Machine Learning Techniques in Predicting Hot Deformation Behavior of Metallic Materials

In engineering practice,it is often necessary to determine functional relationships between dependent and independent variables.These relationships can be highly nonlinear,and classical regression approaches cannot always provide sufficiently reliable solutions.Nevertheless,Machine Learning(ML)techniques,which offer advanced regression tools to address complicated engineering issues,have been developed and widely explored.This study investigates the selected ML techniques to evaluate their suitability for application in the hot deformation behavior of metallic materials.The ML-based regression methods of Artificial Neural Networks(ANNs),Support Vector Machine(SVM),Decision Tree Regression(DTR),and Gaussian Process Regression(GPR)are applied to mathematically describe hot flow stress curve datasets acquired experimentally for a medium-carbon steel.Although the GPR method has not been used for such a regression task before,the results showed that its performance is the most favorable and practically unrivaled;neither the ANN method nor the other studied ML techniques provide such precise results of the solved regression analysis.

Particle Discontinuous Deformation Analysis of Static and Dynamic Crack Propagation in Brittle Material

Crack propagation in brittle material is not only crucial for structural safety evaluation,but also has a wideranging impact on material design,damage assessment,resource extraction,and scientific research.A thorough investigation into the behavior of crack propagation contributes to a better understanding and control of the properties of brittle materials,thereby enhancing the reliability and safety of both materials and structures.As an implicit discrete elementmethod,the Discontinuous Deformation Analysis(DDA)has gained significant attention for its developments and applications in recent years.Among these developments,the particle DDA equipped with the bonded particle model is a powerful tool for predicting the whole process of material from continuity to failure.The primary objective of this research is to develop and utilize the particle DDAtomodel and understand the complex behavior of cracks in brittle materials under both static and dynamic loadings.The particle DDA is applied to several classical crack propagation problems,including the crack branching,compact tensile test,Kalthoff impact experiment,and tensile test of a rectangular plate with a hole.The evolutions of cracks under various stress or geometrical conditions are carefully investigated.The simulated results are compared with the experiments and other numerical results.It is found that the crack propagation patterns,including crack branching and the formation of secondary cracks,can be well reproduced.The results show that the particle DDA is a qualified method for crack propagation problems,providing valuable insights into the fracture mechanism of brittle materials.

Unraveling engineering disturbance effects on deformation in red-bed mudstone railway cuttings:incorporating crack-facilitated moisture diffusion

Red-bed mudstone, prevalent in southwest China, poses a formidable challenge due to its hydrophilic clay minerals, resulting in expansion, deformation, and cracking upon exposure to moisture. This study addresses uplift deformation disasters in high-speed railways by employing a moisture diffusion-deformation-fracture coupling model based on the finite-discrete element method(FDEM). The model integrates the influence of cracks on moisture diffusion. The investigation into various excavation depths reveals a direct correlation between depth and the formation of tensile cracks at the bottom of the railway cutting. These cracks expedite moisture migration, significantly impacting the temporal and spatial evolution of the moisture field. Additionally, crack expansion dominates hygroscopic deformation, with the lateral coordinate of the crack zone determining peak vertical displacement. Furthermore, key factors influencing deformation in railway cuttings, including the swelling factor and initial moisture content at the bottom of the cutting, are explored. The number of tensile and shear cracks increases with greater excavation depth, particularly concerning shear cracks. Higher swelling factors and initial moisture contents result in an increased total number of cracks, predominantly shear cracks. Numerical calculations provide valuable insights, offering a scientific foundation and directional guidance for the precise prevention, control, prediction, and comprehensive treatment of mudstone-related issues in high-speed railways.

