STUDY ON PROPERTY PREDICTION FOR SEALING ALLOYS

This paper describes a model of property prediction for alloys using the mapping function and self-learning ability of artificial neural network. By learning from experimental data, the neural network induces the relationship between composition, processing and properties of alloys, and predicts the properties with given composition and processing parameters of new alloys.The verification of sealing alloys demonstrates that the artificial neural network is an effective method for materials design and properties prediction.

Advanced deep learning methods for molecular property prediction

The prediction of molecular properties is a crucial task in the field of drug discovery.Computational methods that can accurately predict molecular properties can significantly accelerate the drug discovery process and reduce the cost of drug discovery.In recent years,iterative updates in computing hardware and the rise of deep learning have created a new and effective path for molecular property prediction.Deep learning methods can leverage the vast amount of data accumulated over the years in drug discovery and do not require complex feature engineering.in this review,we summarize molecular representations and commonly used datasets in molecular property prediction models and present advanced deep learning methods for molecular property prediction,including state-of-the-art deep learning networks such as graph neural networks and Transformer-based models,as well as state-of-the-art deep learning strategies such as 3D pre-train,contrastive learning,multi-task learning,transfer learning,and meta-learning.We also point out some critical issues such as lack of datasets,low information utilization,and lack of specificity for diseases.

Mechanical Property Prediction of Strip Model Based on PSO-BP Neural Network

Mechanical property prediction of hot rolled strip is one of the hotspots in material processing research. To avoid the local infinitesimal defect and slow constringency in pure BP algorithm, a kind of global optimization algorithm-particle swarm optimization （PSO） is adopted. The algorithm is combined with the BP rapid training algorithm, and then, a kind of new neural network （NN） called PSO-BP NN is established. With the advantages of global optimization ability and the rapid constringency of the BP rapid training algorithm, the new algorithm fully shows the ability of nonlinear approach of multilayer feedforward network, improves the performance of NN, and provides a favorable basis for further online application of a comprehensive model.

Prediction of mechanical property of E4303 electrode using artificial neural network

Based on the method of artificial neural network, a new approach has been devised to predict the mechanical property of E4303 electrode. The outlined predication model for determining the mechanical property of electrode was built upon the production data. The research leverages a back propagation algorithm as the neural network’s learning rule. The result indicates that there are positive correlations between the predicted results and the practical production data. Hence, using the neural network, predication of electrode property can be realized. For the first time, this research provides a more scientific method for designing electrode.

Property Prediction Using Hierarchical Regression Model Based on Calibration

Redundant information and inaccurate model will greatly affect the precision of quality prediction.A multiphase orthogonal signal correction modeling and hierarchical statistical analysis strategy are developed for the improvement of process understanding and quality prediction.Bidirectional orthogonal signal correction is used to remove the structured noise in both X and Y,which does not contribute to prediction model.The corresponding loading vectors provide good interpretation of the covariant part in X and Y.According to background,hierarchical PLS（Hi-PLS）is used to build regression model of process variables and property variables.This blocking leads to two model levels：the lower level shows the relationship of variables in each annealing furnace using hierarchical PLS based on bidirectional orthogonal signal correction,and the upper level reflects the relationship of annealing furnaces.With analysis of continuous annealing line data,the production precisions of hardness and elongation are improved by comparison of previous method.Result demonstrates the efficiency of the proposed algorithm for better process understanding X and property interpretation Y.

PREDICTION OF MECHANICAL PROPERTY OF WHISKER REINFORCED METAL MATRIX COMPOSITE: PART-I. MODEL AND FORMULATION

Based on study of strain distribution in whisker reinforced metal matrix composites, an explicit precise stiffness tensor is derived. In the present theory, the effect of whisker orientation on the macro property of composites is considered, but the effect of random whisker position and the complicated strain field at whisker ends are averaged. The derived formula is able to predict the stiffness modulus of composites with arbitrary whisker orientation under any loading condition. Compared with the models of micro mechanics, the present theory is competent for modulus prediction of actual engineering composites. The verification and application of the present theory are given in a subsequent paper published in the same issue

Analysis of Hot Rolling Routes of AZ31B Magnesium Alloy and Prediction of Tensile Property of Hot-rolled Sheets

