CN118080578B - A rolling control device and method based on artificial intelligence and finite element analysis - Google Patents

Abstract

The present application provides a rolling control device and method based on artificial intelligence and finite element analysis. The device and method acquire the initial rolling temperature of each point on the surface of the strip during the rolling process by starting an artificial intelligence client to obtain a strip rolling temperature array; determine a discrete sparse matrix of the strip rolling temperature array, and determine a strip sparse temperature domain corresponding to the strip rolling temperature array by the discrete sparse matrix; perform finite element analysis based on the acquired roll shifting amount and roll temperature to obtain the strip bending roll resistance, and determine the bending roll deformation temperature rise by the strip bending roll resistance; perform temperature aggregation based on the strip sparse temperature domain, the bending roll deformation temperature rise and the medium heat transfer coefficient of the strip to obtain a rolling temperature aggregation value; when the rolling temperature aggregation value is not in a preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill to effectively control the fluctuation degree of the strip rolling temperature, thereby reducing defective products caused by temperature fluctuations.

Description

A rolling control device and method based on artificial intelligence and finite element analysis

Technical Field

The present application relates to the field of rolling control technology, and more specifically, to a rolling control device and method based on artificial intelligence and finite element analysis.

Background technique

Rolling is a metal processing process that uses a rolling mill to press, stretch or extrude metal billets to cause plastic deformation, thereby obtaining a finished product with the desired size, shape and surface quality. A rolling control device is a device used to monitor and control the metal rolling process. The device usually includes sensors, data acquisition systems, analysis software and feedback control systems.

The rolling control device usually includes sensors installed on the rolling mill, which can collect data in the rolling process in real time, such as temperature, pressure, mechanical deformation, etc., and then collect the data obtained by the sensors through the data acquisition system and transmit it to the data processing unit. Then, machine learning or deep learning algorithms are used to analyze and process the collected data in real time to achieve control and regulation of the rolling mill. However, in the prior art, during the rolling of the strip steel material by the rolling mill, the surface temperature distribution of the strip steel material is uneven, and when rolling through the rollers, the roller temperature is affected by many factors and is difficult to control, and the roller temperature will affect the surface temperature of the strip steel material, causing the strip steel rolling temperature to change, which deviates greatly from the preset rolling temperature value, affecting the strip steel rolling quality.

Summary of the invention

The present application provides a rolling control device and method based on artificial intelligence and finite element analysis. During the strip rolling process, the fluctuation degree of the strip rolling temperature can be effectively controlled to reduce defective products caused by temperature fluctuations.

In a first aspect, the present application provides a rolling control method based on artificial intelligence and finite element analysis, comprising the following steps:

Start the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtain the strip rolling temperature array;

Determine a discrete vector of the strip rolling temperature array, obtain a discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine a strip sparse temperature domain corresponding to the strip rolling temperature array through the discrete sparse matrix;

Obtaining the roll shifting amount and the roll temperature, performing finite element analysis according to the roll shifting amount and the roll temperature, obtaining the strip bending roll resistance, and then determining the bending roll deformation temperature rise degree according to the strip bending roll resistance;

Determine the medium heat transfer coefficient of the steel strip, perform temperature aggregation based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient, and obtain a rolling temperature aggregation value;

When the rolling temperature aggregate value is not within the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill.

In some embodiments, starting the artificial intelligence client to collect the initial rolling temperature of each point on the surface of the strip during the rolling process, and then obtaining the strip rolling temperature array specifically includes:

For each strip surface point, determine the temperature mutation value corresponding to the strip surface point according to the initial rolling temperature corresponding to the strip surface point at all sampling moments, and then obtain the temperature mutation value corresponding to each strip surface point;

Eliminate all initial rolling temperatures corresponding to the strip surface points whose temperature mutation values are higher than a preset mutation threshold, thereby obtaining the strip surface temperature missing points;

The missing points on the strip surface temperature are filled with temperature using all the initial rolling temperatures corresponding to the strip surface points whose temperature mutation values are lower than the preset mutation threshold, and then a strip rolling temperature array is formed by the initial rolling temperatures corresponding to all the strip surface points.

