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.

Recent progress in visualization and digitization of coherent transformation structures and application in high-strength steel

High-strength steels are mainly composed of medium-or low-temperature microstructures,such as bainite or martensite,with coherent transformation characteristics.This type of microstructure has a high density of dislocations and fine crystallographic structural units,which ease the coordinated matching of high strength,toughness,and plasticity.Meanwhile,given its excellent welding perform-ance,high-strength steel has been widely used in major engineering constructions,such as pipelines,ships,and bridges.However,visual-ization and digitization of the effective units of these coherent transformation structures using traditional methods(optical microscopy and scanning electron microscopy)is difficult due to their complex morphology.Moreover,the establishment of quantitative relationships with macroscopic mechanical properties and key process parameters presents additional difficulty.This article reviews the latest progress in microstructural visualization and digitization of high-strength steel,with a focus on the application of crystallographic methods in the development of high-strength steel plates and welding.We obtained the crystallographic data(Euler angle)of the transformed microstruc-tures through electron back-scattering diffraction and combined them with the calculation of inverse transformation from bainite or martensite to austenite to determine the reconstruction of high-temperature parent austenite and orientation relationship(OR)during con-tinuous cooling transformation.Furthermore,visualization of crystallographic packets,blocks,and variants based on actual OR and digit-ization of various grain boundaries can be effectively completed to establish quantitative relationships with alloy composition and key process parameters,thereby providing reverse design guidance for the development of high-strength steel.

Mechanical Behavior and Microstructure Evolution during Tensile Deformation of Twinning Induced Plasticity Steel Processed by Warm Forgings

The mechanical behavior and microstructural evolution of an Fe-30Mn-3Al-3Si twinninginduced plasticity(TWIP)steel processed using warm forging was investigated.It is found that steel processed via warm forging improves comprehensive mechanical properties compared to the TWIP steel processed via cold rolling,with a high tensile strength(R_(m))of 793 MPa,a yield strength(R_(P))of 682 MPa,an extremely large R_(P)/R_(m)ratio as high as 0.86 as well as an excellent elongation rate of 46.8%.The microstructure observation demonstrates that steel processed by warm forging consists of large and elongated grains together with fine,equiaxed grains.Complicated micro-defect configurations were also observed within the steel,including dense dislocation networks and a few coarse deformation twins.As the plastic deformation proceeds,the densities of dislocations and deformation twins significantly increase.Moreover,a great number of slip lines could be observed in the elongated grains.These findings reveal that a much more dramatic interaction between microstructural defect and dislocations glide takes place in the forging sample,wherein the fine and equiaxed grains propagated dislocations more rapidly,together with initial defect configurations,are responsible for enhanced strength properties.Meanwhile,larger,elongated grains with more prevalently activated deformation twins result in high plasticity.

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.

Lap-Shear Performance of Weld-Bonded Mg Alloy and Austenitic Stainless Steel in Three-Sheet Stack-Up

With the growing interest in utilizing Mg and austenitic stainless steel(ASS)in the automotive sector,joining them together in three-sheet configuration is inevitable.However,achieving this task presents considerable challenges due to the large differences in their physical,metallurgical and mechanical properties.To overcome these challenges,the feasibility of using weld-bonding to join Mg alloy/ASS/ASS was investigated.The nugget formation,interface characteristics,microstructure and mechanical properties of the joints were investigated.The results show that the connection between the Mg alloy and upper ASS was achieved through the combined effect of the cured adhesive and weld-brazing in the weld zone.On the other hand,a metallurgical bond was formed at the ASS/ASS interface.The Mg nugget microstructure exhibited fine columar grains composed predominantly of primaryα-Mg grains along with a eutectic mixture ofα-Mg andβ-Mg17Al12.The nugget formed at the ASS/ASS interface consisted largely of columnar grains of austenite,with some equiaxed dendritic grains formed at the centerline of the joint.The weld-bonded joints exhibited an average peak load and energy absorption of about 8.5 kN and 17 J,respectively(the conventional RSW joints failed with minimal or no load application).The failure mode of the joints changed with increasing welding current from interfacial failure via the Mg nugget/upper ASS interface to partial interfacial failure(part of the Mg nugget was pulled out of the Mg sheet).Both failure modes were accompanied by cohesive failure in the adhesive zone.