At the initial rolling temperature of 250 to 400 ℃, AZ31B magnesium alloy sheets were hot rolled by four different rolling routes. Microstructures and mechanical properties of the hot-rolled magnesium alloy sheets were analyzed by optical microscope and tensile tests respectively. Based on the Hall-Petch relation, considering the average grain size and grain size distribution, the nonlinear fitting analysis between the tensile strength and average grain size was carried on, and then the prediction model of tensile strength of hot-rolled AZ31B magnesium alloy sheet was established. The results indicate that, by rolling with multi-pass cross rolling, uniform, fine and equiaxial grain microstructures can be produced, the anisotropy of hot-rolled magnesium sheet can also be effectively weakened. Strong correlation was observed between the average grain size and tensile property of the hot-rolled magnesium alloy sheet. Grain size distribution coefficient d（CV） was introduced to reflect the dispersion degree about a set of grain size data, and then the Hall-Petch relation was perfected. Ultimately, the prediction accuracy of tensile strength of multi-pass hot-rolled AZ31B magnesium alloy was improved, and the prediction of tensile property can be performed by the model.

Crysformer:An attention-based graph neural network for properties prediction of crystals

We present a novel approach for the prediction of crystal material properties that is distinct from the computationally complex and expensive density functional theory(DFT)-based calculations.Instead,we utilize an attention-based graph neural network that yields high-accuracy predictions.Our approach employs two attention mechanisms that allow for message passing on the crystal graphs,which in turn enable the model to selectively attend to pertinent atoms and their local environments,thereby improving performance.We conduct comprehensive experiments to validate our approach,which demonstrates that our method surpasses existing methods in terms of predictive accuracy.Our results suggest that deep learning,particularly attention-based networks,holds significant promise for predicting crystal material properties,with implications for material discovery and the refined intelligent systems.

Improved Neural Network Prediction on Electrochemistry Properties of AB_5-Based Alloy

A traditional neural network was improved in two ways. An improved algorithm is associated into the network in order to enhance the optimization rate and predictability of the network. Two different methods were supplied to improve the generalization of the network. With this improved neural network, the properties of the AB_5-based hydrogen-storage alloys, the initial discharge capacity and capacity retention ratios after charge-discharge cycles, were predicted. A better prediction result was obtained by using the network.

Mechanical Properties Prediction of the Mechanical Clinching Joints Based on Genetic Algorithm and BP Neural Network

For optimal design of mechanical clinching steel-aluminum joints, the back propagation （BP） neural network is used to research the mapping relationship between joining technique parameters including sheet thickness, sheet hardness, joint bottom diameter etc., and mechanical properties of shearing and peeling in order to investigate joining technology between various material plates in the steel-aluminum hybrid structure car body. Genetic algorithm （GA） is adopted to optimize the back-propagation neural network connection weights. The training and validating samples are made by the BTM Tog-L-Loc system with different technologic parameters. The training samples＇ parameters and the corresponding joints＇ mechanical properties are supplied to the artificial neural network （ANN） for training. The validating samples＇ experimental data is used for checking up the prediction outputs. The calculation results show that GA can improve the model＇s prediction precision and generalization ability of BP neural network. The comparative analysis between the experimental data and the prediction outputs shows that ANN prediction models after training can effectively predict the mechanical properties of mechanical clinching joints and prove the feasibility and reliability of the intelligent neural networks system when used in the mechanical properties prediction of mechanical clinching joints. The prediction results can be used for a reference in the design of mechanical clinching steel-aluminum joints.

Integrated Modelling of Microstructure Evolution and Mechanical Properties Prediction for Q&P Hot Stamping Process of Ultra‑High Strength Steel

High strength steel products with good ductility can be produced via Q&P hot stamping process,while the phase transformation of the process is more complicated than common hot stamping since two-step quenching and one-step carbon partitioning processes are involved.In this study,an integrated model of microstructure evolution relating to Q&P hot stamping was presented with a persuasively predicted results of mechanical properties.The transformation of diffusional phase and non-diffusional phase,including original austenite grain size individually,were considered,as well as the carbon partitioning process which affects the secondary martensite transformation temperature and the subsequent phase transformations.Afterwards,the mechanical properties including hardness,strength,and elongation were calculated through a series of theoretical and empirical models in accordance with phase contents.Especially,a modified elongation prediction model was generated ultimately with higher accuracy than the existed Mileiko’s model.In the end,the unified model was applied to simulate the Q&P hot stamping process of a U-cup part based on the finite element software LS-DYNA,where the calculated outputs were coincident with the measured consequences.

