Enhanced prediction of anisotropic deformation behavior using machine learning with data augmentation

Mg alloys possess an inherent plastic anisotropy owing to the selective activation of deformation mechanisms depending on the loading condition.This characteristic results in a diverse range of flow curves that vary with a deformation condition.This study proposes a novel approach for accurately predicting an anisotropic deformation behavior of wrought Mg alloys using machine learning(ML)with data augmentation.The developed model combines four key strategies from data science:learning the entire flow curves,generative adversarial networks(GAN),algorithm-driven hyperparameter tuning,and gated recurrent unit(GRU)architecture.The proposed model,namely GAN-aided GRU,was extensively evaluated for various predictive scenarios,such as interpolation,extrapolation,and a limited dataset size.The model exhibited significant predictability and improved generalizability for estimating the anisotropic compressive behavior of ZK60 Mg alloys under 11 annealing conditions and for three loading directions.The GAN-aided GRU results were superior to those of previous ML models and constitutive equations.The superior performance was attributed to hyperparameter optimization,GAN-based data augmentation,and the inherent predictivity of the GRU for extrapolation.As a first attempt to employ ML techniques other than artificial neural networks,this study proposes a novel perspective on predicting the anisotropic deformation behaviors of wrought Mg alloys.

Evolution of microstructure and properties of a novel Ni-based superalloy during stress relief annealing

We discussed the decrease in residual stress,precipitation evolution,and mechanical properties of GH4151 alloy in different annealing temperatures,which were studied by the scanning electron microscope(SEM),high-resolution transmission electron microscopy(HRTEM),and electron backscatter diffraction(EBSD).The findings reveal that annealing processing has a significant impact on diminishing residual stresses.As the annealing temperature rose from 950 to 1150℃,the majority of the residual stresses were relieved from 60.1 MPa down to 10.9 MPa.Moreover,the stress relaxation mechanism transitioned from being mainly controlled by dislocation slip to a combination of dislocation slip and grain boundary migration.Meanwhile,the annealing treatment promotes the decomposition of the Laves,accompanied by the precipitation ofμ-(Mo_(6)Co_(7))starting at 950℃ and reaching a maximum value at 1050℃.The tensile strength and plasticity of the annealing alloy at 1150℃ reached the maximum(1394 MPa,56.1%)which was 131%,200%fold than those of the as-cast alloy(1060 MPa,26.6%),but the oxidation process in the alloy was accelerated at 1150℃.The enhancement in durability and flexibility is primarily due to the dissolution of the brittle phase,along with the shape and dispersal of theγ′phase.

Achieving High Strength and Tensile Ductility in Pure Nickel by Cryorolling with Subsequent Low-Temperature Short-Time Annealing

Ultra fine-grained pure metals and their alloys have high strength and low ductility.In this study,cryorolling under different strains followed by low-temperature short-time annealing was used to fabricate pure nickel sheets combining high strength with good ductility.The results show that,for different cryorolling strains,the uniform elongation was greatly increased without sacrificing the strength after annealing.A yield strength of 607 MPa and a uniform elongation of 11.7%were obtained after annealing at a small cryorolling strain(ε=0.22),while annealing at a large cryorolling strain(ε=1.6)resulted in a yield strength of 990 MPa and a uniform elongation of 6.4%.X-ray diffraction(XRD),transmission electron microscopy(TEM),scanning electron microscopy(SEM),and electron backscattered diffraction(EBSD)were used to characterize the microstructure of the specimens and showed that the high strength could be attributed to strain hardening during cryorolling,with an additional contribution from grain refinement and the formation of dislocation walls.The high ductility could be attributed to annealing twins and micro-shear bands during stretching,which improved the strain hardening capacity.The results show that the synergistic effect of strength and ductility can be regulated through low-temperature short-time annealing with different cryorolling strains,which provides a new reference for the design of future thermo-mechanical processes.

