Finish rolling roll gap inclination presetting system based on historical rolling data and calibration data

Abstract

The application discloses a kind of based on historical rolling data and calibration data's finishing roll gap inclination presetting system, belongs to the technical field of hot continuous rolling finishing rolling control, this system includes data module, artificial mark module, roll gap inclination calculation module, historical database and model database;At the end of current stand calibration, data module reads the rolling data and calibration data corresponding to current stand, and reads the rolling data and calibration data in historical database;Roll gap inclination calculation module calculates roll gap inclination value by the data read by data module and issues it to current stand;When receiving storage data signal, data module updates historical database;When receiving artificial mark signal, data module updates model database, and re-trains roll gap inclination calculation model using the data in updated model database.The application can improve the stability of rolling process and reduce operator intervention.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hot continuous rolling finishing rolling control, in particular to a finishing rolling roll gap inclination presetting system based on historical rolling data and calibration data. BACKGROUND

[0002] The steel industry is in a high-quality development stage, especially under the background of increasing demand in the fields of aerospace, artificial intelligence, military industry, etc., the demand for high-precision and high-quality strip steel is increasing. Hot-rolled strip steel accounts for more than 75% of the steel output, among which the finishing rolling unit as the core of the hot continuous rolling production of strip steel, its technical level determines the quality of the product. The accurate measurement and control of the strip steel deviation between the finishing rolling stands has become a hot issue in the industry. Due to the multi-dimensional factors such as the raw material of the produced strip steel, the rolling process, the control system, etc., the phenomenon of strip steel deviation is difficult to avoid.

[0003] Roll gap inclination presetting is to pre-tilt the roll gap according to the calibration of the rolling mill to avoid the phenomenon of asymmetric springing of the roll gap in the rolling process due to the difference in stiffness on both sides of the rolling mill, thereby causing the strip steel to deviate and produce asymmetric wave defects. The accuracy of the roll gap inclination value lays the foundation for the stability of the rolling of the strip steel. If the roll gap inclination value is not accurate, the strip steel will produce asymmetric wave defects after biting into the stand, and when the wave is large, the strip steel is prone to breakage, and in more serious cases, it will hit the side guide plate and cause side overturning, resulting in a steel stacking accident.

[0004] A Chinese patent application with the application number CN201310100969.1 discloses a leveling method for zero-adjustment work roll opening roll gap, in the static state, the two sides of the oil cylinder are automatically synchronized to press down, so that the total rolling force reaches the first target value 500±10T, it is judged whether the following conditions are met: the difference between the two sides of the rolling force ≤10T, if not met, the pre-dancing roll is made to lift up the side with large rolling force and press down the side with small rolling force by the same amount, so that the requirement is met; then the car is turned and continues to press down, so that the total rolling force reaches the second target value, the second target value is: F1~F4 is 1500±10T, F5~F7 is 1000±10T. Then the two sides of the AGC oil column deviation, i.e. the difference between the working side oil column value and the transmission side oil column value, is corrected again to reach the oil column deviation target value. The oil column deviation target value is: the two sides of the oil column deviation recorded in the rolling process of the third steel in the last opening rolling plan + the oil column deviation after the completion of the 500T static pressure of this opening rolling - the oil column deviation after the completion of the 500±10T static pressure of the last opening rolling. After the operator confirms that there is no abnormal situation, the zero-adjustment pre-embedding process, i.e. the leveling method for zero-adjustment work roll opening roll gap, is ended, and the preparation for opening rolling is ready.

[0005] The Chinese patent application with the application number CN201711476218.4 discloses a method for zero adjustment of a finishing mill, which comprises the following steps: recording the average value of the hydraulic cylinder deviation after the fourth to ninth steels in the last production unit are thrown; replacing the work roll after the last production unit is rolled; initially positioning the hydraulic cylinder to reach the initial position of zero adjustment; performing the zero adjustment pressure closed loop through the downward movement of the hydraulic cylinder; compensating the average value of the hydraulic cylinder deviation after the fourth to ninth steels are thrown; clearing the roll gap of the hydraulic cylinder; lifting the hydraulic cylinder to the set position of the roll gap to complete the zero adjustment without flattening.

[0006] Although the above prior art all relates to the pre-setting of the finishing roll gap inclination, it does not consider the case that the stiffness of the mill changes greatly due to the replacement of the support roll or the step pad before the calibration of the finishing mill, and thus it is not universal. Moreover, the control precision of the above prior art is also low. SUMMARY

[0007] The present application provides a finishing roll gap inclination pre-setting system based on historical rolling data and calibration data to solve the technical problem that the prior art does not consider the case that the stiffness of the mill changes greatly due to the replacement of the support roll or the step pad before the calibration of the finishing mill, and thus it is not universal, and the control precision is also low.

