RBFType Artificial Neural Network Model Applied in Alloy Design of Steels

RBF model, a new type of artificial neural network model was developed to design the content of carbon in lowalloy engineering steels. The errors of the ANN model are: MSE 0052 1, MSRE 1785%, and VOF 1932 9. The results obtained are satisfactory. The method is a powerful aid for designing new steels.     

Effect of Chromium on CCT Diagrams of Novel AirCooled Bainite Steels Analyzed by Neural Network

The quantitative effects of chromium content on continuous cooling transformation (CCT) diagrams of novel aircooled bainite steels were analyzed using artificial neural network models. The results showed that the chromium may retard the high and mediumtemperature martensite transformation.     

MultiObjective Optimization and Analysis Model of Sintering Process Based on BP Neural Network

A multiobjective optimization and analysis model of the sintering process based on BP neural network is presented. Genetic algorithms are combined to simplify the BP neural network, which can reduce the learning time and increase the forecasting accuracy of the network model. This model has been experimented in the sintering process, and the production cost, the energy consumption, the quality (revolving intensity), and the output are considered at the same time. Moreover, the relation between some factors and the multiobjectives has been analyzed, and the results are consistent with the process. Different objectives are emphasized at different practical periods, and this can provide a theoretical basis for the manager.     

Modeling of Austenite Decomposition in Low SiMn TRIP Steel During Cooling

Transformation behavior in low carbon SiMn TRIP steel was investigated by means of microstructural observation and computer modelling. A transformation model in which transformation is controlled by carbon diffusion was suggested, which well described the volume fractional change of ferrite, pearlite, and bainite during continuous cooling. The influence of Si content and austenite grain size was thoroughly investigated. The calculated results indicated that Si retards pearlite transformation, accelerates polygonal ferrite transformation, refines the austenite grain, and increases the ferrite transformation rate.     

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 online application of a comprehensive model.     

Influence of Edge Rolling Reduction on PlateEdge Stress Distribution During Finish Rolling

Dimensions of one kind of stainless steel plate before finish rolling were obtained through analysis of the rough rolling processes by finite element method and updated geometrical method. The FE models of finish rolling process with a front edge roll were built, and influences of the edge rolling reduction on the stress change in the plate edge during finish rolling were analyzed. The results show that when the edge rolling reduction is increased from 0 mm to 2 mm, the compressive stress in plate corner clearly increases in edge rolling process, and the zone of tensile stress during whole rolling decreases; when the edge rolling reduction is increased from 2 mm to 5 mm, the compressive stress in the plate corner seldom changes, and the compressive stress decreases after the horizontal rolling.     

Modeling of StrainInduced Precipitation Kinetics and Evolution of Austenite Grains in Nb Microalloyed Steels

Considering the effect of strain and chemical composition on precipitation behavior, new models for the start and end time of Nb(C,N) precipitation in austenite under the conditions of different temperatures and strains have been investigated for Nb microalloyed steel. The value of n in the precipitation kinetic equation has been determined by using the available experimental data in literature, which indicated that n is a constant and independent of temperature. The values of the start and end time of the predicted precipitation are compared with the experimental values. Calculated results are in good agreement with the experimental results. Also, the evolution of austenite grains before ferrite transformation is simulated by taking the effect of precipitation into consideration. The measured austenite grain size is in good agreement with predicted one prior to ferrite transformation.     

Process Simulation and Microstructure Analysis of Low Carbon SiMn Quenched and Partitioned Steel

The quenching and partitioning (Q&P) process was experimentally investigated on the thermomechanical simulator (Gleeble3800). The microstructure and fracture mechanism of the sheets were investigated by means of TEM. It was found that the microstructure of quenched and partitioned steel consists of fine lath martensite and thin interlath austenite films. The optimum quenching temperature of producing the maximum amount of retained austenite after final quenching at room temperature was predicted by Matlab software package. It was found that the calculations by Matlab software can provide guidance for experimental processing design reliably. The volume fraction of retained austenite at room temperature was approximately 8%, which was measured easily by the software VC60++ programming. The results verified that quenched and partitioned steel possesses a good combination of strength and plasticity due to its fine microstructure. This steel exhibited high ultimate tensile strength (exceeding 1 000 MPa) and good elongation of 25%. The results showed that the fracture mechanism of the sheets is typical tough fracture under the condition of tensile failure.     

Long and ShortTerm SelfLearning Models of Rolling Force in Rolling Process Without Gaugemeter of Plate

Owing to a lack of gaugemeter and the variety of steel grades and standards in some plate mills, the long and shortterm selflearning models of rolling force based on gauge softmeasuring with high precision were brought up. The softmeasuring method and target value locked method were used in these models to confirm the actual exit gauge of passes, and thick layer division and exponential smoothing method were used to dispose the deformation resistance parameter, which could be calculated from the actual data of the rolling process. The correlative mathematical methods can also be adapted to selflearning with gaugemeter. The models were applied to the process control system of AGC (automatic gauge control) reconstruction on 2 800 mm finishing mill of Anyang steel and favorable effect was obtained.     