An improved strain-softening constitutive model of granite considering the effect of crack deformation

This paper presents an improved strain-softening constitutive model considering the effect of crack deformation based on the triaxial cyclic loading and unloading test results.The improved model assumes that total strain is a combination of plastic,elastic,and crack strains.The constitutive relationship between the crack strain and the stress was further derived.The evolutions of mechanical parameters,i.e.strength parameters,dilation angle,unloading elastic modulus,and deformation parameters of crack,with the plastic strain and confining pressure were studied.With the increase in plastic strain,the cohesion,friction angle,dilation angle,and crack Poisson's ratio initially increase and subsequently decrease,and the unloading elastic modulus and the crack elastic modulus nonlinearly decrease.The increasing confining pressure enhances the strength and unloading elastic modulus,and decreases the dilation angle and Poisson's ratio of the crack.The theoretical triaxial compressive stress-strain curves were compared with the experimental results,and they present a good agreement with each other.The improved constitutive model can well reflect the nonlinear mechanical behavior of granite.

Effect of pre-deformation on the stress corrosion cracking susceptibility of aluminum alloy 2519

The effects of pre-deformation and strain rate on the stress corrosion cracking （SCC） behavior of aluminum alloy 2519 in air and in 3.5% NaCI water solution were investigated by means of slow strain rate tension （SSRT）, scanning electron microscopy （SEM）, and transmission electron microscopy （TEM）. The results indicate that the alloy is susceptible to SCC in 3.5% NaCI water solution and not in air. At the same pre-deformation, the alloy is more susceptible to SCC at 1.33 × 10^-5 s^-1 than at 6.66 × 10^-5 s^-1. Moreover, it is more susceptible to SCC at free pre-deformation than at 10% pre-deformation at the same strain rate. The number of 0 precipitated along the grain boundaries is reduced and distributed discontinuously, at the same time, the precipitate-free zones （PFZ） become narrow and the susceptibility to stress corrosion cracking is reduced after 10% pre-deformation.

Some Observations of Flow Localization and Shear Cracking in Pearlite during Deformation

Flow localization, which is an importantmode of deformation in engineering materi-als, has been the interesting subject ofa number of experimental observationsand theoretical investigations in recentyears. However, the basic mechanism ofthe phenomena is not well understood atpresent. In a tensile test, the initiationand growth of a shear band are often simul-taneous. Therefore, it is rather difficult

Influence of Deformation-Induced Martensite on Stress Corrosion Cracking of AISI 321 Stainless Steel

Specimens of AISI 321 stainless steel (0Cr18Ni9Ti) of various martensile contents were prepared by the low temperature(-70℃) elongation method- X-ray diffraction (XRD) and transmission electron micrograph (TEM) techniques were used to study the phase transition process and its structure. The relationship between deformation-induced martensite and stress corrosion cracking (SCC) susceptibility of the steel in 42% (boiling) MgCl2 solution was investigated using the constant load SCC test with the normalized threshold values. The results reveal that when the α'-martensite content is less than 5% and also in the range of 15%-24 % , the SCC susceptibility of this material decreases with the increase of α'-martensite content.However. whenthe α' martensite content is in the rang of 5% -15% and more than 24%, the SCC susceptibility of this material increases with the increase of the α'-martensite content. The SCC fracture surface of the specimens exhibits a stepped fracture surface and transgranular stress corrosion fracture surface morphology.

Grain Boundary Triple Junction Effects on the Fatigue Deformation and Cracking Behaviors of Copper Tricrystal and Tetracrystals

Cyclic symmetrical tension-compression fatigue tests in an axial plastic strain range of 2.0×10-4 to 1.5×10-3 were performed on three copper tetracrystal specimens containing two grain boundary triple lines as well as one copper tricrystal specimen employing a multiple step method. Experimental results show that the strengthening effect of triple junction (TJ) on axial saturation stress increased with increasing plastic strain amplitude. The strengthening effects owe much to the strain incompatibilities at TJ. The cyclic stress-strain (CSS) curves of tetracrystals are higher than that of tricrystal. At low strain amplitude, deformation at TJ is smaller than that near grain boundary (GB), which results in that the width of TJ effect zone is smaller than that near GB. Whether GB split or not is associated with the angle between GB and loading axis, activation of slip systems beside GB and the accommodation and annihilation of residual dislocations on GB planes.