[0008] To solve the above technical problem, the present application provides the following technical solution:

[0009] A finishing roll gap inclination pre-setting system based on historical rolling data and calibration data, comprising: a data module, an artificial marking module, a roll gap inclination calculation module, a historical database and a model database; wherein,

[0010] The historical database and the model database are used to store rolling data and calibration data;

[0011] The artificial marking module is used to trigger an artificial marking signal;

[0012] The roll gap inclination calculation module comprises a plurality of pre-set roll gap inclination calculation models;

[0013] In each calibration process of each finishing stand, the system performs the following operations on each finishing stand respectively:

[0014] At the end of the calibration of the current stand, the data module reads the rolling data and calibration data corresponding to the current stand, and reads the rolling data and calibration data in the historical database;

[0015] The roll gap inclination calculation module calculates the roll gap inclination value through the data read by the data module, as the roll gap inclination value corresponding to the current roll, and sends it to the current stand;

[0016] When receiving the storage data signal, the data module updates the historical database; when receiving the manual marking signal, the data module updates the model database, and re-trains the roll gap tilt calculation model in the roll gap tilt calculation module with the data in the updated model database.

[0017] Further, each piece of data stored in the historical database includes: time, work roll roll number, backup roll roll number, upper step position, lower step position, cylinder difference at the end of calibration, and roll gap tilt value.

[0018] Further, at the end of calibration of the current stand, the data module reads the rolling data and calibration data corresponding to the current stand, and reads the rolling data and calibration data in the historical database, specifically:

[0019] At the end of calibration of the current stand, the data module reads the roll numbers of the current work roll and the current backup roll, the upper step position and the lower step position corresponding to the current roll, and the cylinder difference at the end of calibration corresponding to the current roll; and reads the latest time cylinder difference at the end of calibration and the roll gap tilt value from the historical database as the last roll calibration end cylinder difference and the last roll roll gap tilt value respectively; then reads the upper step position, the lower step position, the cylinder difference at the end of calibration and the roll gap tilt value from the historical database which are the latest time and the same as the roll numbers of the current work roll and the current backup roll as the same roll number upper step position, the same roll number lower step position, the same roll number calibration end cylinder difference and the same roll number roll gap tilt value respectively; wherein, in the process of reading data by the data module, if any item of data is read abnormally, the corresponding data is assigned a null value.

[0020] Further, the roll gap tilt calculation model includes a linear model and a particle swarm-random forest model.

[0021] Further, the finishing roll gap tilt presetting system further comprises a field control display module;

[0022] The roll gap tilt calculation module calculates the roll gap tilt value as the roll gap tilt value corresponding to the current roll through the data read by the data module, and sends it to the current stand, specifically:

[0023] If any item of data in the roll numbers of the current work roll and the current backup roll, the upper step position and the lower step position corresponding to the current roll, and the cylinder difference at the end of calibration corresponding to the current roll is a null value, "data reading abnormal, roll gap tilt value is ΔS0" is displayed in the field control display module; wherein,

[0024]

[0025] wherein, is the last roll roll gap tilt value.

[0026] If the same roll number step-up position, the same roll number step-down position, the same roll number calibration end cylinder difference and the same roll number roll gap inclination value are null, the field control display module displays "new roll on machine, roll gap inclination value is ΔS0"; wherein,

[0027]

[0028] If the current roll corresponding upper step-up position is the same as the same roll number step-up position and the current roll corresponding lower step-up position is the same as the same roll number step-down position and the rest of the data are not null, the field control display module displays "linear model, roll gap inclination value is ΔS0"; wherein, ΔS0 is calculated by linear model;

[0029] If the current roll corresponding upper step-up position is not the same as the same roll number step-up position or the current roll corresponding lower step-up position is not the same as the same roll number step-down position and the rest of the data are not null, the field control display module displays "RFR model, roll gap inclination value is ΔS0"; wherein, ΔS0 is calculated by particle swarm-random forest model;

[0030] The calculated roll gap inclination value is taken as the current roll corresponding roll gap inclination value, and is issued to the current stand.

[0031] Further, the formula for calculating ΔS0 by linear model is:

[0032]

[0033] Wherein, represents the same roll number roll gap inclination value; represents the current roll corresponding cylinder difference at the calibration end; represents the same roll number calibration end cylinder difference; represents the preset same roll number roll gap inclination value coefficient; represents the preset cylinder difference coefficient; represents the preset stand coefficient.

[0034] Further, the input of the particle swarm-random forest model is the current roll corresponding upper step-up position and lower step-up position, the current roll corresponding cylinder difference at the calibration end, the same roll number upper step-up position, the same roll number lower step-up position, the same roll number calibration end cylinder difference, the same roll number roll gap inclination value, the last roll calibration end cylinder difference and the last roll roll gap inclination value; the output is the current roll corresponding roll gap inclination value.