Thermodynamic Properties of Carbon and Manganese in MnC and MnFeC Melts

Carbon solubility in MnFe melts (xMn=0083-0706, xFe=0034-0715) was measured experimentally at various temperatures. By thermodynamic derivation and calculation, the relationship between activity coefficient of carbon in infinite dilute solution of manganese in MnC system and temperature was obtained. Using GibbsDuhem relationship, the experimental results of this study, and experimental data obtained by strict thermodynamic derivation and calculation in references, the relationships between other thermodynamic properties (εCC, εCCC, εCFe, εCCFe, and εCFeFe) in MnFeC system and temperature were obtained.     

Microstructure Characteristics of an FeMnC TWIP Steel After Deformation

 Abstract: The present paper investigated deformatiom microstructure characteristcsl of the Fe-Mn-C TWIP steel .The results showed that the hot rolled – cold rolled - annealed sample of Fe-Mn-C TWIP steels has excellent mechanical properties, the true stress-strain curve from tension tests exhibit repeated serrations. The deformed microstructure exhibited the typical planar glide characteristics such as no cell formation, dislocation pile ups on a single slip plane, mechanical twins and stacking faults. There are equiaxial and deep dimple structures in the fractograph, it is a typical ductile fracture. microcrack initiated from inclusions and twin-twin intersections, Its deformation and mfracture processes were the formation, growth and coalescence of microvoids. Because of high amount of anganese, there are many inclusions of strip MnS, the quantity of sulphur should be controlled during steelmaking.     

Effect of Co on Microstructure and Interfacial Properties of FeBased Laser Cladding

The coatings consisting of Fe064Ni036 dendrites as matrix and (Fe,Cr)7(C,B)3 interdendritic compounds as reinforcement were fabricated on the medium steel substrate by laser cladding using the Febased powders with different Co content, and Co is uniformly dissolved in the coatings. Compared with the coatings containing 1% and 5% Co, the coating containing 3% Co increases in the area fraction of the interdendritic region by about 5%, in the microhardness nearby the interface by about HV 55 and in the interfacial bond strength by about 30 MPa. The interface fracture morphology exhibits the tear appearance, which can be characterized as the ductile fracture.     

Evolution of Microstructure and Ordering in Rolling Process of Fe-6.5 mass％ Si Alloy

Fe-6. 5 mass% Si alloy is an excellent soft magnetic material with good application prospects. After rolling,the structure of the sheet is likely to be heterogeneous along the normal direction. The microstructure and ordering evolution in the thickness range of the sheets during hot-warm rolling process was studied by means of optical microscope and transmission electron microscope. The results show that dynamic recrystallization occurs in the surface parts during the hot and warm rolling processes,where the grains are equiaxed but have high density of dislocations due to the large deformation. The grains in the center part are elongated along the rolling direction. It is also found that in the hot rolled sheet,the center part has lower density of dislocations because of dynamic recovery. Meanwhile,this part has higher ordering content compared with the surface part,indicating that the high density of dislocations can inhibit the formation of ordering in the air cooling process after hot rolling. In the warm rolling process,both of the parts are deformed heavily. Large deformation destroys ordered phases and induces disordering. The ordering content is low in the whole warm rolled sheet.     

Properties and Microstructure of OneStep Cold Rolled Steel Strip for Shadow Mask

The effect of recrystallization annealing temperature on the properties and microstructure of onestep cold rolled steel strip for shadow mask was studied. The results showed that there was no yield point elongation when the tensile tests were performed on the samples for annealing temperatures ranging from 750 ℃ to 810 ℃. Moreover, increasing annealing temperature resulted in large grains, which was beneficial to the formability and magnetic property of steel strips. On the other hand, when the sample was annealed at 840 ℃, its microstructure showed ununiformity with 004% yield point elongation, which was not good for the function of the shadow mask. Therefore, the proper recrystallization annealing temperature was about 810 ℃ for the present steel strip for shadow mask.     

Influence of Mn Content and Hot Deformation on Transformation Behavior of CMn Steels

The hot deformation behaviors and the microstructural evolution of plain CMn steels with similar contents of C and Si but different contents of Mn have been investigated by compressive processing using Gleeble1500 mechanical simulator. Influence of Mn and hot deformation on continuous cooling transformation of steels has been studied. The experimental results showed that deformation in austenite region accelerated transformation process, and the extent is dependent on the hot deformation and cooling conditions. The hot deformation would promote transformation process, but the increase of transformation temperature is dependent on Mn contents. The results have also shown that the effect of deformation on ferrite transformation becomes more obvious with the increase of Mn content at relatively low cooling rate.