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.

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.

Development in oxide metallurgy for improving the weldability of high -strength low-alloy steel-Combined deoxidizers and microalloying elements

The mechanisms of oxide metallurgy include inducing the formation of intragranular acicular ferrite(IAF)using micron-sized inclusions and restricting the growth of prior austenite grains(PAGs)by nanosized particles during welding.The chaotically oriented IAF and refined PAGs inhibit crack initiation and propagation in the steel,resulting in high impact toughness.This work summarizes the com-bined effect of deoxidizers and alloying elements,with the aim to provide a new perspective for the research and practice related to im-proving the impact toughness of the heat affected zone(HAZ)during the high heat input welding.Ti complex deoxidation with other strong deoxidants,such as Mg,Ca,Zr,and rare earth metals(REMs),can improve the toughness of the heat-affected zone(HAZ)by re-fining PAGs or increasing IAF contents.However,it is difficult to identify the specific phase responsible for IAF nucleation because ef-fective inclusions formed by complex deoxidation are usually multiphase.Increasing alloying elements,such as C,Si,Al,Nb,or Cr,con-tents can impair HAZ toughness.A high C content typically increases the number of coarse carbides and decreases the potency of IAF formation.Si,Cr,or Al addition leads to the formation of undesirable microstructures.Nb reduces the high-temperature stability of the precipitates.Mo,V,and B can enhance HAZ toughness.Mo-containing precipitates present good thermal stability.VN or V(C,N)is ef-fective in promoting IAF nucleation due to its good coherent crystallographic relationship with ferrite.The formation of the B-depleted zone around the inclusion promotes IAF formation.The interactions between alloying elements are complex,and the effect of adding dif-ferent alloying elements remains to be evaluated.In the future,the interactions between various alloying elements and their effects on ox-ide metallurgy,as well as the calculation of the nucleation effects of effective inclusions using first principles calculations will become the focus of oxide metallurgy.

Corrosion behavior and corrosion products of a low-alloy weathering steel in Qingdao and Wanning

A newly developed low-alloy weathering steel has been exposed in two coastal sites （Qingdao in the north, Wanning in the south） in China for one year. The samples in Wanning corroded far more seriously than those in Qingdao. The rust layer formed on the steel was analyzed by X-ray diffraction （XRD）, scanning electron microscopy （SEM）, N2 adsorption approach, polarization curves, and electrochemical impedance spectroscopy （EIS）. The rust formed in Qingdao contains more X-ray amorphous compounds and is more compact than that formed in Wanning. Cr and Cu are enriched in the rust layer near the steel matrix, and the phenomenon is more obvious in Qingdao than in Wanning. The rust layer formed in Qingdao suppresses the anodic and cathodic reaction more remarkably than that formed in Wanning does. The rust layer formed in Qingdao possesses a higher ability to block the permeation of chloride ions than that formed in Wanning does.

Determining role of heterogeneous microstructure in lowering yield ratio and enhancing impact toughness in high-strength low-alloy steel

Here we present a novel approach of intercritical heat treatment for microstructure tailoring,in which intercritical annealing is introduced between conventional quenching and tempering.This induced a heterogeneous microstructure consisting of soft intercritical ferrite and hard tempered martensite,resulting in a low yield ratio(YR)and high impact toughness in a high-strength low-alloy steel.The initial yielding and subsequent work hardening behavior of the steel during tensile deformation were modified by the presence of soft intercritical ferrite after intercritical annealing,in comparison to the steel with full martensitic microstructure.The increase in YR was related to the reduction in hardness difference between the soft and hard phases due to the precipitation of nano-carbides and the recovery of dislocations during tempering.The excellent low-temperature toughness was ascribed not only to the decrease in probability of microcrack initiation for the reduction of hardness difference between two phases,but also to the increase in resistance of microcrack propagation caused by the high density of high angle grain boundaries.

Dual Phase Heat Treatment of Low-Alloy Steel

Dual phase heat treatment is an economical and effective way for improving the properties of low carbon steels and low-alloy steel materials. In this paper, the microstructures and mechanical properties of 20MnSi steel treated by different dual phase heat treatment have been studied. The results show that dual phase heat treatment with pre-quenching technique and then heating from room temperature to the critical zone can achieve finer and more homogeneous microstructure than that with pre-normalizing technique and then cooling from austenite zone to the critical zone. Among all factors affecting dual phase heat treatment, quenching temperature at the critical zone and tempering temperature play an important part in mechanical properties. Using proper dual phase heat treatment technique with computer optimized parameters, the yield strength, the elongation and impact toughness of 20MnSi can reach 860 MPa, 16% and 207 MPa respectively.