[0035] Further, when receiving the storage data signal, the data module updates the historical database, specifically:

[0036] When the storage data signal is received for the first time, the data module stores the current time, the roll numbers of the current work roll and the current support roll, the upper step position and the lower step position corresponding to the current roll, the cylinder difference at the end of calibration corresponding to the current roll, and the roll gap inclination value corresponding to the current roll as a new data to the historical database;

[0037] When the storage data signal is received for the Nth time, the data module updates the roll gap inclination value in the historical database to the roll gap inclination value on the rack at the current time; wherein N is a preset integer greater than 1, and when the calibration start signal is received, the number of times of receiving the storage data signal is cleared; the storage data signal is triggered when the strip steel enters the F1 rack.

[0038] Further, when the artificial marking signal is received, the data module updates the model database, and re-trains the roll gap inclination calculation model in the roll gap inclination calculation module using the data in the updated model database, specifically:

[0039] When the artificial marking signal is received, the data module updates the roll gap inclination value in the historical database to the roll gap inclination value on the rack at the current time calculated by the roll gap inclination calculation module, reads the roll numbers of the current work roll and the current support roll, the upper step position and the lower step position corresponding to the current roll, and the cylinder difference at the end of calibration corresponding to the current roll and the roll gap inclination value corresponding to the current roll after updating; and reads the time newest cylinder difference at the end of calibration and the roll gap inclination value from the historical database as the last roll calibration end cylinder difference and the last roll roll gap inclination value respectively; then reads the time newest upper step position, lower step position, cylinder difference at the end of calibration and roll gap inclination value from the historical database which are the same as the roll numbers of the current work roll and the current support roll as the same roll number upper step position, the same roll number lower step position, the same roll number calibration end cylinder difference and the same roll number roll gap inclination value respectively; wherein, during the data reading process of the data module, if any item of data is read abnormally, the corresponding data is assigned a null value; the read data is stored in the model database to complete the update of the model database, and the particle swarm-random forest model is re-trained using the data in the updated model database.

[0040] Further, the training process of the particle swarm-random forest model includes:

[0041] First, select data from the model database to construct an original data set;

[0042] The bootstrap self-help method is used to randomly extract samples from the original data set to construct a training set for constructing a single decision tree; when constructing each decision tree, for each feature in the feature subset, multiple candidate split points are tried, the feature and split point with the maximum reduction of mean square error are selected as the split criterion, and the recursive splitting is continued until the maximum depth of the decision tree or the minimum sample number of node splitting or the mean square error in the node reaches the preset threshold; meanwhile, the mean square error is used as the optimization target, and the PSO algorithm is used to update the hyperparameters of the random forest by simulating the movement of particles in the search space, the hyperparameters including the number of decision trees, the maximum depth of the decision tree, and the minimum sample number of node splitting;

[0043] The average of the prediction values of all decision trees is the roll gap inclination value calculated by the particle swarm-random forest model.

[0044] The technical scheme provided by the present application has at least the following beneficial effects:

[0045] The technical scheme of the present application uses a data-driven method to establish a scientific finishing roll gap inclination presetting system, accurately calculates the roll gap inclination value for different working conditions, effectively compensates for the asymmetric springback phenomenon of the roll gap on both sides during the rolling process of the rolling mill, and can be updated according to the actual rolling condition, improve the stability of the rolling process, and reduce the intervention of the operator. And the technical scheme of the present application considers the case that the stiffness of the rolling mill changes greatly due to the replacement of the supporting roller or the step position before the finishing mill is calibrated, and has universality. At the same time, the technical scheme of the present application incorporates the method of machine learning, so it also has higher control accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0047] Figure 1 is the structural block diagram of the finishing roll gap inclination presetting system provided by the embodiment of the present application;

[0048] Figure 2 is the working flowchart of the finishing roll gap inclination presetting system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical scheme and advantages of the present application more clear, the following will further describe the embodiments of the present application in combination with the drawings.

[0050] First, it should be pointed out that in the embodiments of the present application, the words "exemplarily", "for example" and the like are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of the word "exemplarily" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be either one of the two.

[0051] The present embodiment provides a finishing roll gap inclination presetting system based on historical rolling data and calibration data, which comprises a data module, a manual marking module, a roll gap inclination calculation module, a historical database and a model database, as shown in Figure 1 The roll gap inclination calculation model comprises a linear model and a particle swarm-random forest model. The data module reads required data from the field PLC and the database at the end of calibration of each rolling mill according to the field rolling signal, transmits the data into the roll gap inclination calculation module, stores the required data into the historical database at the first storage data signal, and updates the data at the Nth storage data signal. The manual marking module is equipped with a manual marking button in the field, which updates the data in the historical database, stores the required data into the model database, and re-trains the model in the roll gap inclination calculation module. The roll gap inclination calculation model judges the trigger logic according to the data transmitted by the data module at the end of calibration of each stand according to the field rolling signal, calculates the roll gap inclination value, and sends the value to each rolling mill and displays it in the field control display module.