In some embodiments, determining the strip steel sparse temperature domain corresponding to the strip steel rolling temperature array by the discrete sparse matrix specifically includes:

Performing eigenvalue decomposition on the discrete sparse matrix to obtain eigenvalues and eigenvectors;

Constructing a rolling temperature projection matrix according to the eigenvalues and the eigenvectors;

The strip steel rolling temperature array is projected through the rolling temperature projection matrix, thereby obtaining a strip steel sparse temperature domain corresponding to the strip steel rolling temperature array.

In some embodiments, performing finite element analysis based on the roll shifting amount and the roll temperature to obtain the strip bending resistance specifically includes:

Obtain the finite element model of strip rolling in the finite element analysis software;

The roll shifting amount and the roll temperature are input into the finite element model of the strip rolling to simulate the strip rolling stress, and then the strip bending resistance is obtained.

In some embodiments, the rolling temperature aggregation value obtained by performing temperature aggregation on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient specifically includes:

Determining the strip rolling temperature according to the strip rarefaction temperature domain;

The bending roll deformation temperature rise is converted into the strip temperature rise through the medium heat transfer coefficient;

The strip rolling temperature and the strip temperature rise are aggregated into a rolling temperature aggregate value.

In some embodiments, when the rolling temperature aggregate value is not within the preset rolling temperature range, the automatic adjustment of the roll temperature of the strip rolling mill by the artificial intelligence control center specifically includes:

When the rolling temperature aggregate value is higher than the upper limit of the preset rolling temperature range, increasing the roll temperature of the strip rolling mill;

When the rolling temperature aggregate value is lower than the preset lower limit of the rolling temperature range, the roll temperature of the strip rolling mill is reduced.

In some embodiments, the roller shifting amount is obtained by a laser rangefinder, and the roller temperature is obtained by an infrared thermometer.

In a second aspect, the present application provides a rolling control device based on artificial intelligence and finite element analysis, comprising a data processing unit, wherein the data processing unit comprises:

The acquisition module is used to start the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtain the strip rolling temperature array;

A processing module, used to determine a discrete vector of the strip rolling temperature array, obtain a discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine a strip sparse temperature domain corresponding to the strip rolling temperature array from the discrete sparse matrix;

The processing module is further used to obtain the roll shifting amount and the roll temperature, perform finite element analysis according to the roll shifting amount and the roll temperature, obtain the strip bending roll resistance, and then determine the bending roll deformation temperature rise degree through the strip bending roll resistance;

The processing module is further used to determine the medium heat transfer coefficient of the steel strip, and to perform temperature aggregation based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient to obtain a rolling temperature aggregation value;

The automatic adjustment module is used to automatically adjust the roller temperature of the strip rolling mill by the artificial intelligence control center when the rolling temperature aggregation value is not in the preset rolling temperature range.

In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned rolling control method based on artificial intelligence and finite element analysis.

In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned rolling control method based on artificial intelligence and finite element analysis when executed.

The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

In the present application, first, the artificial intelligence client is started to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then the strip rolling temperature array is obtained; the discrete vector of the strip rolling temperature array is determined, and the discrete sparse matrix of the strip rolling temperature array is obtained through the discrete vector. The discrete sparse matrix identifies the areas and factors that affect the accuracy of the rolling temperature data, which is convenient for identifying and eliminating unreliable or interfered rolling temperature data, and improving the accuracy of the rolling temperature data. Then, the temperature is aggregated by the sparse temperature domain of the strip, the temperature rise of the bending roll deformation and the heat transfer coefficient of the medium to obtain the rolling temperature aggregation value. The sparse temperature domain of the strip, the temperature rise of the bending roll deformation and the heat transfer coefficient of the medium are combined to comprehensively consider the influence of different factors on the strip temperature, thereby improving the comprehensiveness and accuracy of the rolling temperature aggregation value, and can optimize the rolling parameters and control. A control strategy is adopted to more accurately control the rolling temperature of the strip. Finally, when the rolling temperature aggregation value is not in the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roller temperature of the strip rolling mill. During the rolling process of the strip material, the strip will contact the roller of the rolling mill. Therefore, the surface temperature of the strip is much higher than the roller temperature. At this time, the contact between the two will cause heat to be transferred from the strip material to the roller, thereby reducing the temperature of the strip. During automatic adjustment, the temperature drop of the strip rolling can be changed by increasing or decreasing the roller temperature, thereby preventing the strip rolling temperature from deviating from the preset rolling temperature range. The preset rolling temperature range represents the normal temperature range of strip rolling. During the strip rolling process, the fluctuation degree of the strip rolling temperature is effectively controlled, thereby reducing defective products caused by temperature fluctuations.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