Effect of nanosized NbC precipitates on hydrogen-induced cracking of high-strength low-alloy steel

We investigated the effect of nanosized NbC precipitates on hydrogen-induced cracking(HIC)of high-strength low-alloy steel by conducting slow-strain-rate tensile tests(SSRT)and performing continuous hydrogen charging and fracture analysis.The results reveal that the HIC resistance of Nb-bearing steel is obviously superior to that of Nb-free steel,with the fractured Nb-bearing steel in the SSRT exhibiting a smaller ratio of elongation reduction(Iδ).However,as the hydrogen traps induced by NbC precipitates approach hydrogen saturation,the effect of the precipitates on the HIC resistance attenuate.We speculate that the highly dispersed nanosized NbC precipitates act as irreversible hydrogen traps that hinder the accumulation of hydrogen at potential crack nucleation sites.In addition,much like Nb-free steel,the Nb-bearing steel exhibits both H-solution strengthening and the resistance to HIC.

Susceptibility of two types of low-alloy hull steels to pit initiation

Four low-alloy hull steels with different alloy elements were selected. Theirsusceptibility to pitting corrosion was compared by means of electrochemical polarization test. Theinclusions in the steels and their pitting corrosion characteristics were studied by an electronprobe micro-analyzer (EPMA). The results indicate that some inclusions are the main sources ofpitting corrosion. The susceptibility of nickel-chromium steel to pit initiation is less than thatof manganese steel. Under the same conditions, nickel-chromium steel is easier to passivate thanmanganese steel, and the passive films on nickel-chromium steel surface are more stable than that onmanganese steel. In low-alloy steels, the higher the contents of nickel and chromium, the lower thecritical passive pH value. In the same kind of steel, multi-phase inclusions containing sulfide areeasier to initiate pitting corrosion than other inclusions.

Effect of microstructure variation on the corrosion behavior of high-strength low-alloy steel in 3.5wt% NaCl solution

The effect of microstructure variation on the corrosion behavior of high-strength low-alloy（HSLA） steel was investigated. The protective property of the corrosion product layer was also explored. Experimental results reveal that the type of microstructure has significant effect on the corrosion resistance of HSLA steel. The measurement results of weight loss, potentiodynamic polarization curves, and electrochemical impedance spectroscopy indicate that the steel with acicular ferrite microstructure exhibits the lowest corrosion rate. Martensite exhibits a reduced corrosion resistance compared with polygonal ferrite. It is found that the surface of the acicular ferrite specimen uniformly covered by corrosion products is seemingly denser and more compact than those of the other two microstructures, and can provide some amount of protection to the steel; thus, the charge transfer resistance and modulus values of the acicular ferrite specimen are the largest. However, corrosion products on martensite and polygonal ferrite are generally loose, porous, and defective, and can provide minor protectiveness; thus, the charge transfer resistance values for polygonal ferrite and martensite are lower.

MODELING OF AUSTENITE GRAIN SIZE IN LOW-ALLOY STEEL WELD METAL

The size of austenite grain has significant effects on components and proportions ofvarious ferrites in low-alloy steel weld metal. Therefore, it is important to determinethe size of austenite grain in the weld metal. In this paper, a model based upon thecarbon diffusion rate is developed for computing austenite grain size in low-alloy steelweld metal during continuous cooling. The model takes into account the effects of theweld thermal cycles, inclusion particles and various alloy elements on the austenitegrain growth. The calculating results agree reasonably with those reported experimentalobservations. The model demonstrates a significant promise to understand the weldmicrostructure and properties based on the welding science.

Impact property analysis of weld metal and heat-affected zone for low-alloy carbon steel multi-pass welded joint

Welded joint impact performances of low-alloy carbon steel plates welded by full-automatic gas metal arc welding （GMAW） were evaluated. To clarity the effect of impact temperature on impact properties of weld metal （WM） and heat- affected zone （ HAZ）, Charpy V impact tests at different temperatures and fracture surface analysis were carried out. The Charpy V impact energy decreases with the decreasing test temperature both for the WM and HAZ, while the proportion of crystal zone on WM and HAZ impact fracture surface increases with the decreasing test temperature. Research results indicate that the welding defects （void and slag） make the impact energy of WM more scattered and lower than that of HAZ.