Efficient Removal of Phosphate from Aqueous Solutions Using Corundum-hollow-spheres Supported Caclined Hydrotalcite Porous Thin Films

Phosphate was removed from aqueous environment by corundum-hollow-spheres supported caclined hydrotalcite (cHT) thin films. Mg-Al-CO3 hydrotalcite (HT) thin films were deposited on corundumhollow-sphere substrates by hydrothermal homogeneous precipitation at 120℃for 30-240 min and cHT thin films were obtained by annealing of the HT thin films at 500℃for 180 min. Their crystal phase, morphology and microstructure were characterized by X-ray diffraction (XRD) and scanning electron microscopy (SEM).The results show that homogeneous, well-crystallized and hierarchical flower-like thin films were deposited firmly on the surface of the corundum. The mechanism of nucleation and growth of the HT thin films was fitted well with the anion coordination polyhedron growth unit model. To determine the absorption of phosphate by this adsorbent, different bed depth (10-30 cm) and flow rate (1.0-3.0 m L/min) were examined by column experiments. The highest removal efficiency of phosphate amounted to 98.5%under optimum condition (pH=7.2). The adsorption capacity increased as the bed depth increased and decreased as the flow rate increased.

Developing kNN forest data imputation for Catalonia

The combined use of LiDAR(Light Detection And Ranging)scanning and field inventories can provide spatially continuous wall-to-wall information on forest characteristics.This information can be used in many ways in forest mapping,scenario analyses,and forest manage-ment planning.This study aimed to find the optimal way to obtain continuous forest data for Catalonia when using kNN imputation(kNN stands for“k nearest neighbors”).In this method,data are imputed to a certain location from k field-measured sample plots,which are the most similar to the location in terms of LiDAR metrics and topographic variables.Weighted multidimensional Euclidean distance was used as the similarity measure.The study tested two different methods to optimize the distance measure.The first method optimized,in the first step,the set of LiDAR and topographic variables used in the measure,as well as the transformations of these variables.The weights of the selected variables were optimized in the second step.The other method optimized the variable set as well as their transformations and weights in one single step.The two-step method that first finds the variables and their transfor-mations and subsequently optimizes their weights resulted in the best imputation results.In the study area,the use of three to five nearest neighbors was recommended.Altitude and latitude turned out to be the most important variables when assessing the similarity of two locations of Catalan forests in the context of kNN data imputation.The optimal distance measure always included both LiDAR metrics and topographic variables.The study showed that the optimal similarity measure may be different for different regions.Therefore,it was suggested that kNN data imputation should always be started with the optimization of the measure that is used to select the k nearest neighbors.

Effect of annealing treatment on the microstructure and mechanical properties of warm-rolled Mg-Zn-Gd-Ca-Mn alloys

The basal texture of traditional magnesium alloy AZ31 is easy to form and exhibits poor plasticity at room temperature.To address these problems,a multi-micro-alloyed high-plasticity Mg-1.8Zn-0.8Gd-0.1Ca-0.2Mn(wt%)alloy was developed using the unique role of rare earth and Ca solute atoms.In addition,the influence of the annealing process on the grain size,second phase,texture,and mechanical properties of the warm-rolled sheet at room temperature was analyzed with the goal of developing high-plasticity mag-nesium alloy sheets and obtaining optimal thermal-mechanical treatment parameters.The results show that the annealing temperature has a significant effect on the microstructure and properties due to the low alloying content:there are small amounts of larger-sized block and long string phases along the rolling direction(RD),as well as several spherical and rodlike particle phases inside the grains.With increas-ing annealing temperature,the grain size decreases and then increases,and the morphology,number,and size of the second phase also change correspondingly.The particle phase within the grains vanishes at 450℃,and the grain size increases sharply.In the full recrystal-lization stage at 300-350℃,the optimum strength-plasticity comprehensive mechanical properties are presented,with yield strengths of 182.1 and 176.9 MPa,tensile strengths of 271.1 and 275.8 MPa in the RD and transverse direction(TD),and elongation values of 27.4%and 32.3%,respectively.Moreover,there are still some larger-sized phases in the alloy that influence its mechanical properties,which offers room for improvement.