Control of Facies and Potential on Jurassic Hydrocarbon Accumulation and Prediction of Favorable Targets in the Hinterland Region of the Junggar Basin

Exploration practices show that the Jurassic System in the hinterland region of the Junggar Basin has a low degree of exploration but huge potential, however the oil/gas accumulation rule is very complicated, and it is difficult to predict hydrocarbon-bearing properties. The research indicates that the oil and gas is controlled by structure facies belt and sedimentary system distribution macroscopically, and hydrocarbon-bearing properties of sand bodies are controlled by lithofacies and petrophysical facies microscopically. Controlled by ancient and current tectonic frameworks, most of the discovered oil and gas are distributed in the delta front sedimentary system of a palaeo-tectonic belt and an ancient slope belt. Subaqueous branch channels and estuary dams mainly with medium and fine sandstone are the main reservoirs and oil production layers, and sand bodies of high porosity and high permeability have good hydrocarbon-bearing properties; the facies controlling effect shows a reservoir controlling geologic model of relatively high porosity and permeability. The hydrocarbon distribution is also controlled by relatively low potential energy at the high points of local structure macroscopically, while most of the successful wells are distributed at the high points of local structure, and the hydrocarbon-bearing property is good at the place of relatively low potential energy; the hydrocarbon distribution is in close connection with faults, and the reservoirs near the fault in the region of relatively low pressure have good oil and gas shows; the distribution of lithologic reservoirs at the depression slope is controlled by the distribution of sand bodies at positions of relatively high porosity and permeability. The formation of the reservoir of the Jurassic in the Junggar Basin shows characteristics of favorable facies and low-potential coupling control, and among the currenffy discovered reservoirs and industrial hydrocarbon production wells, more than 90% are developed within the scope of facies- potential index FPI〉0.5, while the FPI and oil saturation of the discovered reservoir and unascertained traps have relatively good linear correlation. By establishing the relation model between hydrocarbon- bearing properties of traps and FPI, totally 43 favorable targets are predicted in four main target series of strata and mainly distributed in the Badaowan Formation and the Sangonghe Formation, and the most favorable targets include the north and east of the Shinan Sag, the middle and south of the Mobei Uplift, Cai-35 well area of the Cainan Oilfield, and North-74 well area of the Zhangbei fault-fold zone.

Prediction on Carbon/Carbon Composites Ablative Performance by Artificial Neutral Net

A preliminary estimation of ablation property for carbon-carbon composites by artificial neutral net （ANN） method was presented. It was found that the carbon-carbon composites＇ density, degree of graphitization and the sort of matrix are the key controlling factors for its ablative performance. Then, a brief fuzzy mathematical relationship was established between these factors and ablative performance. Through experiments, the performance of the ANN was evaluated, which was used in the ablative performance prediction of C/C composites. When the training set, the structure and the training parameter of the net change, the best match ratio of these parameters was achieved. Based on the match ratio, this paper forecasts and evaluates the carbon-carbon ablation performance. Through experiences, the ablative performance prediction of carbon-carbon using ANN can achieve the line ablation rate, which satisfies the need of precision of practical engineering fields.

An Intelligent Manufacturing Platform of Polymers:Polymeric Material Genome Engineering

Polymeric materials with excellent performance are the foundation for developing high-level technology and advanced manufacturing.Polymeric material genome engineering(PMGE)is becoming a vital platform for the intelligent manufacturing of polymeric materials.However,the development of PMGE is still in its infancy,and many issues remain to be addressed.In this perspective,we elaborate on the PMGE concepts,summarize the state-of-the-art research and achievements,and highlight the challenges and prospects in this field.In particular,we focus on property estimation approaches,including property proxy prediction and machine learning prediction of polymer properties.The potential engineering applications of PMGE are discussed,including the fields of advanced composites,polymeric materials for communications,and integrated circuits.

Evaluation of the Predicted Particle Properties (P3) Microphysics Scheme in Simulations of Stratiform Clouds with Embedded Convection

To evaluate the ability of the Predicted Particle Properties(P3)scheme in the Weather Research and Forecasting(WRF)model,we simulated a stratiform rainfall event over northern China on 22 May 2017.WRF simulations with two P3 versions,P3-nc and P3-2ice,were evaluated against rain gauge,radar,and aircraft observations.A series of sensitivity experiments were conducted with different collection efficiencies between ice and cloud droplets.The comparison of the precipitation evolution between P3-nc and P3-2ice suggested that both P3 versions overpredicted surface precipitation along the Taihang Mountains but underpredicted precipitation in the localized region on the leeward side.P3-2ice had slightly lower peak precipitation rates and smaller total precipitation amounts than P3-nc,which were closer to the observations.P3-2ice also more realistically reproduced the overall reflectivity structures than P3-nc.A comparison of ice concentrations with observations indicated that P3-nc underestimated aggregation,whereas P3-2ice produced more active aggregation from the self-collection of ice and ice-ice collisions between categories.Efficient aggregation in P3-2ice resulted in lower ice concentrations at heights between 4 and 6 km,which was closer to the observations.In this case,the total precipitation and precipitation pattern were not sensitive to riming.Riming was important in reproducing the location and strength of the embedded convective region through its impact on ice mass flux above the melting level.