FIG1 is an exemplary flow chart of a rolling control method based on artificial intelligence and finite element analysis according to some embodiments of the present application;

FIG2 is an exemplary flow chart of determining a strip rolling temperature array according to some embodiments of the present application;

FIG3 is an exemplary flow chart of determining a rarefaction temperature domain of a steel strip according to some embodiments of the present application;

FIG4 is a schematic diagram of exemplary hardware and/or software of a temperature control unit according to some embodiments of the present application;

FIG5 is a schematic diagram of the structure of a computer device for implementing a rolling control method based on artificial intelligence and finite element analysis according to some embodiments of the present application.

Detailed ways

The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

The embodiment of the present application provides a rolling control device and method based on artificial intelligence and finite element analysis, the core of which is to start the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtain the strip rolling temperature array; determine the discrete vector of the strip rolling temperature array, and obtain the discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine the strip sparse temperature domain corresponding to the strip rolling temperature array by the discrete sparse matrix; obtain the roll shifting amount and the roll temperature, and according to the roll shifting amount and the roll temperature Finite element analysis is performed to obtain the strip bending roll resistance, and then the bending roll deformation temperature rise is determined through the strip bending roll resistance; the medium heat transfer coefficient of the strip is determined, and the temperature aggregation is performed on the strip sparse temperature domain, the bending roll deformation temperature rise and the medium heat transfer coefficient to obtain the rolling temperature aggregation value; when the rolling temperature aggregation value is not in the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill, and effectively controls the fluctuation degree of the strip rolling temperature during the strip rolling process to reduce defective products caused by temperature fluctuations.

In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the drawings and specific implementation methods of the specification. Referring to FIG1 , this figure is an exemplary flow chart of a rolling control method based on artificial intelligence and finite element analysis according to some embodiments of the present application. The rolling control method 100 based on artificial intelligence and finite element analysis mainly includes the following steps:

In step 101, the artificial intelligence client is started to collect the initial rolling temperature of each point on the surface of the strip during the rolling process, and then the strip rolling temperature array is obtained.

Preferably, in some embodiments, referring to FIG. 2 , which is an exemplary flow chart of determining the strip rolling temperature array in some embodiments of the present application, the strip rolling temperature array can be determined in the present embodiment by the following steps:

First, in step 1011, for each strip surface point, the temperature mutation value corresponding to the strip surface point is determined according to the initial rolling temperature corresponding to the strip surface point at all acquisition moments, thereby obtaining the temperature mutation value corresponding to each strip surface point;

Secondly, in step 1012, all initial rolling temperatures corresponding to the strip surface points whose temperature mutation values are higher than the preset mutation threshold are eliminated, thereby obtaining the strip surface temperature missing points;

Finally, in step 1013, the missing points on the strip surface temperature are filled with all the initial rolling temperatures corresponding to the strip surface points whose temperature mutation values are lower than the preset mutation threshold, and then a strip rolling temperature array is formed by the initial rolling temperatures corresponding to all the strip surface points.

In the above embodiment, the temperature mutation value corresponding to the strip surface point can be determined according to the initial rolling temperature corresponding to the strip surface point at all acquisition moments in the following manner, namely:

Determine the average initial rolling temperature of the strip surface points corresponding to all acquisition moments;

Determine the dispersion of the initial rolling temperature corresponding to the surface points of the strip at all acquisition moments;

The temperature mutation value corresponding to the surface point of the strip is determined by the average value of the initial rolling temperature corresponding to all the acquisition moments and the dispersion of the initial rolling temperature corresponding to all the acquisition moments. In specific implementation, the temperature mutation value can be determined according to the following formula:

S _i = exp(γ _i ) + μ _i

Among them, _Si represents the temperature mutation value corresponding to the i-th strip surface point, _μi represents the average of the initial rolling temperatures corresponding to the i-th strip surface point at all sampling moments, and _γi represents the discreteness of the initial rolling temperatures corresponding to the i-th strip surface point at all sampling moments. It should be noted that in the present application, the temperature mutation value represents the degree of deviation of the initial rolling temperatures corresponding to the strip surface points at all sampling moments relative to the conventional rolling temperature value, and the discreteness represents the degree of difference between the initial rolling temperatures corresponding to the strip surface points at all sampling moments. The variance of the initial rolling temperatures corresponding to the strip surface points at all sampling moments can be used as the discreteness of the initial rolling temperatures corresponding to the strip surface points at all sampling moments.

