Finite element model simulation and back propagation neural network modeling of void closure for an extra-thick plate during gradient temperature rolling

The void closure behavior in a central extra-thick plate during the gradient temperature rolling was simulated and a back propagation(BP)neural network model was established.The thermal–mechanical finite element model of the gradient temperature rolling process was first developed and validated.The prediction error of the model for the rolling force is less than 2.51%,which has provided the feasibility of imbedding a defect in it.Based on the relevant data obtained from the simulation,the BP neural network was used to establish a prediction model for the compression degree of a void defect.After statistical analysis,80%of the data had a hit rate higher than 95%,and the hit rate of all data was higher than 90%,which indicates that the BP neural network can accurately predict the compression degree.Meanwhile,the comparisons between the results with the gradient temperature rolling and uniform temperature rolling,and between the results with the single-pass rolling and multi-pass rolling were discussed,which provides a theoretical reference for developing process parameters in actual production.

An analytical model of hot rolling force for a thick plate by combining globally optimal approximation yield criterion and egg-circular velocity field

For the sake of solving the problem that it is difficult to be integrated for the Mises specific plastic power due to its nonlinearity,a new linear criterion,named the globally optimal approximation criterion,is constructed by the polygonal approximation to the Mises circle.The new criterion is proved to be the linear function of the principal stress componentsσ1,σ2 andσ3 and the trajectory of it on theπ-plane is a non-equiangular but equilateral dodecagon intersecting the Mises circle.The theoretical results of the current criterion described by the Lode stress parameters are in excellent accordance with the experimental results.Meanwhile,according to the trend that the metallic flow velocity between rollers aggrandizes gradually from the inlet to the outlet during the hot rolling of a thick plate,a biomimetic velocity field is proposed in which the horizontal velocity component fits the egg-circular curve distribution.The velocity field and its simulated results agree quite well.Subsequently,using the determined linear criterion,energy analysis of the constructed velocity field is utilized to obtain the interior deformation power,while the vector decomposition approach is utilized to obtain the frictional power and shear power.On this basis,the overall power is obtained and the analytical solutions are generated for the rolling torque,rolling force and the coefficient of the stress state under different egg curves by minimizing the neutral angle.Furthermore,the parameter optimization of the characteristic parameterρwhich affects the slope of the egg-circular curve is carried out and the best egg-circular curve which can minimize the energy consumption is determined.The best agreement between the theoretical and observed values of rolling force and rolling torque is under this curve,and the mean relative errors of the rolling torque and rolling force are no more than 2.93%,while the maximum error is no more than 8.35%.

A new integrated model of deformation resistance and its application in prediction of rolling force of a thick plate

The prediction accuracy of existing models of the rolling force of a thick plate is always very low.To address this problem,a high-precision genetic algorithm-backpropagation network(GA-BP)model of deformation resistance was built,and its integration with the traditional fitted model was further established.Then,a novel rolling force model was obtained by embedding the integration model of deformation resistance in the original model of rolling force.According to this research idea,the industrial data are normalized at first.On this basis,the interactions among the process parameters were disclosed through the variance analysis,and then described by various virtual factors.These factors are set as part of input parameters.Then,the optimal structure of the GA-BP model of deformation resistance was determined and an integration model of deformation resistance was built.Finally,a novel rolling force model is obtained by substituting the traditional fitted deformation resistance into the Sims model with the integration model of the deformation resistance.The results proves that the introduction of virtual factors can increase the hit rate of±5%from 75.8%to 78%and can reduce the root mean square error from 4.72%to 4.48%.Besides,it is found that the mean relative error of the traditional fitted deformation resistance is 0.142,while that of the modified deformation resistance is only 0.03.In addition,the mean relative error in the original rolling force model is 0.145,while that of the present model is only 0.03.

Research progress and intelligent trend of accurate modeling of rolling force in metal sheet

The rolling force model is the basis for reasonable selection of rolling equipment and optimization of rolling process,and the establishment of an accurate mathematical model as well as doing the corresponding parameter analysis has been the focus of research in this field for many years.Different modeling methods of the rolling force and their research progress were introduced,the main methods of which are the theoretical analysis,the finite element simulation,the artificial neural network modeling,the hybrid modeling of theory and neural network,as well as the hybrid modeling of finite element and neural network.Meanwhile,the application examples of rolling force models in thickness control,strip crown control,and schedule optimization were presented,and an outlook on the new directions of future development was made,including establishing new type of hybrid models,solving the black box problem,and realizing the multi-objective optimization accounting for some special requirements.

Special issue on application of Al in steelmaking and ferrous materials

It is well known that metallurgy is one of the key industries for national economic development.Currently,state-ofthe-art information technologies,like artificial intelligence(AI),industrial big data,etc.,are of vital importance for economic and social development to meet the intelligentization of metallurgical processes and to promote intelligent manufacturing.These techniques are also boosting the transformation and upgrading of traditional manufacturing industries.Al-based intelligent manufacturing process,integrating the technologies of advanced manufacturing and the new generation of informatics,is a new opportunity for further innovation and development of global metallurgical industries.

Analysis of Hot Tandem Rolling Force with Logarithmic Velocity Field and EA Yield Criterion

In order to analyze the hot tandem roiling force, a new logarithmic velocity field is proposed. Using the field and linear EA （equal area） yield criterion, the plastic deformation power for plate rolling is analyzed, and the friction power is obtained based on the co-line vector inner product method. Then analytical solution of plate rolling power functional is obtained. Finally, by minimizing the power functional, the rolling torce and torque are received. Compared with those measured ones in hot tandem rolling on-line, the calculated rolling forces are in good agreement with the actual measured ones since the maximum error is less than 12~. Moreover, the effects of various rolling conditions such as thickness reduction, friction factor and shape factor, upon separating force, location of neutral an- gle, and stress state coefficient are discussed systematically.