Nonlinear Study on the Mechanical Performance of Built-Up Cold-Formed Steel Concrete-Filled Columns under Compression

Given their numerous functional and architectural benefits,such as improved bearing capacity and increased resistance to elastic instability modes,cold-formed steel(CFS)built-up sections have become increasingly developed and used in recent years,particularly in the construction industry.This paper presents an analytical and numerical study of assembled CFS two single channel-shaped columns with different slenderness and configurations(backto-back,face-to-face,and box).These columns were joined by double-row rivets for the back-to-back and box configurations,whereas they were welded together for the face-to-face design.The built-up columns were filled with ordinary concrete of good strength.Finite element models were applied,using ABAQUS software,to assess mechanical performance and study the influence of assembly techniques on the behavior of cold-formed columns under axial compression.Analytical approaches based on Eurocode 3 and Eurocode 4 recommendations for un-filled and concrete-filled columns respectively were followed for the numerical analysis,and concrete confinement effects were also considered per American Concrete Institute(ACI)standards for face-to-face and box configurations.The obtained results indicated a good correlation between the numerical results and the proposed analytical methodology which did not exceed 8%.The failure modes showed that the columns failed due to instabilities such as local and global buckling.

Micro defects formation and dynamic response analysis of steel plate of quasi-cracking area subjected to explosive load

As the protective component,steel plate had attracted extensive attention because of frequently threats of explosive loads.In this paper,the evolution of microstructure and the mechanism of damage in the quasi-cracking area of steel plate subjected to explosive load were discussed and the relationships between micro defects and dynamic mechanical response were revealed.After the explosion experiment,five observation points were selected equidistant from the quasi-cracking area of the section of the steel plate along the thickness direction,and the characteristics of micro defects at the observation points were analyzed by optical microscope(OM),scanning electron microscope(SEM) and electron backscattered diffraction(EBSD).The observation result shows that many slip bands(SBs) appeared,and the grain orientation changed obviously in the steel plate,the two were the main damage types of micro defects.In addition,cracks,peeling pits,grooves and other lager micro defects were appeared in the lower area of the plate.The stress parameters of the observation points were obtained through an effective numerical model.The mechanism of damage generation and crack propagation in the quasicracking area were clarified by comparing the specific impulse of each observation point with the corresponding micro defects.The result shows that the generation and expansion of micro defects are related to the stress area(i.e.the upper compression area,the neutral plane area,and the lower tension area).The micro defects gather and expand at the grain boundary,and will become macroscopic damage under the continuous action of tensile stress.Besides,the micro defects at the midpoint of the section of the steel plate in the direction away from the explosion center(i.e.the horizontal direction) were also studied.It was found that the specific impulse at these positions were much smaller than that in the thickness direction,the micro defects were only SBs and a few micro cracks,and the those decreased with the increase of the distance from the explosion center.

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.

Mechanical properties of steel mesh in anchor-mesh support for rocky tunnels

Underground geotechnical engineering encounters persistent challenges in ensuring the stability and safety of surrounding rock structures, particularly within rocky tunnels. Rock reinforcement techniques, including the use of steel mesh, are critical to achieving this goal. However, there exists a knowledge gap regarding the comprehensive understanding of the mechanical behavior and failure mechanisms exhibited by steel mesh under diverse loading conditions. This study thoroughly explored the steel mesh's performance throughout the entire loading-failure process, innovating with detailed analysis and modeling techniques. By integrating advanced numerical modeling with laboratory experiments, the study examines the influence of varying reinforcement levels and geometric parameters on the steel mesh strength and deformation characteristics. Sensitivity analysis, employing gray correlation theory, identifies the key factors affecting the mesh performance, while a BP (Backpropagation) neural network model predicts maximum vertical deformation with high accuracy. The findings underscore the critical role of steel diameter and mesh spacing in optimizing peak load capacity, displacement, and energy absorption, offering practical guidelines for design improvements. The use of a Bayesian Regularization (BR) algorithm further enhances the predictive accuracy compared to traditional methods. This research provides new insights into optimizing steel mesh design for underground applications, offering an innovative approach to enhancing structural safety in geotechnical projects.