In the specific implementation, the artificial intelligence client is started, and the artificial intelligence technology can be used to realize the intelligent temperature control of the rolling mill equipment, monitor the sensor data and adjust the parameters in the rolling process in real time to ensure that the size, shape and quality of the strip product meet the expectations at the rolling temperature. First, the initial rolling temperature of each point on the strip surface during the rolling process can be collected through the infrared thermometer in the artificial intelligence client, and the initial rolling temperature of each point on the strip surface can be collected multiple times through the infrared thermometer, that is, each strip surface point corresponds to multiple initial rolling temperatures at different collection times. Secondly, for each strip surface point, the temperature mutation value corresponding to the strip surface point is determined according to the initial rolling temperature corresponding to the strip surface point at all collection times, and then the temperature mutation value corresponding to each strip surface point is obtained. Then, if the temperature mutation value is lower than the preset mutation threshold, it means that all the initial rolling temperature values corresponding to the strip surface point are in line with the conventional temperature values during the rolling process. If the temperature mutation value is higher than the preset mutation threshold, it means that the strip surface All initial rolling temperature values corresponding to the point do not conform to the conventional temperature values during the rolling process, which may be caused by the interference caused by the rolling environment or the error of the infrared thermometer. Therefore, all initial rolling temperatures corresponding to the strip surface points with temperature mutation values higher than the preset mutation threshold are eliminated, and the strip surface point is used as the strip surface temperature missing point, that is, the strip surface temperature missing point has no corresponding rolling temperature. Finally, the strip surface temperature missing point is temperature-filled by all initial rolling temperatures corresponding to the strip surface points with temperature mutation values lower than the preset mutation threshold. The mean value of all initial rolling temperatures corresponding to the strip surface points with temperature mutation values lower than the preset mutation threshold can be filled into the strip surface temperature missing point, so that all strip surface points have corresponding initial rolling temperatures. The strip rolling temperature array is composed of the initial rolling temperatures corresponding to all strip surface points. For example, there are n strip surface points and m collection moments, then the strip rolling temperature array is an n*m data matrix containing the initial rolling temperatures.

It should be noted that the above steps can eliminate abnormal rolling temperature data caused by noise or other interference, improve the accuracy and reliability of the rolling temperature data, and make the final strip rolling temperature array more stable and reliable. A more accurate strip rolling temperature array helps to monitor the strip rolling process in real time, making the adjustment of rolling parameters more precise, thereby improving the accuracy of the strip rolling temperature.

In step 102, a discrete vector of the strip rolling temperature array is determined, and a discrete sparse matrix of the strip rolling temperature array is obtained through the discrete vector. The strip sparse temperature domain corresponding to the strip rolling temperature array is determined by the discrete sparse matrix.

In some embodiments, a discrete vector of a strip rolling temperature array is determined. In specific implementation, for each column of the strip rolling temperature array, the standard deviation of all initial rolling temperatures corresponding to the column is taken as the discreteness of the column; for each row of the strip rolling temperature array, the standard deviation of all initial rolling temperatures corresponding to the row is taken as the discreteness of the row; the vector composed of all discreteness obtained through the above steps is taken as the discrete vector of the strip rolling temperature array. It should be noted that in this application, the discreteness represents the degree of fluctuation of the initial rolling temperature of each row or column in the strip rolling temperature array relative to the average rolling temperature.