Achievable hole concentration at room temperature as a function of Mg concentration for MOCVD-grown p-GaN after sufficient annealing

Relationship between the hole concentration at room temperature and the Mg doping concentration in p-GaN grown by MOCVD after sufficient annealing was studied in this paper.Different annealing conditions were applied to obtain sufficient activation for p-GaN samples with different Mg doping ranges.Hole concentration,resistivity and mobility were characterized by room-temperature Hall measurements.The Mg doping concentration and the residual impurities such as H,C,O and Si were measured by secondary ion mass spectroscopy,confirming negligible compensations by the impurities.The hole concentration,resistivity and mobility data are presented as a function of Mg concentration,and are compared with literature data.The appropriate curve relating the Mg doping concentration to the hole concentration is derived using a charge neutrality equation and the ionized-acceptor-density[N-(A)^(-)](cm^(−3))dependent ionization energy of Mg acceptor was determined asE_(A)^(Mg)=184−2.66×10^(−5)×[N_(A)^(-)]1/3 meV.

Quantum control based on three forms of Lyapunov functions

This paper introduces the quantum control of Lyapunov functions based on the state distance, the mean of imaginary quantities and state errors.In this paper, the specific control laws under the three forms are given.Stability is analyzed by the La Salle invariance principle and the numerical simulation is carried out in a 2D test system.The calculation process for the Lyapunov function is based on a combination of the average of virtual mechanical quantities, the particle swarm algorithm and a simulated annealing algorithm.Finally, a unified form of the control laws under the three forms is given.

Dual-physical network PVA hydrogel commensurate with articular cartilage bearing lubrication enabled by harnessing nanoscale crystalline domains

Hydrogel, as one of potential soft materials for articular cartilage, has encountered pressing obstacles, such as insufficient mechanical properties, poor lubrication, and easy to wear. To tackle these, we propose a strong yet slippery polyvinyl alcohol/chitosan (PVA/CS) hydrogel with dual-physically crosslinked networks by harnessing freeze-thawing, salting-out, annealing, and rehydration. High mechanical properties of PVA/CS hydrogel can be readily regulated by adjusting proportion of PVA/CS and annealing temperature. The optimized hydrogel exhibits high mechanical properties with tensile strength of ∼ 19 MPa at strain of 550%, compression strength of ∼ 11 MPa at small strain of 39%, and outstanding toughness and antifatigue owing to the robust physical interactions, including hydrogen bonds, crystallization, and ionic coordination. Moreover, the equilibrium hydrogel shows low friction coefficient of ∼ 0.05 against Al_(2)O_(3) ball under the condition of 30 N, 1 Hz, with water as the tribological medium, which is close to the lubrication performance of native cartilage. And meanwhile, the proposed cartilage-like slippery hydrogel displays stable long-term lubrication performance for 1 × 10^(5) reciprocating cycles without destructive wear and structure damage. It is therefore believed that the biocompatible cartilage-like slippery hydrogel opens innovative scenarios for developing cartilage-mimicking water-lubricated coating and biomedical implants with satisfactory load-bearing and lubrication performance.

Effect of annealing on the electrical performance of N-polarity GaN Schottky barrier diodes

A nitrogen-polarity(N-polarity)GaN-based high electron mobility transistor(HEMT)shows great potential for high-fre-quency solid-state power amplifier applications because its two-dimensional electron gas(2DEG)density and mobility are mini-mally affected by device scaling.However,the Schottky barrier height(SBH)of N-polarity GaN is low.This leads to a large gate leakage in N-polarity GaN-based HEMTs.In this work,we investigate the effect of annealing on the electrical characteristics of N-polarity GaN-based Schottky barrier diodes(SBDs)with Ni/Au electrodes.Our results show that the annealing time and tem-perature have a large influence on the electrical properties of N-polarity GaN SBDs.Compared to the N-polarity SBD without annealing,the SBH and rectification ratio at±5 V of the SBD are increased from 0.51 eV and 30 to 0.77 eV and 7700,respec-tively,and the ideal factor of the SBD is decreased from 1.66 to 1.54 after an optimized annealing process.Our analysis results suggest that the improvement of the electrical properties of SBDs after annealing is mainly due to the reduction of the inter-face state density between Schottky contact metals and N-polarity GaN and the increase of barrier height for the electron emis-sion from the trap state at low reverse bias.