[0052] Specifically, as shown in Figure 2 The data module is specifically used for:

[0053] According to the field rolling signal, the current work roll and backup roll roll number, the up and down step position, and the calibration end cylinder difference are read from the field PLC equipped on the rolling mill at the end of calibration of each rolling mill, and any abnormal reading is assigned a null value, which is transmitted into the roll gap inclination calculation module. The latest calibration end cylinder difference and roll gap inclination value in the historical data stored in the historical database are found, and the previous roll calibration end cylinder difference and the previous roll roll gap inclination value are correspondingly assigned, which are transmitted into the roll gap inclination calculation module. Then, according to the current work roll and backup roll roll number, the latest calibration end cylinder difference, up and down step position and roll gap inclination value of the work roll and backup roll with the same roll number in the historical data stored in the historical database are found, and the same roll number calibration end cylinder difference, same roll number up and down step position and same roll number roll gap inclination value are correspondingly assigned, and if not found, a null value is assigned, which is transmitted into the roll gap inclination calculation module.

[0054] At the first storage data signal, the current time, work roll and backup roll roll number, up and down ladder position, calibration end cylinder difference and roll gap inclination value are stored to the historical database. The storage data signal is the signal before the industrial field strip steel enters the F1 rolling mill, including: the last pass of rough rolling R2, flying shear cutting head, temperature measuring instrument, edger;

[0055] At the Nth storage data signal, the current roll gap inclination value is updated to the historical database. Wherein, N is a configurable parameter, it is considered that the roll gap inclination value has been adjusted accurately before the rolling of the strip steel in this block, and after receiving the storage data signal for the Nth time, the subsequent will no longer receive the signal.

[0056] The artificial marking module is specifically used for:

[0057] The field is equipped with an artificial marking button. By pressing the artificial marking button, the current roll gap inclination value is updated to the historical database, and the current time, work roll and backup roll roll number, up and down ladder position, calibration end cylinder difference and roll gap inclination value are stored to the model database. In the historical database, the calibration end cylinder difference and roll gap inclination value of the last set of work rolls are found, and the calibration end cylinder difference and roll gap inclination value of the last roll are assigned. The calibration end cylinder difference, up and down ladder position and roll gap inclination value with the latest time and the same work roll and backup roll are found, and the calibration end cylinder difference, up and down ladder position and roll gap inclination value with the same roll number are assigned. If not found, assign empty value and store to the model database. According to the updated model database, the particle swarm-random forest model in the roll gap inclination calculation module is retrained.

[0058] Wherein, the particle swarm-random forest model is specifically:

[0059] First, select data from the field database to construct a data set. Use Bootstrap self-help method to randomly select samples from the original data set to construct a training set, which is used to construct a single decision tree. When constructing each decision tree, for each feature in the feature subset, try multiple candidate split points, select the feature and split point with the maximum reduction of mean square error as the split criterion, and recursively split until the maximum depth of the decision tree or the minimum sample number of node splitting or the mean square error in the node reaches the threshold. At the same time, use the mean square error as the optimization target, and use the PSO algorithm to simulate the movement of particles in the search space to iteratively update the hyperparameters of the random forest: the number of decision trees, the maximum depth of the decision tree, and the minimum sample number of node splitting. The average of the prediction values of all decision trees is the roll gap inclination value calculated by the particle swarm-random forest model.

[0060] The roll gap inclination calculation module is specifically used for:

[0061] The data required by the roll gap inclination calculation module includes the current working roll and backup roll roll number, the current upper and lower step position, the current calibration end cylinder difference, the same roll number upper and lower step position, the same roll number roll gap inclination value, the same roll number calibration end cylinder difference, the last roll roll gap inclination value, and the last roll calibration end cylinder difference, wherein:

[0062] If any one of the current working roll and backup roll roll number, the current upper and lower step position, and the current roll number calibration end cylinder difference is null, the field control display module displays "data reading abnormality, roll gap inclination ΔS0", and the last roll roll gap inclination value is sent to each rolling mill:

[0063]

[0064] wherein, is the roll gap inclination value of the last roll, in mm, obtained from the database;

[0065] If the same roll number upper and lower step position, the same roll number roll gap inclination value, and the same roll number calibration end cylinder difference are null, the current working roll or backup roll is a new roll, the field control display module displays "new roll on machine, roll gap inclination ΔS0", and the last roll roll gap inclination value is sent to each rolling mill:

