel deoxidation in steelmaking process

In the long traditional process of steelmaking,excess oxygen is blown into the converter,and alloying elements are used for deoxidation.This inevitably results in excessive deoxidation of products remaining within the steel liquid,affecting the cleanliness of the steel.With the increasing requirements for steel performance,reducing the oxygen content in the steel liquid and ensuring its high cleanliness is necessary.After more than a hundred years of development,the total oxygen content in steel has been reduced from approximately 100×10^(-6)to approximately 10×10^(-6),and it can be controlled below 5×10^(-6)in some steel grades.A relatively stable and mature deoxidation technology has been formed,but further reducing the oxygen content in steel is no longer significant for improving steel quality.Our research team developed a deoxidation technology for bearing steel by optimizing the entire conventional process.The technology combines silicon–manganese predeoxidation,ladle furnace diffusion deoxidation,and vacuum final deoxidation.We successfully conducted industrial experiments and produced interstitial-free steel with natural decarbonization predeoxidation.Non-aluminum deoxidation was found to control the oxygen content in bearing steel to between 4×10^(-6) and 8×10^(-6),altering the type of inclusions,eliminating large particle Ds-type inclusions,improving the flowability of the steel liquid,and deriving a higher fatigue life.The natural decarbonization predeoxidation of interstitial-free steel reduced aluminum consumption and production costs and significantly improved the quality of cast billets.

Energy absorption characteristics of novel high-strength and hightoughness steels used for rock support

Nowadays,the development of novel metallic materials for rock support have attracted research interests since they can significantly improve the deformation and energy absorption capacities of rock bolts.Although previous studies proved the importance and mechanical advantages of utilizing high-strength and high-toughness(HSHT)steels in rock support,there is no systematic analysis to reveal the essential energy absorption parameter and the guidelines for further development of metallic rock support materials.This paper analyzes the energy absorption characteristics of novel HSHT steels(negative Poisson’s ratio(NPR)and twinning-induced plasticity(TWIP)steels)in comparison with conventional rock support materials.A physically based crystal plasticity(CP)model was set up and calibrated to study the effect of strain hardening rate(SHR).Meanwhile,the roles of underlying physical mechanisms,i.e.the dislocation density and twin volume fraction,were studied.The results show that the improvement of energy absorption density(EAD)is essential for further development of rock support materials,besides the increase of energy absorption rate(EAR)for previous development of conventional rock support materials.The increase of EAD requires increases of both strength and deformation capacity of materials.For HSHT steels,the decrease of SHR has a positive effect on the improvement of EAD.In addition,the increase of EAD is followed by the increase of twin volume fraction and the decrease of plastic Poisson’s ratio which can promote deformation plasticity of materials.Meanwhile,the increase of EAR is correlated with the accumulation of dislocation density,which can increase the strength of materials.This paper provides the theoretical basis and guidelines for developing rock support materials in deep underground engineering and other related fields.

Interfacial reaction between AZ91D magnesium alloy melt and mild steel under high temperature

The metallurgical quality control of magnesium(Mg)and Mg alloys in melting process is required to ensure a satisfied mechanical and corrosion performance,while the typical used steel crucible introduces impurities and interfacial interaction during melting process.Therefore,a systematic study about impurities diffusion and interfacial interaction between molten Mg and steel is necessary.In the present study,the interfacial reaction between molten AZ91D Mg alloy and mild steel during melting process was investigated with the melting temperatures of 700℃,750℃ and 800℃.The results show that Al(Fe,Mn)intermetallic layer is the intermetallic primarily formed at the interfaces of AZ91D melt and mild steel.Meanwhile,Al_(8)(Mn,Fe)5is indexed between Al(Fe,Mn)and AZ91D.AlFe_(3)C appears between the mild steel and Al(Fe,Mn)at 700℃ and 750℃,but absent at 800℃ due to the increased solubility of carbon in Mg matrix.It is found that the growth of the intermetallic layer is controlled by diffusion mechanism,and Al and Mn are the dominant diffusing species in the whole interfacial reaction process.By measuring the thickness of different layers,the growth constant was calculated.It increases from 1.89(±0.03)×10^(-12)m^(2)·s^(-1)at 700℃ to 3.05(±0.05)×10^(-12)m^(2)·s^(-1)at 750℃,and 5.18(±0.05)×10^(-12)m^(2)·s^(-1)at 800℃.Meanwhile,the content of Fe is linearly increased in AZ91D with the increase of holding time at 700℃ and 750℃,while it shows a significantly increment after holding for 8 h at 800℃,indicating holding temperature is more crucial to determine the Fe content of AZ91D than holding time.

Stress-assisted corrosion mechanism of 3Ni steel by using gradient boosting decision tree machining learning method

Traditional 3Ni weathering steel cannot completely meet the requirements for offshore engineering development,resulting in the design of novel 3Ni steel with the addition of microalloy elements such as Mn or Nb for strength enhancement becoming a trend.The stress-assisted corrosion behavior of a novel designed high-strength 3Ni steel was investigated in the current study using the corrosion big data method.The information on the corrosion process was recorded using the galvanic corrosion current monitoring method.The gradi-ent boosting decision tree(GBDT)machine learning method was used to mine the corrosion mechanism,and the importance of the struc-ture factor was investigated.Field exposure tests were conducted to verify the calculated results using the GBDT method.Results indic-ated that the GBDT method can be effectively used to study the influence of structural factors on the corrosion process of 3Ni steel.Dif-ferent mechanisms for the addition of Mn and Cu to the stress-assisted corrosion of 3Ni steel suggested that Mn and Cu have no obvious effect on the corrosion rate of non-stressed 3Ni steel during the early stage of corrosion.When the corrosion reached a stable state,the in-crease in Mn element content increased the corrosion rate of 3Ni steel,while Cu reduced this rate.In the presence of stress,the increase in Mn element content and Cu addition can inhibit the corrosion process.The corrosion law of outdoor-exposed 3Ni steel is consistent with the law based on corrosion big data technology,verifying the reliability of the big data evaluation method and data prediction model selection.

