B21B2269/02

LSTM-BASED HOT-ROLLING ROLL-BENDING FORCE PREDICTING METHOD
20230004781 · 2023-01-05 ·

Provided is an LSTM-based hot-rolling roll-bending force predicting method including the steps of acquiring final rolling data of a stand of a stainless steel rolling mill when performing a hot rolling process, and dividing the data into a training set traindata and a test set testdata; normalizing the traindata; building a matrix P; using a last row of the matrix P as a label of the training set, namely a true value; calculating and updating an output value and the true value of a network; after network training is completed, taking the last m output data of the LSTM network as an input at a next moment, and then obtaining an output of the network at the next moment, wherein the output is a predicted value of the roll-bending force at the next moment; repeating the steps until a sufficient number of prediction data is obtained; and comparing the processed data with the true value in the testdata to check the validity of the network.

MILL STAND

A device for stabilizing of working rollers and back-up rollers of a mill stand that has, for each bending block, first hydraulic pressing units being arranged upstream of the working roller, each first hydraulic pressing unit having a piston with a piston rod and a pressure plate, the piston and the piston rod being integrated in the bending block and the pressure plate being pressable against a working roller chock, and for each stand column, at least one second hydraulic pressing unit, the second hydraulic pressing unit being arranged downstream of the back-up roller and having a piston with a piston rod and a pressure plate, the piston and the piston rod being integrated in the stand column and the pressure plate being pressable against the back-up roller chock, and a first hydraulic pressing unit containing a first oscillation absorber.

Rolling mill, and method for setting rolling mill

There is provided a rolling mill that includes a plurality of rolls, in which any one roll among respective rolls is adopted as a reference roll, including a load detection apparatus, detects a vertical roll load at a rolling support point position; a pressing apparatus pressing the roll chocks in the rolling direction; a driving apparatus moving the roll chocks in the rolling direction; and a position control unit which fixes a rolling direction position of roll chocks of the reference roll, and drives the driving apparatus to control positions in the rolling direction of the roll chocks of the rolls other than the reference roll.

ROLLING MILL, AND METHOD FOR SETTING ROLLING MILL

There is provided a rolling mill that includes a plurality of rolls, in which any one roll among respective rolls is adopted as a reference roll, including a load detection apparatus, detects a vertical roll load at a rolling support point position; a pressing apparatus pressing the roll chocks in the rolling direction; a driving apparatus moving the roll chocks in the rolling direction; and a position control unit which fixes a rolling direction position of roll chocks of the reference roll, and drives the driving apparatus to control positions in the rolling direction of the roll chocks of the rolls other than the reference roll.

LSTM-based hot-rolling roll-bending force predicting method

Provided is an LSTM-based hot-rolling roll-bending force predicting method including the steps of acquiring final rolling data of a stand of a stainless steel rolling mill when performing a hot rolling process, and dividing the data into a training set traindata and a test set testdata; normalizing the traindata; building a matrix P; using a last row of the matrix P as a label of the training set, namely a true value; calculating and updating an output value and the true value of a network; after network training is completed, taking the last m output data of the LSTM network as an input at a next moment, and then obtaining an output of the network at the next moment, wherein the output is a predicted value of the roll-bending force at the next moment; repeating the steps until a sufficient number of prediction data is obtained; and comparing the processed data with the true value in the testdata to check the validity of the network.

DEVICE WITH ADJUSTABLE OFFSET DISTANCE IN SERPENTINE ROLLING FOR ROLLING MILL AND USING METHOD THEREOF

A device for a rolling mill with an adjustable offset distance in serpentine rolling and a method thereof are provided. The device includes a frame, offset moving components, upper and lower work rolls, telescopic components, lifting components, and a monitoring component. The offset moving components are connected to a middle of the frame, and the offset moving components are connected to the lower work roll bearing seats, and the lower work roll bearing seats are connected to the lower work roll; the offset moving components are fixedly connected to the telescopic components; a top of the frame is fixedly connected to the lifting components, and the lifting components are fixedly connected to upper work roll bearing seats, and the upper work roll bearing seats are connected to the upper work roll, and the monitoring component is provided at a rolling exit of the frame.