Recent research progress in the mechanism and suppression of fusion welding-induced liquation cracking of nickel based superalloys

Nickel-based superalloys are extensively used in the crucial hot-section components of industrial gas turbines,aeronautics,and astronautics because of their excellent mechanical properties and corrosion resistance at high temperatures.Fusion welding serves as an effective means for joining and repairing these alloys;however,fusion welding-induced liquation cracking has been a challenging issue.This paper comprehensively reviewed recent liquation cracking,discussing the formation mechanisms,cracking criteria,and remedies.In recent investigations,regulating material composition,changing the preweld heat treatment of the base metal,optimizing the welding process parameters,and applying auxiliary control methods are effective strategies for mitigating cracks.To promote the application of nickel-based superalloys,further research on the combination impact of multiple elements on cracking prevention and specific quantitative criteria for liquation cracking is necessary.

Exploring an eco-friendly approach to improve soil tensile behavior and cracking resistance

Soil tensile strength is a critical parameter governing the initiation and propagation of tensile cracking.This study proposes an eco-friendly approach to improve the tensile behavior and crack resistance of clayey soils.To validate the feasibility and efficacy of the proposed approach,direct tensile tests were employed to determine the tensile strength of the compacted soil with different W-OH treatment concentrations and water contents.Desiccation tests were also performed to evaluate the effectiveness of W-OH treatment in enhancing soil tensile cracking resistance.During this period,the effects of W-OH treatment concentration and water content on tensile properties,soil suction and microstructure were investigated.The tensile tests reveal that W-OH treatment has a significant impact on the tensile strength and failure mode of the soil,which not only effectively enhances the tensile strength and failure displacement,but also changes the brittle failure behavior into a more ductile quasi-brittle failure behavior.The suction measurements and mercury intrusion porosimetry(MIP)tests show that W-OH treatment can slightly reduce soil suction by affecting skeleton structure and increasing macropores.Combined with the microstructural analysis,it becomes evident that the significant improvement in soil tensile behavior through W-OH treatment is mainly attributed to the W-OH gel's ability to provide additional binding force for bridging and encapsulating the soil particles.Moreover,desiccation tests demonstrate that W-OH treatment can significantly reduce or even inhibit the formation of soil tensile cracking.With the increase of W-OH treatment concentration,the surface crack ratio and total crack length are significantly reduced.This study enhances a fundamental understanding of eco-polymer impacts on soil mechanical properties and provides valuable insight into their potential application for improving soil crack resistance.

Deformation monitoring of long-span railway bridges based on SBAS-InSAR technology

The deformation monitoring of long-span railway bridges is significant to ensure the safety of human life and property.The interferometric synthetic aperture radar(In SAR)technology has the advantage of high accuracy in bridge deformation monitoring.This study monitored the deformation of the Ganjiang Super Bridge based on the small baseline subsets(SBAS)In SAR technology and Sentinel-1A data.We analyzed the deformation results combined with bridge structure,temperature,and riverbed sediment scouring.The results are as follows:(1)The Ganjiang Super Bridge area is stable overall,with deformation rates ranging from-15.6 mm/yr to 10.7 mm/yr(2)The settlement of the Ganjiang Super Bridge deck gradually increases from the bridge tower toward the main span,which conforms to the typical deformation pattern of a cable-stayed bridge.(3)The sediment scouring from the riverbed cause the serious settlement on the bridge’s east side compared with that on the west side.(4)The bridge deformation negatively correlates with temperature,with a faster settlement at a higher temperature and a slow rebound trend at a lower temperature.The study findings can provide scientific data support for the health monitoring of long-span railway bridges.