Characteristics and Weldability of Resistance Plug Welding of Dissimilar Steels

TRIP980 high-strength steel plate/SPCC low-carbon steel plate were welded by RPW. The key factors such as size and material of filler were studied, and the structure, fusion ratio and mechanical properties of the RPW joint were analyzed. The experimental results show that the calculation formulas of the length and diameter of the filler were designed reasonably. Q235 as a filler for RPW of TRIP980 high-strength steel plate/SPCC low-carbon steel plate is suitable according to schaeffler organization chart. The deposited metal of RPW joint is in the shape of “spool”,and the base metal and cap of deposited metal are alternately combined. The deposited metal has the characteristics of “locking” as rivets, which is beneficial to the improvement of mechanical properties of RPW joint. The nugget of RPW joint is uniform without deviates. TRIP980 high-strength steel plate, SPCC low-carbon steel plate, and filler were metallurgically bonded in the RPW joint.

Flow characteristics and hot workability of a typical low-alloy high-strength steel during multi-pass deformation

Heavy components of low-alloy high-strength(LAHS) steels are generally formed by multi-pass forging. It is necessary to explore the flow characteristics and hot workability of LAHS steels during the multi-pass forging process, which is beneficial to the formulation of actual processing parameters. In the study, the multi-pass hot compression experiments of a typical LAHS steel are carried out at a wide range of deformation temperatures and strain rates. It is found that the work hardening rate of the experimental material depends on deformation parameters and deformation passes, which is ascribed to the impacts of static and dynamic softening behaviors. A new model is established to describe the flow characteristics at various deformation passes. Compared to the classical Arrhenius model and modified Zerilli and Armstrong model, the newly proposed model shows higher prediction accuracy with a confidence level of 0.98565. Furthermore, the connection between power dissipation efficiency(PDE) and deformation parameters is revealed by analyzing the microstructures. The PDE cannot be utilized to reflect the efficiency of energy dissipation for microstructure evolution during the entire deformation process, but only to assess the efficiency of energy dissipation for microstructure evolution in a specific deformation parameter state.As a result, an integrated processing map is proposed to better study the hot workability of the LAHS steel, which considers the effects of instability factor(IF), PDE, and distribution and size of grains. The optimized processing parameters for the multi-pass deformation process are the deformation parameters of 1223–1318 K and 0.01–0.08 s^(-1). Complete dynamic recrystallization occurs within the optimized processing parameters with an average grain size of 18.36–42.3 μm. This study will guide the optimization of the forging process of heavy components.

Improving creep strength of the fine-grained heat-affected zone of novel 9Cr martensitic heat-resistant steel via modified thermo-mechanical treatment

The infamous type Ⅳ failure within the fine-grained heat-affected zone (FGHAZ) in G115 steel weldments seriously threatens the safe operation of ultra-supercritical (USC) power plants.In this work,the traditional thermo-mechanical treatment was modified via the replacement of hot-rolling with cold rolling,i.e.,normalizing,cold rolling,and tempering (NCT),which was developed to improve the creep strength of the FGHAZ in G115 steel weldments.The NCT treatment effectively promoted the dissolution of preformed M_(23)C_(6)particles and relieved the boundary segregation of C and Cr during welding thermal cycling,which accelerated the dispersed reprecipitation of M_(23)C_(6) particles within the fresh reaustenitized grains during post-weld heat treatment.In addition,the precipitation of Cu-rich phases and MX particles was promoted evidently due to the deformation-induced dislocations.As a result,the interacting actions between precipitates,dislocations,and boundaries during creep were reinforced considerably.Following this strategy,the creep rupture life of the FGHAZ in G115 steel weldments can be prolonged by 18.6%,which can further push the application of G115 steel in USC power plants.

Comparative research on the formability of several ultra-high-strength steels

Three kinds of ultra-high-strength steels are subjected to uniaxial tensile,forming limit,and hole expansion tests to characterize their material forming properties.Results show that the elongation of S1500 reaches 12.9%and is higher than that of MS1500 with the same strength grade but is lower than that of QP980.The forming limit of S1500 steel is higher than that of MS1500 but lower than that of QP980.The instantaneous n-value of the material changes with the volume fraction of retained austenite.The hole expansion ratios of S1500,MS1500,and QP980 steels are 31.3%,32.2%,and 28.3%,respectively.The hole expansion ratio of QP steel increases slightly with the increase in strength grade.This behavior is contrary to the change trend of elongation and forming limit.Among the three kinds of materials,QP980 steel has the best global formability,and S1500 steel has better global formability than martensitic steel with a similar strength grade.The local formability of the materials improves slightly with the decrease in the amount of retained austenite.MS1500 may have the best local formability in accordance with engineering practice.

Effect of Chromium-enhanced Diffusivity on Reverted Transformation in Metastable Austenitic Stainless Steels:Theoretical Calculation and Experiment

Effects of nucleation sites and diffusivity enhancement of chromium on reverted transformation of AISI 304 stainless steel during annealing process were investigated.Dynamics calculation revealed that the reverted transformation of strain-inducedα’-martensite→γaustenite could were closely associated with active nucleation sites and diffusivity enhancement of chromium in nanocrystallineα’-martensite.The experimental data and the results were in accordance with 2-grain austenite/α’-martensite junctions calculated theoretically,which could result from high chromium diffusion rate in nanocrystallineα’-martensite.In addition,low temperature is not conducive to reversed transformation,while high temperature and long annealing time will lead to inhomogeneous grain size distribution.