Prospects for green steelmaking technology with low carbon emissions in China

The steel industry is a major source of CO_(2) emissions,and thus,the mitigation of carbon emissions is the most pressing challenge in this sector.In this paper,international environmental governance in the steel industry is reviewed,and the current state of development of low-carbon technologies is discussed.Additionally,low-carbon pathways for the steel industry at the current time are proposed,emphasizing prevention and treatment strategies.Furthermore,the prospects of low-carbon technologies are explored from the perspective of transitioning the energy structure to a“carbon-electricity-hydrogen”relationship.Overall,steel enterprises should adopt hydrogen-rich metallurgical technologies that are compatible with current needs and process flows in the short term,based on the carbon substitution with hydrogen(prevention)and the CCU(CO_(2) capture and utilization)concepts(treatment).Additionally,the capture and utilization of CO_(2) for steelmaking,which can assist in achieving short-term emission reduction targets but is not a long-term solution,is discussed.In conclusion,in the long term,the carbon metallurgical process should be gradually supplanted by a hydrogen-electric synergistic approach,thus transforming the energy structure of existing steelmaking processes and attaining near-zero carbon emission steelmaking technology.

Remaining Useful Life for Heavy-Duty Railway Cast Steel Knuckles Based on Crack Growth Behavior with Hypothetical Distributions

The current research on the integrity of critical structures of rail vehicles mainly focuses on the design stage,which needs an effective method for assessing the service state.This paper proposes a framework for predicting the remaining useful life(RUL)of in-service structures with and without visible cracks.The hypothetical distribution and delay time models were used to apply the equivalent crack growth life data of heavy-duty railway cast steel knuckles,which revealed the evolution characteristics of the crack length and life scores of the knuckle under different fracture failure modes.The results indicate that the method effectively predicts the RUL of service knuckles in different failure modes based on the cumulative failure probability curves for different locations and surface crack lengths.This study proposes an RUL prediction framework that supports the dynamic overhaul and state maintenance of knuckle fatigue cracks.

A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational efficiency.As technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process.In this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing accuracy.Initially,features are extracted by the VGG19 convolutional block.Then,after processing through the GAP layer,the extracted features are fed to the SVM classifier for classification.For this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the datasets.The outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS dataset.Similarly,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

Microscopic defects formation and dynamic mechanical response analysis of Q345 steel plate subjected to explosive load

As the basic protective element, steel plate had attracted world-wide attention because of frequent threats of explosive loads. This paper reports the relationships between microscopic defects of Q345 steel plate under the explosive load and its macroscopic dynamics simulation. Firstly, the defect characteristics of the steel plate were investigated by stereoscopic microscope(SM) and scanning electron microscope(SEM). At the macroscopic level, the defect was the formation of cave which was concentrated in the range of 0-3.0 cm from the explosion center, while at the microscopic level, the cavity and void formation were the typical damage characteristics. It also explains that the difference in defect morphology at different positions was the combining results of high temperature and high pressure. Secondly, the variation rules of mechanical properties of steel plate under explosive load were studied. The Arbitrary Lagrange-Euler(ALE) algorithm and multi-material fluid-structure coupling method were used to simulate the explosion process of steel plate. The accuracy of the method was verified by comparing the deformation of the simulation results with the experimental results, the pressure and stress at different positions on the surface of the steel plate were obtained. The simulation results indicated that the critical pressure causing the plate defects may be approximately 2.01 GPa. On this basis, it was found that the variation rules of surface pressure and microscopic defect area of the Q345 steel plate were strikingly similar, and the corresponding mathematical relationship between them was established. Compared with Monomolecular growth fitting models(MGFM) and Logistic fitting models(LFM), the relationship can be better expressed by cubic polynomial fitting model(CPFM). This paper illustrated that the explosive defect characteristics of metal plate at the microscopic level can be explored by analyzing its macroscopic dynamic mechanical response.

Comparative impact behaviours of ultra high performance concrete columns reinforced with polypropylene vs steel fibres