Application of GNSS-PPP on Dynamic Deformation Monitoring of Offshore Platforms

The real-time dynamic deformation monitoring of offshore platforms under environmental excitation is crucial to their safe operation.Although Global Navigation Satellite System-Precise Point Positioning(GNSS-PPP)has been considered for this purpose,its monitoring accuracy is relatively low.Moreover,the influence of background noise on the dynamic monitoring accuracy of GNSS-PPP remains unclear.Hence,it is imperative to further validate the feasibility of GNSS-PPP for deformation monitoring of offshore platforms.To address these concerns,vibration table tests with different amplitudes and frequencies are conducted.The results demonstrate that GNSS-PPP can effectively monitor horizontal vibration displacement as low as±30 mm,which is consistent with GNSS-RTK.Furthermore,the spectral characteristic of background noise in GNSS-PPP is similar to that of GNSS-RTK(Real Time Kinematic).Building on this observation,an improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)has been proposed to de-noise the data and enhance the dynamic monitoring accuracy of GNSS-PPP.Field monitoring application research is also undertaken,successfully extracting and analyzing the dynamic deformation of an offshore platform structure under environmental excitation using GNSS-PPP monitoring in conjunction with improved CEEMDAN de-noising.By comparing the de-noised dynamic deformation trajectories of the offshore platform during different periods,it is observed that the platform exhibits reversible alternating vibration responses under environmental excitation,with more pronounced displacement deformation in the direction of load action.The research results confirm the feasibility and potential of GNSS-PPP for dynamic deformation monitoring of offshore platforms.

Violent collisions can reveal hexadecapole deformation of nuclei

A new observable in heavy ion collision experiments was identified to be sensitive to the hexadecapole deformation of the colliding nuclei.Such deformation is difficult to measure in traditional nuclear electric transition measurements,as it is often overwhelmed by the nuclear quadrupole deformation.This opens the door to gain new insight into nuclear structure with experiments that were designed to study hot and dense nuclear matter.

Spatiotemporal deformation characteristics of Outang landslide and identification of triggering factors using data mining

Since the impoundment of Three Gorges Reservoir(TGR)in 2003,numerous slopes have experienced noticeable movement or destabilization owing to reservoir level changes and seasonal rainfall.One case is the Outang landslide,a large-scale and active landslide,on the south bank of the Yangtze River.The latest monitoring data and site investigations available are analyzed to establish spatial and temporal landslide deformation characteristics.Data mining technology,including the two-step clustering and Apriori algorithm,is then used to identify the dominant triggers of landslide movement.In the data mining process,the two-step clustering method clusters the candidate triggers and displacement rate into several groups,and the Apriori algorithm generates correlation criteria for the cause-and-effect.The analysis considers multiple locations of the landslide and incorporates two types of time scales:longterm deformation on a monthly basis and short-term deformation on a daily basis.This analysis shows that the deformations of the Outang landslide are driven by both rainfall and reservoir water while its deformation varies spatiotemporally mainly due to the difference in local responses to hydrological factors.The data mining results reveal different dominant triggering factors depending on the monitoring frequency:the monthly and bi-monthly cumulative rainfall control the monthly deformation,and the 10-d cumulative rainfall and the 5-d cumulative drop of water level in the reservoir dominate the daily deformation of the landslide.It is concluded that the spatiotemporal deformation pattern and data mining rules associated with precipitation and reservoir water level have the potential to be broadly implemented for improving landslide prevention and control in the dam reservoirs and other landslideprone areas.

Effect of Hot Deformation on Formation and Growth of Thermal Fatigue Crackin Chromium Wear Resistant Cast Iron

The formation and growth of thermal fatigue crack in chromium wear resistant cast iron was investigated, and the effect of hot deformation on the crack was analyzed by means of optical microscope and scanning electron microscope and high frequency induction thermal fatigue tester. The results show that eutectic carbide is the main location and passage for initiation and extension of thermal fatigue cracks, hot deformation can improve the eutectic carbiders morphology and distribution, inhibit the generation and propagation of thermal fatigue cracks. In the experiment, the propagation rate of thermal fatigue crack reduces with the quantity of hot deformation increasing, which was analyzed in the point view of the activation energy of crack propagation.