Present situation and countermeasure of low-alloy spring steel wire rod for domestic automobile

The variety,inner quality and surface quality of low-alloy spring steel wire rod for domestic automobile is summarized in detail.And according to commercial low-alloy spring steel wire rod variety, product quality level and its actual application situation on automobile supplied by present industrially developed country metallurgy enterprises,it is pointed that the variety of low-alloy spring steel wire rod for domestic automobile can't satisfy the requirements of automobile industry development,compare with overseas advanced technology,product quality has the following gaps:the first is that steel purity is low,the control level of non-metallic inclusions is not steady,there is often large grain difficult deforming non-deformation inclusions existing,the control level of steel purity has big difference,the level of large steel factory is high,but its steady has a large gap compare with foreign advanced level,not to mention small steel factory which research and development powder is low.The second is surface complete decarburization can' t be avoided completely.The third is that surface defects are more.The fourth is that composition segregation and structure segregation are not steady,steel wire can't be drawn normally when the segregation is serious. In all,the segregation of 55SiCrA is superior to 60Si2MnA obviously.The industrialization of domestic high level low-alloy spring steel wire rod can't seek quick success and instant benefits,independent innovation perseveringly must be adopted,the success may be reached after master core technologies and adopt the science way of step by step.

Effect of Heat Treatment Parameters on the Mechanical and Microstructure Properties of Low-Alloy Steel

This study examines the effect of heat treatment at three different temperatures of 800°C, 950°C and 1100°C on the microstructure and mechanical properties of low-alloy steel with an addition of manganese, chrome and lead. To determine an impact of the applied heat treatment operations, testing of mechanical properties and microstructural examinations of the steel with 0.23%, 0.24%, 0.29% and 0.31% C were conducted. This work shows that the mechanical strengths of the alloy steel are improved with increasing the heat treatment temperature. In addition, the microstructure trends toward recrystallized ferrite grains as the heat treatment temperature increases.

Impact of Mo/Ni alloying on microstructural modulation and low-temperature toughness of high-strength low-alloy steel

The high-strength low-alloy steel plates with varying Ni/Mo contents were manufactured using the thermos-mechanical control process.The investigation was conducted to explore the effect of Ni/Mo microalloying on microstructure evolution and mechanical properties of the steel.The results revealed that the increase in Ni content from 1 to 2 wt.%reduced the transition temperature of ferrite and the growth range of ferritic grain was narrowed,which promoted grain refinement.The optimized combination of grain size,high-angle grain boundaries(HAGBs),and martensite-austenite(M-A)islands parameter contributed to the excellent impact toughness of S1 steel at-100℃(impact absorbed energy of 218.2 J at-100℃).As the Mo increases from 0 to 2 wt.%,the matrix structure changes from multiphase structure to granular bainite,which increases the average effective grain size to~4.62 pm and reduces HAGBs proportion to~36.22%.With these changes,the low-temperature impact toughness of S3 steel is weakened.In addition,based on the analysis of the characteristics of crack propagation path,it was found that M-A islands with low content(~2.21%)and small size(~1.76 pm)significantly retarded crack propagation,and the fracture model of M-A islands with different morphologies was further proposed.Furthermore,correlation between behaviour of delamination and toughness was further analysed by observing delamination size and impact energy parameters.

Multi-performance evaluation of high-throughput accelerated corrosion test for high-strength low-alloy 921A steel

The corrosion behavior of high-strength low-alloy 921A steel in a simulated marine atmospheric environment was studied using a high-throughput experimental method.The corrosion behavior,corrosion morphology,and corrosion products of 921A steels were analyzed using various techniques,including corrosion mass loss method,polarization curve,white-light interferometry,scanning electron microscopy,energy-dispersive spectrometry,microbeam X-ray fluorescence spectrometry,X-ray diffraction technique,and X-ray photoelectron spectroscopy.The test results indicated that 921A steel exhibits better corrosion resistance than Q450NQR1 steel in simulated harsh atmospheric environments,as evidenced by a lower corrosion mass loss rate throughout the corrosion tests.The corrosion products of both steels consisted ofα-FeOOH,Fe_(3)O_(4),andγ-FeOOH,withα-FeOOH being more prevalent in the rust layer of 921A steel than in Q450NQR1 steel.The inner rust layer of 921A steel also exhibited an appositional enrichment region of Cr,Ni,Mo,and V,leading to its superior corrosion resistance compared to that of Q450NQR1 steel.The efficacy of high-throughput accelerated corrosion experimental methods was highlighted for evaluating the corrosion resistance of steel materials in harsh environmental conditions.The findings suggest that 921A steel exhibits better corrosion resistance compared to Q450NQR1 steel and has the potential to be more suitable in harsh marine atmospheric environments.The characterization of the rust layer structures and composition reveals the parallel enrichment of certain elements in the inner rust layer of 921A steel,which enhances its corrosion resistance.