[0066]

[0067] wherein, is the roll gap inclination value of the last roll, in mm, obtained from the database;

[0068] If the current upper and lower step position is the same as the same roll number upper and lower step position, and the remaining data are not null, the linear model is triggered to calculate the roll gap inclination value, the field control display module displays "linear model, roll gap inclination ΔS0", and the model calculation value is sent to each rolling mill:

[0069]

[0070] wherein, is the same roll number roll gap inclination value, in mm, obtained from the database;

[0071] is the current end calibration cylinder difference, in mm, obtained from the communication field PLC;

[0072] is the same roll number calibration end cylinder difference, in mm, obtained from the database;

[0073] is the same roll number roll gap inclination value coefficient, and the set value is shown in Table 1:

[0074] Table 1 Same roll number roll gap inclination value coefficient

[0075]

[0076] is a cylinder difference coefficient, and the set value is shown in Table 2:

[0077] Table 2 Cylinder difference coefficient

[0078]

[0079] is a stand coefficient, and the set value is shown in Table 3:

[0080] Table 3 Stand coefficient

[0081]

[0082] If the current upper and lower step positions are different from the upper and lower step positions of the same roll number, and the remaining data are not null, the roll gap inclination value is calculated by the particle swarm-random forest model, the field control display module displays "RFR model, roll gap inclination ΔS0", and the model calculation value is sent to each rolling mill. The input data required by the particle swarm-random forest model are the current upper and lower step positions, the current calibration end cylinder difference, the upper and lower step positions of the same roll number, the roll gap inclination value of the same roll number, the calibration end cylinder difference of the same roll number, the roll gap inclination value of the last roll, and the calibration end cylinder difference of the last roll.

[0083] Next, the implementation process of the scheme of the present application is described by taking the F7 stand of the 1580 production line of a certain factory as an example.

[0084] First, the historical rolling data and calibration data are collected to train the particle swarm-random forest model: according to the collected historical rolling data and calibration data, the data related to the roll gap inclination preset are screened out, including the roll number of the current work roll and backup roll, the current upper and lower step positions, the current calibration end cylinder difference, the upper and lower step positions of the same roll number, the roll gap inclination value of the same roll number, the calibration end cylinder difference of the same roll number, the roll gap inclination value of the last roll, and the calibration end cylinder difference of the last roll, to construct a data set. Part of the data is shown in Table 4.

[0085] Table 4 Part of the data in the data set

[0086]

[0087]

[0088] Bootstrap self-help method is used to randomly extract samples from the data set to construct the training set for building single decision tree. When building each decision tree, for each feature in the feature subset, multiple candidate split points are tried, and the feature and split point with the maximum reduction in mean square error are selected as the split criterion. The recursive splitting is continued until the maximum depth of the decision tree or the minimum sample size of node splitting or the mean square error in the node reaches the threshold. At the same time, the mean square error is used as the optimization objective, and the PSO algorithm is used to update the hyperparameters of the random forest by simulating the movement of particles in the search space: the number of decision trees, the maximum depth of the decision tree, and the minimum sample size of node splitting. The average of the prediction values of all decision trees is the roll gap inclination value calculated by the particle swarm-random forest model. Thus, the training of the particle swarm-random forest model is completed, and the roll gap inclination value can be calculated according to the input data.

[0089] According to the field rolling signal, when the F7 rolling mill calibration end signal is received, the data module communicates with the field PLC to read the current upper work roll number FW61910, lower work roll number FW61907, upper support roll number FB20002, lower support roll number FB20001, upper step position 3, lower step position 3, calibration end cylinder difference -2.36 mm, and transmits them to the roll gap inclination calculation model.

[0090] In the database historical data, the latest calibration end cylinder difference -2.63 mm and roll gap inclination value -0.6 mm are found, which correspond to the last roll calibration end cylinder difference and roll gap inclination value, and are transmitted to the roll gap inclination calculation model.

[0091] According to the current work roll and support roll numbers, the latest calibration end cylinder difference -2.27 mm, upper step position 3, lower step position 3, and roll gap inclination value -0.58 mm are found in the database historical data, which correspond to the same roll number calibration end cylinder difference, same roll number upper and lower step positions, and same roll number roll gap inclination value, and are transmitted to the roll gap inclination calculation model.

[0092] The current upper and lower step positions are the same as the same roll number upper and lower step positions, and the remaining data are not empty, triggering the linear model to calculate the roll gap inclination value:

[0093]

[0094] wherein, is the same roll number roll gap inclination value, which is -0.58 mm obtained from the database;

[0095] is the current end calibration cylinder difference, which is -2.36 mm obtained by communicating with the field PLC;

[0096] The same roll number calibration end cylinder difference is obtained from the database, and is-2.27mm;

[0097] The same roll number roll gap inclination value coefficient is set to 1;

[0098] The oil cylinder difference coefficient is set to 1;

[0099] The frame coefficient is set to 1;

[0100] The F7 rolling mill roll gap inclination value is calculated as-0.67mm; .