Purification of copper foils driven by single crystallization

High-purity copper(Cu) with excellent thermal and electrical conductivity, is crucial in modern technological applications, including heat exchangers, integrated circuits, and superconducting magnets. The current purification process is mainly based on the zone/electrolytic refining or anion exchange, however, which excessively relies on specific integrated equipment with ultra-high vacuum or chemical solution environment, and is also bothered by external contaminants and energy consumption. Here we report a simple approach to purify the Cu foils from 99.9%(3N) to 99.99%(4N) by a temperature-gradient thermal annealing technique, accompanied by the kinetic evolution of single crystallization of Cu.The success of purification mainly relies on(i) the segregation of elements with low effective distribution coefficient driven by grain-boundary movements and(ii) the high-temperature evaporation of elements with high saturated vapor pressure.The purified Cu foils display higher flexibility(elongation of 70%) and electrical conductivity(104% IACS) than that of the original commercial rolled Cu foils(elongation of 10%, electrical conductivity of ~ 100% IACS). Our results provide an effective strategy to optimize the as-produced metal medium, and therefore will facilitate the potential applications of Cu foils in precision electronic products and high-frequency printed circuit boards.

Residual stress modeling of mitigated fused silica damage sites with CO_(2)laser annealing

A numerical model based on measured fictive temperature distributions is explored to evaluate the residual stress fields of CO_(2)laser-annealed mitigated fused silica damage sites.The proposed model extracts the residual strain from the differences in thermoelastic contraction of fused silica with different fictive temperatures from the initial frozen-in temperatures to ambient temperature.The residual stress fields of mitigated damage sites for the CO_(2)laser-annealed case are obtained by a finite element analysis of equilibrium equations and constitutive equations.The simulated results indicate that the proposed model can accurately evaluate the residual stress fields of laser-annealed mitigated damage sites with a complex thermal history.The calculated maximum hoop stress is in good agreement with the reported experimental result.The estimated optical retardance profiles from the calculated radial and hoop stress fields are consistent with the photoelastic measurements.These results provide sufficient evidence to demonstrate the suitability of the proposed model for describing the residual stresses of mitigated fused silica damage sites after CO_(2)laser annealing.

Effect of annealing temperature on microstructure and mechanical properties of Mg-Zn-Zr-Nd alloy with large final rolling deformation

In this study,the Mg-3Zn-0.5Zr-χNd(χ=0,0.6)alloys were subjected to final rolling treatment with large deformation of 50%.The impact of annealing temperatures on the microstructure and mechanical properties was investigated.The rolled Mg-3Zn-0.5Zr-0.6Nd alloy exhibited an ultimate tensile strength of 386 MPa,a yield strength of 361 MPa,and an elongation of 7.1%.Annealing at different temperatures resulted in reduced strength and obviously increased elongation for both alloys.Optimal mechanical properties for the Mg-3Zn-0.5Zr-0.6Nd alloy were achieved after annealing at 200℃,with an ultimate tensile strength of 287 MPa,a yield strength of 235 MPa,and an elongation of 26.1%.The numerous deformed microstructures,twins,and precipitated phases in the rolled alloy could impede the deformation at room temperature and increase the work hardening rate.After annealing,a decrease in the work hardening effect and an increase in the dynamic recovery effect were obtained due to the formation of fine equiaxed grains,and the increased volume fraction of precipitated phases,which significantly improved the elongation of the alloy.Additionally,the addition of Nd element could enhance the annealing recrystallization rate,reduce the Schmid factor difference between basal and prismatic slip systems,facilitate multi-system slip initiation and improve the alloy plasticity.

