Roll gap prediction in acceleration and deceleration process of cold rolling based on a data-driven method

Severe fluctuation of the effective roll gap in the acceleration and deceleration section of the cold rolling process is a significant factor causing thickness deviation.However,the conventional roll gap compensation method and control strategy do not meet the stringent strip quality requirements.The roll gap model in the acceleration and deceleration process is studied to increase the thickness control precision.In order to improve model accuracy,a roll gap prediction method based on data-driven is proposed.Given the complexities of the cold rolling process,the extreme gradient boosting(XGBoost)method is used to predict the roll gap model as the rolling speed changes.Meanwhile,support vector regression and neural network-based methods are taken to evaluate and compare the prediction performances.Based on the field data,the simulation experiments are carried out.It demonstrated that the prediction performance of the proposed method outperformed the other two methods.The values of root mean square error,determination coefficient value,mean absolute percentage error and mean absolute error obtained from the XGBoost model were equal to 0.000346,0.952,7.02,and 0.00028,respectively.In addition,the proposed method analyzed the contribution rates of the rolling affecting parameters on the roll gap.The data showed that in the controllable rolling parameters,the rolling speed is the most impacting factor that disturbs the roll gap model in the acceleration and deceleration process,which can provide a useful direction for actual roll gap adjustment.

Optimized shearing strategy for heavy plate based on contour recognition

The shearing line is the key to improve the quality and efficiency of heavy plates.A model of contour recognition and intelligent shearing strategy for the heavy plate was proposed.Firstly,multi-array binocular vision linear cameras were used to complete the image acquisition.Secondly,the total length of the steel plate after cooling was predicted by back propagation neural network algorithm according to the contour data.Finally,using the scanning line and a new camber description method,the shearing strategy including head/tail irregular shape length and rough dividing strategy was calculated.The practical application shows that the model and strategy can effectively solve the problems existing in the shearing process and can effectively improve the yield of steel plates.The maximum error of detection width,length,camber,and the length of the irregular deformation area at the head/tail of the plate are all less than 5 mm.The correlation coefficient of the length prediction model based on the back propagation neural network is very high.The reverse ratio result of edge cutting failure using the proposed rough dividing strategy is 1/401=0.2%,which is 2%higher than that by human.

Optimization of Temperature and Force Adaptation Algorithm in Hot Strip Mill

Abstract： In the hot strip rolling control system, the temperature distribution and deformation resistance are the main parameters affecting prediction of rolling force. In order to improve the model prediction precision, an optimiza- tion algorithm based on objective function was put forward, in which the penalty function index was adopted. During the adaptation process, the temperature distribution and deformation resistance were taken as the optimized parame ters, and the Nelder-Mead simplex algorithm was used to search the optimal solution of the objective function. Fur thermore, the temperature adaptation and force adaptation were solved simultaneously. Application results show that the method can improve the accuracy of the rolling force model obviously, and it can meet the demand of the indus trial production and has a good application prospect.

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.

Simplified Weighted Velocity Field for Prediction of Hot Strip Rolling Force by Taking into Account Flattening of Rolls

The weighted velocity field was simplified for analysis of hot strip rolling. Using the field and GM （geometric midline） yield criterion, the deformation power, friction power and shear power were obtained respectively. Summing the partial power contributions, the total deformation power for strip rolling was presented. Then, by minimizing the power function, the rolling force was obtained; meanwhile, considering the effect of roll elastic flattening, iterative calculation of the roll radius was carried out until the radius was convergent. On line data were corn pared with the calculated results to verify the model accuracy. It was indicated that the calculated rolling forces were basically in agreement with the measured ones since the maximum error was less than 10.0%. Moreover, the effects of various rolling conditions such as thickness reduction, friction factor and shape factor, upon separating force, location of neutral angle, and stress state coefficient were discussed systematically.