[0101] The "linear model, roll gap inclination-0.67mm" is displayed on the field control interface, and the model calculation value is sent to the F7 rolling mill.

[0102] Before the strip steel enters the F1 frame, the current time, the upper work roll roll number FW61910, the lower work roll roll number FW61907, the upper support roll roll number FB20002, the lower support roll roll number FB20001, the current upper and lower step positions 3, the current lower step position 3, the current calibration end cylinder difference-2.63mm, and the current roll gap inclination value-0.67mm are stored in the database;

[0103] When the fifth data signal is stored or the manual marking signal is received, the current roll gap inclination value-0.69mm is updated to the database.

[0104] After the completion of the current rolling plan, the work roll of the F7 rolling mill is replaced, and calibration is performed.

[0105] When the F7 rolling mill calibration end signal is received, the data module communicates with the field PLC to read the current upper work roll roll number FW61940, the lower work roll roll number FW61939, the upper support roll roll number FB20002, the lower support roll roll number FB20001, the upper step position 4, the lower step position 4, the calibration end cylinder difference-2.06mm, and transmits the roll gap inclination calculation model.

[0106] The latest calibration end cylinder difference-2.29mm and the roll gap inclination value-0.74mm in the database historical data are searched, and the previous roll calibration end cylinder difference and the same roll number roll gap inclination value are assigned, and the roll gap inclination calculation model is transmitted.

[0107] According to the current work roll and support roll roll number, the latest calibration end cylinder difference-2.31mm of the same work roll and support roll, the upper step position 3, the lower step position 4, and the roll gap inclination value-0.69mm in the database historical data are searched, and the same roll number calibration end cylinder difference, the same roll number upper and lower step positions, and the same roll number roll gap inclination value are assigned, and the roll gap inclination calculation model is transmitted;

[0108] The current up-down step position is different from the up-down step position of the same roll number, and the rest of the data is not null value, triggering the particle swarm-random forest model to calculate the roll gap inclination value as .

[0109] The field control interface displays "RFR model, roll gap inclination -0.83mm", and the model calculation value is issued to the F7 rolling mill.

[0110] Before the strip steel enters the F1 rack, the current time, the upper work roll roll number FW61940, the lower work roll roll number FW61939, the upper support roll roll number FB20002, the lower support roll roll number FB20001, the current up-down step position 4, the current down step position 4, the current calibration end cylinder difference -2.06mm and the current roll gap inclination value -0.83mm are stored to the database.

[0111] When the 5th storage data signal or the artificial marking signal is received, the current roll gap inclination value -0.93mm is updated to the database.

[0112] In summary, the embodiment uses a data-driven approach to establish a scientific finishing roll gap inclination presetting system that accurately calculates the roll gap inclination value for different working conditions, effectively compensates for the asymmetric springback phenomenon of the two sides of the roll gap during the rolling process, and can be updated according to the actual rolling situation, improving the stability of the rolling process and reducing operator intervention. The technical solution of the embodiment also considers the case where the support roll or step pad is replaced before the finishing mill is calibrated, resulting in a large change in the stiffness of the two sides of the mill, making it universally applicable. At the same time, the technical solution of the embodiment incorporates machine learning methods, so it also has higher control accuracy.

[0113] Moreover, it should be noted that the present application can be provided as a method, an apparatus, or a computer program product. Therefore, the embodiments of the present application can take the form of an entirely or partially hardware embodiment, an entirely or partially software embodiment, or an embodiment combining software and hardware aspects. Furthermore, when implemented in software, the embodiments of the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, a computer diskette, an optical storage medium, a magnetic storage medium, and a semiconductor memory device). The computer program product includes one or more computer instructions that when loaded and executed by a computer, cause the computer to carry out the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website, a computer, a server, or a data center to another website, computer, server, or data center through a wired (for example, infrared, wireless, microwave, or the like) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, data center, or the like, including one or more collections of available media. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0114] The embodiments of the present application are described with reference to flowcharts and / or block diagrams of the method, terminal device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device that implements the flowcharts and / or block diagrams. Figure 1 The flowcharts and / or block diagrams Figure 1 The device that implements the functions specified in one or more flows and / or blocks.

