Prediction of mechanical properties for deep drawing steel by deep learning

At present,iron and steel enterprises mainly use“after spot test ward”to control final product quality.However,it is impossible to realize on-line quality predetermining for all products by this traditional approach,hence claims and returns often occur,resulting in major eco-nomic losses of enterprises.In order to realize the on-line quality predetermining for steel products during manufacturing process,the predic-tion models of mechanical properties based on deep learning have been proposed in this work.First,the mechanical properties of deep drawing steels were predicted by using LSTM(long short team memory),GRU(gated recurrent unit)network,and GPR(Gaussian process regression)model,and prediction accuracy and learning efficiency for different models were also discussed.Then,on-line re-learning methods for transfer learning models and model parameters were proposed.The experimental results show that not only the prediction accuracy of optimized trans-fer learning models has been improved,but also predetermining time was shortened to meet real time requirements of on-line property prede-termining.The industrial production data of interstitial-free(IF)steel was used to demonstrate that R2 value of GRU model in training stage reaches more than 0.99,and R2 value in testing stage is more than 0.96.

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.

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.

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.

An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method

Properties prediction of crude oil remains an essential issue for refineries. In this communication, an exhaustive and extendable support vector machine(SVM) intelligent prediction process has been proposed to solve this problem. A novel hybrid genetic algorithm-particle swarm optimization(GA-PSO)method was applied to optimize the SVM model. The optimization process and result demonstrated that the newly proposed GA-PSO-SVM method was more accurate and time-saving than the classical GA or PSO method. Compared with the classical Grid-search SVM, the combined GA-PSO-SVM model appeared to be more applicable for the properties prediction task. The TBP distillation curve fitting was exampled to evaluate the performance of the developed model. The regression result demonstrated the high accuracy and efficiency of the proposed process. The model can be applied in the Industrial Internet as a plugin, and the adaptability and flexibility is demonstrated by the implement of crude oil molecular reconstruction employing the intelligent prediction process.

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.

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.

Flood Hazard Prediction from Soil Properties by Remote Sensing and Genographic Information System:A Case Study of Mae Rim Watershed,Chiang Mai Province,Thailand

Physiography and soil in Mae Rim watershed, Chiang Mai Province, Thailand were investigated by using aerial photographs and satellite image in conjunction with field work, and soil infiltration rate and soil shear resistance were measured in field. Many factors affecting runoff were analyzed using the Integrated Land and Water Information System (ILWIS). As a result, a model determining flood hazard was set up. Three maps including runoff curve number map, runoff coefficient map, and flood inundation map were created. In addition, the time of concentration was predicted.

New Computer-aided Method for Optimum Use and Properties Prediction of Steels

When selecting a steel grade, a quenching medium or heat treating parameters for a given steel part, their applicability depends on whether the microstructures and properties at the specified position of the cross-section satisfy the specific application requirements. Based on steel hardenability elements, charts of equivalent cooling rates as well as object-oriented programming methods, a computerized method is developed. In addition, this paper has studied the prediction of mechanical properties and microstructures of the as-quenched parts. It is also studied that the prediction of ideal critical diameter and Jominy curve from chemical composition on the basis of ASTM A255.

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.

DEPENDENCE OF PREDICTION MODEL OF FORMING LIMIT STRAINS ON FORMING METHOD AND MECHANICAL PROPERTIES OF SHEET METALS

ＤＥＰＥＮＤＥＮＣＥＯＦＰＲＥＤＩＣＴＩＯＮＭＯＤＥＬＯＦＦＯＲＭＩＮＧＬＩＭＩＴＳＴＲＡＩＮＳＯＮＦＯＲＭＩＮＧＭＥＴＨＯＤＡＮＤＭＥＣＨＡＮＩＣＡＬＰＲＯＰＥＲＴＩＥＳＯＦＳＨＥＥＴＭＥＴＡＬＳ①ＺｈｏｕＷｅｉｘｉａｎＤｅｐａｒｔｍｅｎｔｏｆＡｅ...

Are yarn quality prediction tools useful in the breeding of high yielding and better fibre quality cotton(Gossypium hirsutum L.)?

Results The population had large variations for lint yield,fibre properties,predicted yarn properties,and composite fibre quality values.Lint yield with all fibre quality traits was not correlated.When the selection was conducted first to keep those with improved fibre quality,and followed for high yields,a large proportion in the resultant populations was the same between selections based on Cottonspec predicted yarn quality and HVI-measured fibre properties.They both exceeded the selection based on FQI and Background The approach of directly testing yarn quality to define fibre quality breeding objectives and progress the selection is attractive but difficult when considering the need for time and labour.The question remains whether yarn prediction tools from textile research can serve as an alternative.In this study,using a dataset from three seasons of field testing recombinant inbred line population,Cottonspec,a software developed by the Commonwealth Scientific and Industrial Research Organisation(CSIRO)for predicting ring spun yarn quality from fibre properties measured by High Volume Instrument(HVI),was used to select improved fibre quality and lint yield in the population.The population was derived from an advanced generation inter-crossing of four CSIRO conventional commercial varieties.The Cottonspec program was able to provide an integrated index of the fibre qualities affecting yarn properties.That was compared with selection based on HVI-measured fibre properties,and two composite fibre quality variables,namely,fibre quality index(FQI),and premium and discount(PD)points.The latter represents the net points of fibre length,strength,and micronaire based on the Premiums and Discounts Schedule used in the market while modified by the inclusion of elongation.PD points.Conclusions The population contained elite segregants with improved yield and fibre properties,and Cottonspec predicted yarn quality is useful to effectively capture these elites.There is a need to further develop yarn quality prediction tools through collaborative efforts with textile mills,to draw better connectedness between fibre and yarn quality.This connection will support the entire cotton value chain research and evolution.