Deep learning for predictive mechanical properties of hot-rolled strip in complex manufacturing systems

Higher requirements for the accuracy of relevant models are put throughout the transformation and upgrade of the iron and steel sector to intelligent production.It has been difficult to meet the needs of the field with the usual prediction model of mechanical properties of hotrolled strip.Insufficient data and difficult parameter adjustment limit deep learning models based on multi-layer networks in practical applications;besides,the limited discrete process parameters used make it impossible to effectively depict the actual strip processing process.In order to solve these problems,this research proposed a new sampling approach for mechanical characteristics input data of hot-rolled strip based on the multi-grained cascade forest(gcForest)framework.According to the characteristics of complex process flow and abnormal sensitivity of process path and parameters to product quality in the hot-rolled strip production,a three-dimensional continuous time series process data sampling method based on time-temperature-deformation was designed.The basic information of strip steel(chemical composition and typical process parameters)is fused with the local process information collected by multi-grained scanning,so that the next link’s input has both local and global features.Furthermore,in the multi-grained scanning structure,a sub sampling scheme with a variable window was designed,so that input data with different dimensions can get output characteristics of the same dimension after passing through the multi-grained scanning structure,allowing the cascade forest structure to be trained normally.Finally,actual production data of three steel grades was used to conduct the experimental evaluation.The results revealed that the gcForest-based mechanical property prediction model outperforms the competition in terms of comprehensive performance,ease of parameter adjustment,and ability to sustain high prediction accuracy with fewer samples.

Composition design for (PrNd-La-Ce)2Fe(14)B melt-spun magnets by machine learning technique

Data-driven technique is a powerful and efficient tool for guiding materials design,which could supply as an alternative to trial-and-error experiments.In order to accelerate composition design for low-cost rare-earth permanent magnets,an approach using composition to estimate coercivity（H（cj）） and maximum magnetic energy product（BH）（max） via machine learning has been applied to（PrNd–La–Ce）2Fe（14）B melt-spun magnets.A set of machine learning algorithms are employed to build property prediction models,in which the algorithm of Gradient Boosted Regression Trees is the best for predicting both H（cj） and（BH）（max）,with high accuracies of R^2= 0.88 and 0.89,respectively.Using the best models,predicted datasets of H（cj） or（BH）max in high-dimensional composition space can be constructed.Exploring these virtual datasets could provide efficient guidance for materials design,and facilitate the composition optimization of 2：14：1 structure melt-spun magnets.Combined with magnets＇ cost performance,the candidate cost-effective magnets with targeted properties can also be accurately and rapidly identified.Such data analytics,which involves property prediction and composition design,is of great time-saving and economical significance for the development and application of La Ce-containing melt-spun magnets.

Prediction of mechanical properties of cold rolled strip based on improved extreme random tree

Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.

Fast determination of meso-level mechanical parameters of PFC models

To solve the problems of blindness and inefficiency existing in the determination of meso-level mechanical parameters of particle flow code (PFC) models, we firstly designed and numerically carried out orthogonal tests on rock samples to investigate the correlations between macro-and meso-level mechanical parameters of rock-like bonded granular materials. Then based on the artificial intelligent technology, the intelligent prediction systems for nine meso-level mechanical parameters of PFC models were obtained by creating, training and testing the prediction models with the set of data got from the orthogonal tests. Lastly the prediction systems were used to predict the meso-level mechanical parameters of one kind of sandy mudstone, and according to the predicted results the macroscopic properties of the rock were obtained by numerical tests. The maximum relative error between the numerical test results and real rock properties is 3.28% which satisfies the precision requirement in engineering. It shows that this paper provides a fast and accurate method for the determination of meso-level mechanical parameters of PFC models.

FULLY COUPLED FORWARD-BACKWARD STOCHASTIC DIFFERENTIAL EQUATIONS WITH GENERAL MARTINGALE

The article first studies the fully coupled Forward-Backward Stochastic Differential Equations （FBSDEs） with the continuous local martingale. The article is mainly divided into two parts. In the first part, it considers Backward Stochastic Differential Equations （BSDEs） with the continuous local martingale. Then, on the basis of it, in the second part it considers the fully coupled FBSDEs with the continuous local martingale. It is proved that their solutions exist and are unique under the monotonicity conditions.