In some embodiments, the discrete sparse matrix of the strip rolling temperature array can be obtained by discrete vectors in the following manner, namely:

Determine the covariance matrix H of the strip rolling temperature array;

Obtain rolling temperature penalty function δ(i, j);

The discrete sparse matrix θ of the strip rolling temperature array is determined according to the discrete vector, the covariance matrix H of the strip rolling temperature array and the rolling temperature penalty function δ(i, j). In specific implementation, the discrete sparse matrix θ of the strip rolling temperature array can be determined according to the following formula:

Among them, n represents the number of rows of the strip rolling temperature array, m represents the number of columns of the strip rolling temperature array, _σi represents the discreteness corresponding to the i-th row of the strip rolling temperature array, and _σj represents the discreteness corresponding to the j-th column of the strip rolling temperature array. It should be noted that in this application, the discrete sparse matrix is a matrix used to improve the accuracy of the strip rolling temperature array, and the rolling temperature penalty function δ(i, j) is a function used to constrain the value of the discrete sparse matrix. In actual implementation, when i and j are equal, the value of the rolling temperature penalty function δ(i, j) is 1, otherwise the value of the rolling temperature penalty function δ(i, j) is 0.

Preferably, in some embodiments, referring to FIG. 3 , which is an exemplary flow chart of determining the rarefaction temperature domain of the steel strip in some embodiments of the present application, the determination of the rarefaction temperature domain of the steel strip in this embodiment can be achieved by the following steps:

First, in step 1021, the discrete sparse matrix is subjected to eigenvalue decomposition to obtain eigenvalues and eigenvectors;

Next, in step 1022, a rolling temperature projection matrix is constructed according to the eigenvalues and the eigenvectors;

Finally, in step 1023, the strip rolling temperature array is projected by the rolling temperature projection matrix, so as to obtain a strip sparse temperature domain corresponding to the strip rolling temperature array.

In the specific implementation, first, the discrete sparse matrix of the strip rolling temperature array is decomposed by eigenvalues to obtain the eigenvalues and eigenvectors of the discrete sparse matrix. It should be noted that the eigenvalues and eigenvectors are one-to-one corresponding. Then, the corresponding eigenvectors are sorted according to the size of the eigenvalues, so as to select the eigenvectors corresponding to the first K largest eigenvalues, and the matrix composed of these K eigenvectors is used as the rolling temperature projection matrix. The rolling temperature projection matrix is a linear transformation matrix containing the most important rolling temperature information, which is used to map the original strip rolling temperature array to the new feature space. Finally, the original strip rolling temperature array is projected by the rolling temperature projection matrix to obtain the strip sparse temperature domain in the new feature space. The data dimension of the strip sparse temperature domain is lower and the proportion of important rolling temperature information contained is higher. The strip sparse temperature domain is a data set containing rolling temperature.

It should be noted that a discrete sparse matrix is constructed through discreteness. The discrete sparse matrix can identify the areas and factors that affect the accuracy of rolling temperature data, which helps to identify and eliminate unreliable or interfered rolling temperature data and improve the quality of rolling temperature data. The sparse temperature domain of the strip is determined by the discrete sparse matrix. This is a set of rolling temperature data considered based on accuracy. The rolling temperature data can be relied on more confidently in the sparse temperature domain of the strip, thereby improving the accuracy of the rolling temperature of the strip.

In step 103, the roll shifting amount and the roll temperature are obtained, and finite element analysis is performed based on the roll shifting amount and the roll temperature to obtain the strip bending resistance, and then the bending deformation temperature rise is determined through the strip bending resistance.

In specific implementation, the amount of roller shifting can be obtained by a laser rangefinder and the roller temperature can be obtained by an infrared thermometer. It should be noted that the amount of roller shifting in the present application refers to the amount of thickness reduction of the strip when passing through the roll gap between the rollers. A laser rangefinder can be used to monitor the position and displacement of the rollers to obtain the amount of roller shifting. The roller temperature refers to the temperature of the roller surface, which can be measured non-contactly by an infrared thermometer. When the strip passes through the rollers of the rolling mill, the rollers apply pressure to the strip, causing the strip material to deform, thereby generating deformation heat, which increases the rolling temperature of the strip. The roller temperature is much lower than the initial rolling temperature of the strip surface. Therefore, when the rollers come into contact with the strip material, the rolling temperature of the strip surface will drop.

In some embodiments, finite element analysis is performed based on the roll shifting amount and the roll temperature to obtain the strip bending resistance, which can be specifically obtained in the following manner, namely:

Obtain the finite element model of strip rolling in the finite element analysis software;

The roll shifting amount and the roll temperature are input into the finite element model of the strip rolling to simulate the strip rolling stress, and then the strip bending resistance is obtained.