[0115] These computer program instructions can also be stored in a computer-readable storage medium that can direct the computer or other programmable data processing terminal device to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a product including instruction devices that implement the flowcharts and / or block diagrams. Figure 1 The flowcharts and / or block diagrams Figure 1the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing terminal devices, so that a series of operational steps are performed on the computer or other programmable terminal devices to generate a computer implemented process, thus the instructions executed on the computer or other programmable terminal devices provide a process for implementing the functions specified in the flowchart block or blocks. Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing terminal devices, so that a series of operational steps are performed on the computer or other programmable terminal devices to generate a computer implemented process, thus the instructions executed on the computer or other programmable terminal devices provide a process for implementing the functions specified in the flowchart block or blocks. Figure 1 the functions specified in the individual block or blocks. Such computer program instructions can also be loaded into a computer or other programmable data processing terminal devices, so that a series of operational steps are performed on the computer or other programmable terminal devices to generate a computer implemented process, thus the instructions executed on the computer or other programmable terminal devices provide a process for implementing the functions specified in the flowchart block or blocks.

[0116] It should also be noted that, in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such a process, method, article or terminal device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or terminal device including the element. In addition, the term "and / or" is merely a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which means that A exists alone, A and B exist together, B exists alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the preceding and following associated objects, but it can also represent an "and / or" relationship, which can be understood in the context before and after. "At least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including single item or any combination of multiple items. For example, at least one of a, b or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0117] In addition, it can be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0118] Those skilled in the art can appreciate that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or in a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0119] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of functional modules / units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms. The units described as separate components can be or can not be physically separated, and the components displayed as units can be or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment. In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present, or two or more units can be integrated in one unit.

[0120] If the method is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0121] Finally, it should be noted that the above description is only the preferred embodiment of the application, it should be pointed out that although the preferred embodiment of the application has been described, for those skilled in the art, once the basic creative concept of the application is known, several improvements and refinements can be made without departing from the principles of the application, and these improvements and refinements should also be considered as the protection scope of the application. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the application.

Claims

1. A pre-setting system for the roll gap inclination of a finishing mill based on historical rolling data and calibration data, characterized in that, The finishing mill roll gap tilt presetting system includes: a data module, a manual marking module, a roll gap tilt calculation module, a historical database, and a model database; wherein... The historical database and the model database are used to store rolling data and calibration data; The artificial marking module is used to trigger the artificial marking signal; The roll gap tilt calculation module includes a variety of preset roll gap tilt calculation models; During each calibration process of each finishing mill stand, the system performs the following operations on each finishing mill stand: When the calibration of the current stand is completed, the data module reads the rolling data and calibration data corresponding to the current stand, and also reads the rolling data and calibration data from the historical database; The roll gap tilt calculation module calculates the roll gap tilt value using the data read by the data module, uses it as the roll gap tilt value corresponding to the current roll, and sends it to the current frame. When a stored data signal is received, the data module updates the historical database; when a manual labeling signal is received, the data module updates the model database and retrains the roll gap tilt calculation model in the roll gap tilt calculation module using the data in the updated model database.

2. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 1, characterized in that, Each piece of data stored in the historical database includes: time, working roll number, support roll number, upper step position, lower step position, cylinder difference at the end of calibration, and roll gap inclination value.

3. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 1, characterized in that, At the end of the current stand calibration, the data module reads the rolling data and calibration data corresponding to the current stand, and also reads the rolling data and calibration data from the historical database, specifically: At the end of the current frame calibration, the data module reads the roll number of the current work roll and the current support roll, the upper and lower step positions corresponding to the current roll, and the cylinder difference at the end of calibration for the current roll; it also reads the latest cylinder difference and roll gap tilt value at the end of calibration from the historical database, which are used as the cylinder difference and roll gap tilt value at the end of calibration for the previous roll, respectively; and then reads the latest upper step position, lower step position, cylinder difference at the end of calibration, and roll gap tilt value that are the same as the roll number of the current work roll and the current support roll from the historical database, which are used as the upper step position, lower step position, cylinder difference at the end of calibration for the same roll number, and roll gap tilt value for the same roll number, respectively; if any data is read abnormally during the data reading process of the data module, the corresponding data is assigned a null value.

4. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 3, characterized in that, The calculation model for the roll gap tilt includes a linear model and a particle swarm-random forest model.

5. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 4, characterized in that, The precision mill roll gap tilt preset system also includes a field control and display module; The roll gap tilt calculation module calculates the roll gap tilt value using the data read from the data module, uses this value as the roll gap tilt value corresponding to the current roll, and sends it to the current stand. Specifically: If any one of the following data is empty: the roll number of the current work roll and the current support roll, the upper and lower step positions corresponding to the current roll, or the cylinder difference at the end of calibration corresponding to the current roll, then the field control display module will display "Data reading abnormal, roll gap tilt value is ΔS0"; where, ΔS0=ΔS pre Where, ΔS pre This is the tilt value of the roll gap of the previous roll; If the upper step position, lower step position, cylinder difference at the end of calibration for the same roll number, and roll gap inclination value are all empty, then the field control display module will display "New roll on machine, roll gap inclination value is ΔS0"; where ΔS0 = ΔS pre If the upper step position corresponding to the current roll is the same as the upper step position of the same roll number and the lower step position corresponding to the current roll is the same as the lower step position of the same roll number, and all other data are not empty, then "linear model, roll gap inclination value is ΔS0" will be displayed in the field control display module; where ΔS0 is calculated by the linear model. If the upper step position corresponding to the current roll is different from the upper step position of the same roll number, or the lower step position corresponding to the current roll is different from the lower step position of the same roll number, and all other data are not empty, then "RFR model, roll gap tilt value is ΔS0" will be displayed in the field control display module; where ΔS0 is calculated by the particle swarm-random forest model. The calculated roll gap inclination value is used as the roll gap inclination value corresponding to the current roll, and then sent to the current stand.

6. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 5, characterized in that, The formula for calculating ΔS0 using a linear model is: Where, ΔS same Indicates the roll gap inclination value for the same roll number; D represents the cylinder difference at the end of the calibration corresponding to the current roll; D same α represents the cylinder difference at the end of calibration for the same roll number; β represents the preset roll gap inclination coefficient for the same roll number; γ represents the preset cylinder difference coefficient; and γ represents the preset frame coefficient.

7. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 5, characterized in that, The inputs to the particle swarm-random forest model are the upper and lower step positions corresponding to the current roll, the cylinder difference at the end of the calibration corresponding to the current roll, the upper step position of the same roll number, the lower step position of the same roll number, the cylinder difference at the end of the calibration of the same roll number, the roll gap inclination value of the same roll number, the cylinder difference at the end of the calibration of the previous roll, and the roll gap inclination value of the previous roll; the output is the roll gap inclination value corresponding to the current roll.

8. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 3, characterized in that, When a stored data signal is received, the data module updates the historical database, specifically by: When the data module receives the storage data signal for the first time, it stores the current time, the roll number of the current working roll and the current support roll, the upper and lower step positions of the current roll, the cylinder difference at the end of the calibration of the current roll, and the roll gap tilt value of the current roll as a new data entry into the historical database. When the stored data signal is received for the Nth time, the data module updates the roll gap tilt value in the historical database to the roll gap tilt value on the stand at the current moment; where N is a preset integer greater than 1, and the number of times the stored data signal is received is cleared when the calibration start signal is received; the stored data signal is triggered before the strip enters the F1 stand.

9. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 4, characterized in that, When a manually labeled signal is received, the data module updates the model database and retrains the roll gap tilt calculation model in the roll gap tilt calculation module using the data in the updated model database, specifically: When the manually marked signal is received, the data module updates the roll gap tilt value in the historical database to the roll gap tilt value on the frame at the current moment. After updating, it reads the roll number of the current work roll and the current support roll, the upper and lower step positions corresponding to the current roll, the cylinder difference at the end of calibration corresponding to the current roll, and the roll gap tilt value corresponding to the current roll; it also reads the latest cylinder difference at the end of calibration and the roll gap tilt value from the historical database, using them as the cylinder difference at the end of calibration for the previous roll and the roll gap tilt value for the previous roll, respectively; and then reads the latest cylinder difference at the end of calibration from the historical database. The latest upper step position, lower step position, cylinder difference at the end of calibration, and roll gap tilt value, which are the same as the current working roll and the current support roll, are respectively used as the upper step position, lower step position, cylinder difference at the end of calibration, and roll gap tilt value of the same roll number; wherein, during the data reading process of the data module, if any data reading is abnormal, the corresponding data is assigned a null value; the read data is stored in the model database, the model database is updated, and the particle swarm-random forest model is retrained using the data in the updated model database.

10. The finishing mill roll gap tilt presetting system based on historical rolling data and calibration data as described in claim 9, characterized in that, The training process of the particle swarm random forest model includes: First, select data from the model database to construct the original dataset; The Bootstrap method is used to randomly sample from the original dataset to construct a training set for building single decision trees. When constructing each decision tree, for each feature in the feature subset, multiple candidate split points are tried, and the feature and split point with the largest reduction in mean squared error are selected as the split criteria. The splitting is recursively performed until the maximum depth of the decision tree, the minimum number of samples for node splitting, or the mean squared error in the node reaches a preset threshold is met. At the same time, the mean squared error is used as the optimization objective, and the PSO algorithm is used to iteratively update the hyperparameters of the random forest by simulating the movement of particles in the search space. The hyperparameters include: the number of decision trees, the maximum depth of the decision tree, and the minimum number of samples for node splitting. The average of the predictions from all decision trees is the roll gap tilt value calculated by the particle swarm random forest model.

Images