Prediction of Mechanical Properties of Structural Bamboo and Its Relationship with Growth Parameters

Bamboo is a renewable natural building material with good mechanical properties.However,due to the heterogeneity and anisotropy of bamboo stalk,a large amount of material performance testing costs are required in engineering applications.In this work,longitudinal compression,bending,longitudinal shear,longitudinal tensile,transverse compression and transverse tensile tests of bamboo materials are conducted,considering the influence of the bamboo nodes.The mechanical properties of the whole bamboo stalk with the wall thickness and outer circumference are explored.Through univariate and multiple regression analysis,the relationship between mechanical properties and wall thickness and perimeter is fitted,and the conversion parameters between different mechanical properties are derived.The research results show that the transverse compressive strength of nodal specimen,and transverse tensile strength of nodal and inter-node specimens increase with the increase of wall thickness and outer circumference,but other mechanical properties decrease with the increase of wall thickness and outer circumference.The prediction formula and conversion parameters of bamboo mechanical properties proposed in this research have high applicability and accuracy.Moreover,this research can provide references for the evaluation of bamboo performance and saving test costs.

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

Artificial network prediction on degradable properties of coal-filled films

Utilized degradable data of coal-filled films from the accelerated UV chamber ageing degradation experiments, and on the basis of control factors’ analysis, presented a predicting model on degradable properties of this film in photo-degradation according to back-propagation artificial neural network (BP ANN). 4 controlling factors in films degrada-tion, including temperature, the time of UV irradiation, the concentration and the type of coals were used as input parameters in the ANN model. While the degradable properties after film degradation, including the mechanical properties and carbonyl index, were used as output parameters. It was carried out by the neural network toolbox of Matlab 6.5 soft-ware and Visual Basic 6.0. Discussed partition of sample data and model’s parameters, and then selected the best configuration of ANN network. The accurate scope of predicting results was analyzed. This model has a high precision in predicting on properties of the coal-filled film degradation.

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.

Artificial neural network prediction of mechanical properties of hot rolled low carbon steel strip

Conventionally, direct tensile tests are employed to measure mechanical properties of industrially pro- duced products. In mass production, the cost of sampling and labor is high, which leads to an increase of total pro- duction cost and a decrease of production efficiency. The main purpose of this paper is to develop an intelligent pro- gram based on artificial neural network （ANN） to predict the mechanical properties of a commercial grade hot rolled low carbon steel strip, SPHC. A neural network model was developed by using 7 x 5 x 1 back-propagation （BP） neural network structure to determine the multiple relationships among chemical composition, product pro- cess and mechanical properties. Industrial on-line application of the model indicated that prediction results were in good agreement with measured values. It showed that 99.2 % of the products＇ tensile strength was accurately pre- dicted within an error margin of ~ 10 %, compared to measured values. Based on the model, the effects of chemical composition and hot rolling process on mechanical properties were derived and the relative importance of each in- put parameter was evaluated by sensitivity analysis. All the results demonstrate that the developed ANN models are capable of accurate predictions under real-time industrial conditions. The developed model can be used to sub- stitute mechanical property measurement and therefore reduce cost of production. It can also be used to control and optimize mechanical properties of the investigated steel.

A Prediction of the Excess Partial Molar Free Energies of MgCl_2 in the KCI-MgCl_2-LiCl Molten Salt System Containing MgCl_2 below 0.5 from Thermodynamic Properties of Binary Systems

The thermodynamical properties of MgCl_2 in KCI-MgCl_2-LiCl molten electrolytes containing MgCl_2 below 0.5 (mole fraction, the same below) have been determined from the interchange energies of two binary systems KCI-MgCl_2 and LiCI-MgCl_2, by means of a model on the assumptions that the electrolytes in the solution are treated as independent particles instead of their ion forms and the interchange energy between the component pair KCI-LiCl is ignored when compared with those of component pairs KCl-MgCl_2 and MgCl_2-LiCl. The interchange energies, wKCl-MgCl_2 and wMgcCl_2-Licl, are obtained as-70000 and -13800 J.mol-1, from the corresponding binary solutions, respectively.

Blended coal’s property prediction model based on PCA and SVM

In order to predict blended coal's property accurately, a new kind of hybrid prediction model based on principal component analysis (PCA) and support vector machine (SVM) was established. PCA was used to transform the high-dimensional and correlative influencing factors data to low-dimensional principal component subspace. Well-trained SVM was used to extract influencing factors as input to predict blended coal's property. Then experiments were made by using the real data, and the results were compared with weighted averaging method (WAM) and BP neural network. The results show that PCA-SVM has higher prediction accuracy in the condition of few data, thus the hybrid model is of great use in the domain of power coal blending.

COMPUTERIZED PREDICTION SYSTEM FOR THERMOPHYSICAL PROPERTIES

ＣＯＭＰＵＴＥＲＩＺＥＤＰＲＥＤＩＣＴＩＯＮＳＹＳＴＥＭＦＯＲＴＨＥＲＭＯＰＨＹＳＩＣＡＬＰＲＯＰＥＲＴＩＥＳ①ＺｈａｎｇＪｉａｙｕｎ，ＭａＹｏｎｇｊｉａｎ，ＺｈｏｕＴｕｐｉｎｇ，ＬｅｉＪｕｎｂｏ，ＦａｎｇＸｕｅｌｉａｎｇＤｅｐａｒｔｍｅｎｔｏｆＰ...