In the specific implementation, first, a finite element model of strip rolling is established in the finite element analysis software. The finite element model should take into account the geometric shape of the strip, the mechanical properties of the material and the boundary conditions during the rolling process, such as the force of the rolls, the temperature distribution, etc. Then, the acquired roll shifting amount and roll temperature data are input into the finite element model as boundary conditions or material parameters. The finite element analysis software is used to simulate the force conditions of the strip during the rolling process. This will be based on the input roll shifting amount and roll temperature data, and consider the influence of the pressure and temperature of the roll on the strip. The finite element analysis can calculate the deformation, stress distribution and other parameters of the strip during the rolling process. Based on the simulation results, the bending roll resistance of the strip during the rolling process can be calculated, that is, the strip bending roll resistance. The strip bending roll resistance is the resistance generated by the deformation resistance caused by the strip billet in the roll gap of the rolling mill.

In some embodiments, the following method can be used to determine the deformation temperature rise of the bending roll by using the strip bending roll resistance, namely:

Obtain the influence coefficient R of the stress state in the deformation zone of the strip;

Obtain the heat conduction efficiency β of the strip steel material, the specific heat c of the strip steel material and the density λ of the strip steel material;

Obtain the roller shifting amount η;

The bending roll deformation temperature rise ΔT is determined according to the strip bending roll resistance κ, the stress state influence coefficient R of the strip deformation zone, the roll shifting amount η, the strip material heat conduction efficiency β, the strip material specific heat c and the strip material density λ. In specific implementation, the bending roll deformation temperature rise ΔT can be determined according to the following formula:

Among them, A represents an experimental constant set according to experience. It should be noted that, in this application, the bending roll deformation temperature rise refers to the temperature rise value caused by the plastic deformation of the strip material during the rolling process of the roll. The stress state influence coefficient of the strip deformation zone, the thermal conductivity efficiency of the strip material, the specific heat of the strip material and the density of the strip material can all be obtained through historical experience and the strip material manual, which will not be repeated here.

It should be noted that by calculating the strip bending roll resistance through finite element analysis, the deformation of the strip during the rolling process can be predicted. The accurate calculation of the strip bending roll deformation temperature rise helps to improve the quality of strip production, and the strip bending roll deformation temperature rise can effectively measure the rolling temperature change of the strip.

In step 104, the medium heat transfer coefficient of the steel strip is determined, and the temperature aggregation is performed based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise, and the medium heat transfer coefficient to obtain a rolling temperature aggregation value.

In some embodiments, the medium heat transfer coefficient of the steel strip may be determined in the following manner:

Obtain the radiation heat transfer coefficient G _s ;

Get the strip material size h;

Determine the Nusselt number _Nu ;

Determine the medium thermal conductivity L ₀ of the strip steel material;

The medium heat transfer coefficient G of _the steel strip is determined by the radiation heat transfer coefficient Gs, the steel strip material size h, the Nusselt number _Nu and the medium thermal conductivity _L0 of the steel strip material. In specific implementation, the medium heat transfer coefficient G of the steel strip can be determined according to the following formula:

Among them, the medium heat transfer coefficient of the strip indicates the transfer efficiency of heat to the strip during rolling, the radiation heat transfer coefficient is a parameter that describes the heat transfer of the strip surface through radiation, and the radiation heat transfer coefficient indicates the ratio of the radiation heat flux density per unit surface area to the temperature difference. The Nusselt number is a dimensionless number used to describe heat transfer in fluid flow, and the Nusselt number indicates the ratio of the heat transfer capacity of the fluid during the flow process to the relative contribution of convective heat transfer and conduction heat transfer. In specific implementation, the radiation heat transfer coefficient and the Nusselt number can be obtained through historical experience, which will not be repeated here.

In some embodiments, the rolling temperature aggregation value can be obtained by performing temperature aggregation based on the rarefaction temperature domain of the strip, the bending roll deformation temperature rise and the medium heat transfer coefficient, specifically in the following manner, namely:

Determining the strip rolling temperature according to the strip rarefaction temperature domain;

The bending roll deformation temperature rise is converted into the strip temperature rise through the medium heat transfer coefficient;

The strip rolling temperature and the strip temperature rise are aggregated into a rolling temperature aggregate value.