Expediting carbon dots synthesis by the active adaptive method with machine learning and applications in dental diagnosis and treatment

Synthesis of functional nanostructures with the least number of tests is paramount towards the propelling materials development. However, the synthesis method containing multivariable leads to high uncertainty, exhaustive attempts, and exorbitant manpower costs. Machine learning (ML) burgeons and provokes an interest in rationally designing and synthesizing materials. Here, we collect the dataset of nano-functional materials carbon dots (CDs) on synthetic parameters and optical properties. ML is applied to assist the synthesis process to enhance photoluminescence quantum yield (QY) by building the methodology named active adaptive method (AAM), including the model selection, max points screen, and experimental verification. An interactive iteration strategy is the first time considered in AAM with the constant acquisition of the furnished data by itself to perfect the model. CDs exhibit a strong red emission with QY up to 23.3% and enhancement of around 200% compared with the pristine value obtained through the AAM guidance. Furthermore, the guided CDs are applied as metal ions probes for Co^(2+) and Fe^(3+), with a concentration range of 0–120 and 0–150 µM, and their detection limits are 1.17 and 0.06 µM. Moreover, we also apply CDs for dental diagnosis and treatment using excellent optical ability. It can effectively detect early caries and treat mineralization combined with gel. The study shows that the error of experiment verification gradually decreases and QY improves double with the effective feedback loops by AAM, suggesting the great potential of utilizing ML to guide the synthesis of novel materials. Finally, the code is open-source and provided to be referenced for further investigation on the novel inorganic material prediction.

考虑混合工艺的自动化码头多设备资源协同调度优化模型和算法设计

Considering the uncertainty of the speed of horizontal transportation equipment,a cooperative scheduling model of multiple equipment resources in the automated container terminal was constructed to minimize the completion time,thus improving the loading and unloading efficiencies of automated container terminals.The proposed model integrated the two loading and unloading processes of“double-trolley quay crane+AGV+ARMG”and“single-trolley quay crane+container truck+ARMG”and then designed the simulated annealing particle swarm algorithm to solve the model.By comparing the results of the particle swarm algorithm and genetic algorithm,the algorithm designed in this paper could effectively improve the global and local space search capability of finding the optimal solution.Furthermore,the results showed that the proposed method of collaborative scheduling of multiple equipment resources in automated terminals considering hybrid processes effectively improved the loading and unloading efficiencies of automated container terminals.The findings of this study provide a reference for the improvement of loading and unloading processes as well as coordinated scheduling in automated terminals.

Bonding enhancement of cold rolling TA1 P-Ti/AA6061 composite plates via surface oxidation treatment

TA1 P-Ti/AA6061 composite plate was produced by oxidizing the surface of the titanium plate and adopting a cold roll bonding process.The results revealed that the oxide film(Ti6O)prepared on the surface of TA1 pure titanium was easy to crack during the cold roll bonding,thereby promoting the formation of an effective mechanical interlock at the interface,which can effectively reduce the minimum reduction rate of the composite plates produced by cold rolling of titanium and aluminium plates.Moreover,the composite plate subjected to oxidation treatment exhibited high shear strength,particularly at a 43%reduction rate,achieving a commendable value of 117 MPa.Based on oxidation treatment and different reduction rates,the annealed composite plates at temperatures of 400,450,and 500°C displayed favorable resistance to interface delamination,highlighting their remarkable strength-plasticity compatibility as evidenced by a maximum elongation of 31.845%.

Enhanced Differentiable Architecture Search Based on Asymptotic Regularization

In differentiable search architecture search methods,a more efficient search space design can significantly improve the performance of the searched architecture,thus requiring people to carefully define the search space with different complexity according to various operations.Meanwhile rationalizing the search strategies to explore the well-defined search space will further improve the speed and efficiency of architecture search.With this in mind,we propose a faster and more efficient differentiable architecture search method,AllegroNAS.Firstly,we introduce a more efficient search space enriched by the introduction of two redefined convolution modules.Secondly,we utilize a more efficient architectural parameter regularization method,mitigating the overfitting problem during the search process and reducing the error brought about by gradient approximation.Meanwhile,we introduce a natural exponential cosine annealing method to make the learning rate of the neural network training process more suitable for the search procedure.Moreover,group convolution and data augmentation are employed to reduce the computational cost.Finally,through extensive experiments on several public datasets,we demonstrate that our method can more swiftly search for better-performing neural network architectures in a more efficient search space,thus validating the effectiveness of our approach.