Polypropylene(PP) fibres have primarily used to control shrinkage cracks or mitigate explosive spalling in concrete structures exposed to fire or subjected to impact/blast loads, with limited investigations on capacity improvement. This study unveils the possibility of using PP micro-fibres to improve the impact behaviour of fibre-reinforced ultra-high-performance concrete(FRUHPC) columns. Results show that the addition of fibres significantly improves the impact behaviour of FRUHPC columns by shifting the failure mechanism from brittle shear to favourable flexural failure. The addition of steel or PP fibres affected the impact responses differently. Steel fibres considerably increased the peak impact force(up to 18%) while PP micro-fibres slightly increased the peak(3%-4%). FRUHPC significantly reduced the maximum midheight displacement by up to 30%(under 20°impact) and substantially improved the displacement recovery by up to 100%(under 20° impact). FRUHPC with steel fibres significantly improved the energy absorption while those with PP micro-fibres reduced the energy absorption, which is different from the effect of PP-macro fibre reported in the literature. The optimal fibre content for micro-PP fibres is 1% due to its minimal fibre usage and low peak and residual displacement. This study highlights the potential of FRUHPC as a promising material for impact-resistant structures by creating a more favourable flexural failure mechanism, enhancing ductility and toughness under impact loading, and advancing the understanding of the role of fibres in structural performance.

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.

Effect of deformation parameters on the austenite dynamic recrystallization behavior of a eutectoid pearlite rail steel

Understandings of the effect of hot deformation parameters close to the practical production line on grain refinement are crucial for enhancing both the strength and toughness of future rail steels.In this work,the austenite dynamic recrystallization(DRX)behaviors of a eutectoid pearlite rail steel were studied using a thermo-mechanical simulator with hot deformation parameters frequently employed in rail production lines.The single-pass hot deformation results reveal that the prior austenite grain sizes(PAGSs)for samples with different deformation reductions decrease initially with an increase in deformation temperature.However,once the deformation temperature is beyond a certain threshold,the PAGSs start to increase.It can be attributed to the rise in DRX volume fraction and the increase of DRX grain with deformation temperature,respectively.Three-pass hot deformation results show that the accumulated strain generated in the first and second deformation passes can increase the extent of DRX.In the case of complete DRX,PAGS is predominantly determined by the deformation temperature of the final pass.It suggests a strategic approach during industrial production where part of the deformation reduction in low temperature range can be shifted to the medium temperature range to release rolling mill loads.

Prediction of Hot Deformation Behavior of 7Mo Super Austenitic Stainless Steel Based on Back Propagation Neural Network

The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.

Seismic performance evaluation of hybrid coupled shear wall system with shear and flexural fuse-type steel coupling beams

Replaceable flexural and shear fuse-type coupling beams are used in hybrid coupled shear wall(HCSW)systems,enabling concrete buildings to be promptly recovered after severe earthquakes.This study aimed to analytically evaluate the seismic behavior of flexural and shear fuse beams situated in short-,medium-and high-rise RC buildings that have HCSWs.Three building groups hypothetically located in a high seismic hazard zone were studied.A series of 2D nonlinear time history analyses was accomplished in OpenSees,using the ground motion records scaled at the design basis earthquake level.It was found that the effectiveness of fuses in HCSWs depends on various factors such as size and scale of the building,allowable rotation value,inter-story drift ratio,residual drift quantity,energy dissipation value of the fuses,etc.The results show that shear fuses better meet the requirements of rotations and drifts.In contrast,flexural fuses dissipate more energy,but their sectional stiffness should increase to meet other requirements.It was concluded that adoption of proper fuses depends on the overall scale of the building and on how associated factors are considered.

Robust Particle Swarm Optimization Algorithm for Modeling the Effectof Oxides Thermal Properties on AMIG 304L Stainless Steel Welds

There are several advantages to the MIG(Metal Inert Gas)process,which explains its increased use in variouswelding sectors,such as automotive,marine,and construction.A variant of the MIG process,where the sameequipment is employed except for the deposition of a thin layer of flux before the welding operation,is the AMIG(Activated Metal Inert Gas)technique.This study focuses on investigating the impact of physical properties ofindividual metallic oxide fluxes for 304L stainless steel welding joint morphology and to what extent it can helpdetermine a relationship among weld depth penetration,the aspect ratio,and the input physical properties ofthe oxides.Five types of oxides,TiO_(2),SiO_(2),Fe_(2)O_(3),Cr_(2)O_(3),and Mn_(2)O_(3),are tested on butt joint design withoutpreparation of the edges.A robust algorithm based on the particle swarm optimization(PSO)technique is appliedto optimally tune the models’parameters,such as the quadratic error between the actual outputs(depth and aspectratio),and the error estimated by the models’outputs is minimized.The results showed that the proposed PSOmodel is first and foremost robust against uncertainties in measurement devices and modeling errors,and second,that it is capable of accurately representing and quantifying the weld depth penetration and the weld aspect ratioto the oxides’thermal properties.