Effect of icosahedral phase formation on the stress corrosion cracking(SCC)behaviors of the as-cast Mg-8%Li(in wt.%)based alloys

Through exploring the stress corrosion cracking(SCC)behaviors of the as-cast Mg-8%Li and Mg-8%Li-6%Zn-1.2%Y alloys in a 0.1 M NaCl solution,it revealed that the SCC susceptibility index(I_(SCC))of the Mg-8%Li alloy was 47%,whilst the I_(SCC)of the Mg-8%Li-6%Zn-1.2%Y alloy was 68%.Surface,cross-sectional and fractography observations indicated that for the Mg-8%Li alloy,theα-Mg/β-Li interfaces acted as the preferential crack initiation sites and propagation paths during the SCC process.With regard to the Mg-8%Li-6%Zn-1.2%Y alloy,the crack initiation sites included the I-phase and the interfaces of I-phase/β-Li andα-Mg/β-Li,and the preferential propagation paths were the I-phase/β-Li andα-Mg/β-Li interfaces.Moreover,the SCC of the two alloys was concerned with hydrogen embrittlement(HE)mechanism.

Thermally-induced cracking behaviors of coal reservoirs subjected to cryogenic liquid nitrogen shock

The benefits of using cryogenic liquid nitrogen shock to enhance coal permeability have been confirmed from experimental perspectives.In this paper,we develop a fully coupled thermo-elastic model in combination with the strain-based isotropic damage theory to uncover the cooling-dominated cracking behaviors through three typical cases,i.e.coal reservoirs containing a wellbore,a primary fracture,and a natural fracture network,respectively.The progressive cracking processes,from thermal fracture initiation,propagation or cessation,deflection,bifurcation to multi-fracture interactions,can be well captured by the numerical model.It is observed that two hierarchical levels of thermal fractures are formed,in which the number of shorter thermal fractures consistently exceeds that of the longer ones.The effects of coal properties related to thermal stress levels and thermal diffusivity on the fracture morphology are quantified by the fracture fractal dimension and the statistical fracture number.The induced fracture morphology is most sensitive to changes in the elastic modulus and thermal expansion coefficient,both of which dominate the complexity of the fracture networks.Coal reservoir candidates with preferred thermal-mechanical properties are also recommended for improving the stimulation effect.Further findings are that there exists a critical injection temperature and a critical in-situ stress difference,above which no thermal fractures would be formed.Preexisting natural fractures with higher density and preferred orientations are also essential for the formation of complex fracture networks.The obtained results can provide some theoretical support for cryogenic fracturing design in coal reservoirs.

Deformation Characteristics of Hydrate-Bearing Sediments

The safe and efficient development of natural gas hydrate requires a deep understanding of the deformation behaviors of reservoirs.In this study,a series of triaxial shearing tests are carried out to investigate the deformation properties of hydrate-bearing sediments.Variations of volumetric and lateral strains versus hydrate saturation are analyzed comprehensively.Results indicate that the sediments with high hydrate saturation show dilative behaviors,which lead to strain-softening characteristics during shearing.The volumetric strain curves have a tendency to transform gradually from dilatation to compression with the increase in effective confining pressure.An easy prediction model is proposed to describe the relationship between volumetric and axial strains.The model coefficientβis the key dominating factor for the shape of volumetric strain curves and can be determined by the hydrate saturation and stress state.Moreover,a modified model is established for the calculation of lateral strain.The corresponding determination method is provided for the easy estimation of model coefficients for medium sand sediments containing hydrate.This study provides a theoretical and experimental reference for deformation estimation in natural gas hydrate development.

Origin of nucleation and growth of extension twins in grains unsuitably oriented for twinning during deformation of Mg-1%Al

A large number of anomalous extension twins,with low or even negative twinning Schmid factors,were found to nucleate and grow in a strongly textured Mg-1Al alloy during tensile deformation along the extruded direction.The deformation mechanisms responsible for this behaviour were investigated through in-situ electron back-scattered diffraction,grain reference orientation deviation,and slip trace-modified lattice rotation.It was found that anomalous extension twins nucleated mainly at the onset of plastic deformation at or near grain boundary triple junctions.They were associated with the severe strain incompatibility between neighbour grains as a result from the differentbasal slip-induced lattice rotations.Moreover,the anomalous twins were able to grow with the applied strain due to the continuous activation ofbasal slip in different neighbour grains,which enhanced the strain incompatibility.These results reveal the complexity of the deformation mechanisms in Mg alloys at the local level when deformed along hard orientations.

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.