In-situ study of the microstructure evolution during tension of a Mg-Y-Zn-Al alloy processed by rapidly solidified ribbon consolidation technique

Mg-Y-Zn-Al alloys processed by rapidly solidified ribbon consolidation(RSRC)technique exhibit an exceptional mechanical performance indicating promising application potential.This material has a bimodal microstructure consisting of fine recrystallized and coarse non-recrystallized grains with solute-rich stacking faults forming cluster arranged layers(CALs)and nanoplates(CANaPs),or complete long period stacking ordered(LPSO)phase.In order to reveal the deformation mechanisms,in-situ synchrotron X-ray diffraction line profile analysis was employed for a detailed study of the dislocation arrangement created during tension in Mg-0.9%Zn-2.05%Y-0.15%Al(at%)alloy.For uncovering the effect of the initial microstructure on the mechanical performance,additional samples were obtained by annealing of the as-consolidated specimen at 300 and 400℃ for 2 h.The heat treatment at 300℃ had no significant effect on the initial microstructure,its evolution during tension and,thus,the overall deformation behavior under tensile loading.On the other hand,annealing at 400℃ resulted in a significant increase of the recrystallized grains fraction and a decrease of the dislocation density,leading to only minor degradation of the mechanical strength.The maximum dislocation density at the failure of the samples corresponding to the plastic strain of 10-25% was estimated to be about 16-20×10^(14)m^(-2).The diffraction profile analysis indicated that most dislocations formed during tension were of non-basal and pyramidal types,what was also in agreement with the Schmid factor values revealed independently from orientation maps.It was also shown that the dislocation-induced Taylor hardening was much lower below the plastic strain of 3% than above this value,which was explained by a model of the interaction between prismatic dislocations and CANaPs/LPSO plates.

Application of DSAPSO Algorithm in Distribution Network Reconfiguration with Distributed Generation

With the current integration of distributed energy resources into the grid,the structure of distribution networks is becoming more complex.This complexity significantly expands the solution space in the optimization process for network reconstruction using intelligent algorithms.Consequently,traditional intelligent algorithms frequently encounter insufficient search accuracy and become trapped in local optima.To tackle this issue,a more advanced particle swarm optimization algorithm is proposed.To address the varying emphases at different stages of the optimization process,a dynamic strategy is implemented to regulate the social and self-learning factors.The Metropolis criterion is introduced into the simulated annealing algorithm to occasionally accept suboptimal solutions,thereby mitigating premature convergence in the population optimization process.The inertia weight is adjusted using the logistic mapping technique to maintain a balance between the algorithm’s global and local search abilities.The incorporation of the Pareto principle involves the consideration of network losses and voltage deviations as objective functions.A fuzzy membership function is employed for selecting the results.Simulation analysis is carried out on the restructuring of the distribution network,using the IEEE-33 node system and the IEEE-69 node system as examples,in conjunction with the integration of distributed energy resources.The findings demonstrate that,in comparison to other intelligent optimization algorithms,the proposed enhanced algorithm demonstrates a shorter convergence time and effectively reduces active power losses within the network.Furthermore,it enhances the amplitude of node voltages,thereby improving the stability of distribution network operations and power supply quality.Additionally,the algorithm exhibits a high level of generality and applicability.

XPS Studies on Electroless As-Deposited and Annealed Ni-P Films

Electroless deposition has been used to deposit Ni-P films on glass slides using the reducing agent sodium hypophosphite. This has been done with a purpose to use Ni-P films as back contact for silicon carbide radiation detectors. By keeping deposition time, temperature, pH and concentration of the precursor solution constant, the film deposition has been done. XPS studies were done to analyze the composition and stoichiometry of Ni-P thin films.