Effect of oxide inclusions on MnS precipitates and tensile mechanical property of high-strength low-alloy steel

The key role of oxide inclusions on the microstructure and mechanical property of a high-strength low-alloy steel was investigated.The field emission scanning electron microscope equipped with energy-dispersive spectrometry was used to characterize MnS precipitates.Oxide inclusions play an important role in the shape control of MnS precipitates.More oxides fovored to decrease the size and the aspect ratio of MnS precipitates.With less oxide inclusions in the steel,approximately over 16.7%MnS precipitates were with aspect ratio a>5 and pure MnS precipitates accounted for 75.9%in number.However,with more oxide inclusions in the steel,only 7.4%MnS precipitates were with a>5 and pure MnS precipitates accounted for 60.1%in number.Refinement of MnS by oxide inclusions improved the strength and inhibited the anisotropy.More oxide inclusions in the steel increased the yield strength and tensile strength of the steel in both longitudinal and transverse directions,and lowered the anisotropy of the mechanical property.

Effect of trace boron on corrosion resistance of rust layer of high-strength low-alloy steel in 3.5 wt.% NaCl solution

The influence mechanism of trace boron on the corrosion resistance of high-strength low-alloy(HSLA)steel in a simulated marine environment was studied by combining first-principles calculation with experiment.The effect of boron on the corrosion properties and corrosion morphology of the rust layer formed on the surface of HSLA steel was studied by means of corrosion weightlessness method,polarization curve,scanning electron microscopy(SEM)and X-ray diffraction(XRD)technique.The mass loss measurements and polarization curves revealed that the corrosion resistance of HSLA steel is improved by adding trace boron.XRD and SEM results show that the rust layer is produced byα-FeOOH(the main protective phase),Fe_(3)O_(4) andγ-FeOOH,and boron contributes to stability ofα-FeOOH.Based on the first-principles calculation,the solid solution of B atom in the corrosion product is beneficial to the fixation of Cl atom and to the reduction of the corrosion of Cl atom to the steel matrix.

Machine learning study on time-temperature-transformation diagram of carbon and low-alloy steel

Time-temperature-transformation(TTT)diagram plays a critical role in designing appropriate heat treatment process of steels by describing the relationship among holding time,temperature,and quantities of phase transformation.Making predictions for TTT diagrams of new steel rapidly and accurately is therefore of much practical importance,especially for costly and time-consuming experimental determination.Here,TTT diagrams for carbon and low-alloy steels were predicted using machine learning methods.Five commonly used machine learning(ML)algorithms,backpropagation artificial neural network(BP network),LibSVM,k-nearest neighbor,Bagging,and Random tree,were adopted to select appropriate models for the prediction.The results illustrate that Bagging is the optimal model for the prediction of pearlite transformation and bainite transformation,and BP network is the optimal model for martensite transformation.Finally,the ML framework composed of Bagging and BP network models was applied to predict the entire TTT diagram.Additionally,the ML models show superior performance on the prediction of testing samples than the commercial software JMatPro.

Identifying facile material descriptors for Charpy impact toughness in low-alloy steel via machine learning

High toughness is highly desired for low-alloy steel in engineering structure applications,wherein Charpy impact toughness(CIT)is a critical factor determining the toughness performance.In the current work,CIT data of low-alloy steel were collected,and then CIT prediction models based on machine learning(ML)algorithms were established.Three feature construction strategies were proposed.One is solely based on alloy composition,another is based on alloy composition and heat treatment parameters,and the last one is based on alloy composition,heat treatment parameters,and physical features.A series of ML methods were used to effectively select models and material descriptors from a large number of al-ternatives.Compared with the strategy solely based on the alloy composition,the strategy based on alloy composition,heat treatment parameters together with physical features perform much better.Finally,a genetic programming(GP)based symbolic regression(SR)approach was developed to establish a physical meaningful formula between the selected features and targeted CIT data.

Static Recrystallization Kinetics Model After Hot Deformation of Low-Alloy Steel Q345B

The static recrystallization behavior of low-alloy steel Q345B during double-pass hot compression deformation tests was investigated in the temperature range of 900-1000 ℃,the true strain range of 0.15-0.25 and the interpass time range of 0.5-50 s on Gleeble-3500 thermo-simulation machine.The results show that static recrystallization during the interpass time is observed.As the deformation temperature and strain increase,softening caused by static recrystallization is obvious.According to the analysis and calculation of thermo-simulation data,the static recrystallization activation energy was obtained and static recrystallization kinetics model was built.Finally,the error analysis of static recrystallization kinetics model proved that the model had good accuracy.Therefore,this model provides a theoretical basis for static recrystallization（SRX）and will contribute to the development of multipass hot rolling process,in order to control the rolling process more accurately.