In specific implementation, first, the strip rolling temperature is determined according to the sparse temperature domain of the strip, and the ratio of the sum of all initial rolling temperatures in the sparse temperature domain of the strip to the total number of initial rolling temperatures in the sparse temperature domain of the strip can be used as the strip rolling temperature, and the strip rolling temperature is used to represent the temperature value of the strip before it is rolled by the rollers. Then, the bending roll deformation temperature rise is converted into the strip temperature rise through the medium heat transfer coefficient, and the product of the medium heat transfer coefficient and the bending roll deformation temperature rise can be used as the strip temperature rise, and the strip temperature rise is used to represent the temperature rise value of the strip after it is rolled by the rollers. Finally, the strip rolling temperature and the strip temperature rise are aggregated into a rolling temperature aggregate value, that is, the sum of the strip rolling temperature and the strip temperature rise is used as the rolling temperature aggregate value, and the rolling temperature aggregate value represents the final temperature value of the strip after it is rolled by the rollers.

It should be noted that the influence of different factors on the strip temperature is comprehensively considered by combining the sparse temperature domain of the strip, the temperature rise of the bending roll deformation and the heat transfer coefficient of the medium, which improves the comprehensiveness and accuracy of the rolling temperature aggregation value, and helps to optimize the rolling parameters and control strategies to more accurately control the rolling temperature of the strip.

In step 105, when the rolling temperature aggregate value is not within the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill.

In some embodiments, when the rolling temperature aggregate value is not within the preset rolling temperature range, the artificial intelligence control center may adjust the roll temperature of the strip rolling mill in the following manner, namely:

When the rolling temperature aggregate value is higher than the upper limit of the preset rolling temperature range, reducing the roll temperature of the strip rolling mill;

When the rolling temperature aggregate value is lower than the preset lower limit of the rolling temperature range, the roll temperature of the strip rolling mill is increased.

In specific implementation, the preset rolling temperature range represents the normal temperature range for strip rolling, which can be obtained through the strip rolling manual. When the rolling temperature aggregation value is higher than the upper limit of the preset rolling temperature range, it indicates that the temperature of the strip material is too high. Rolling at this time will cause structural defects in the strip. In this case, the roller temperature of the strip rolling mill can be reduced. A control instruction can be sent through the artificial intelligence control center to control the cooling system to reduce the roller temperature of the strip rolling mill. When the rolling temperature aggregation value is lower than the lower limit of the preset rolling temperature range, it indicates that the temperature of the strip material is too low. Rolling at this time will cause increased rolling resistance, roll jump, etc., thereby reducing the rolling quality. In this case, the roller temperature of the strip rolling mill can be increased. A control instruction can be sent through the artificial intelligence control center to increase the roll speed to increase the roll temperature of the strip rolling mill. Other methods can also be used, which will not be repeated here.

It should be noted that during the rolling process of the strip steel material, the strip steel will come into contact with the rollers of the rolling mill. At this time, the surface temperature of the strip steel is much higher than the temperature of the rollers. The contact between the two will cause heat to be transferred from the strip steel material to the rollers, thereby lowering the rolling temperature of the strip steel. By raising or lowering the roller temperature, the degree of decrease in the strip steel rolling temperature can be changed, preventing the strip steel rolling temperature from deviating from the preset rolling temperature range, thereby effectively improving the accuracy of the strip steel rolling temperature during the rolling process.

In addition, in another aspect of the present application, in some embodiments, the present application provides a rolling control device based on artificial intelligence and finite element analysis, the device also includes a temperature control unit, refer to FIG4, which is a schematic diagram of exemplary hardware and/or software of the temperature control unit shown in some embodiments of the present application, the temperature control unit 400 includes: an acquisition module 401, a processing module 402 and an automatic adjustment module 403, which are described as follows:

The acquisition module 401 in this application is mainly used to start the artificial intelligence client to collect the initial rolling temperature of each point on the surface of the strip during the rolling process, and then obtain the strip rolling temperature array;

Processing module 402, in this application, processing module 402 is mainly used to determine the discrete vector of the strip rolling temperature array, obtain the discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine the strip sparse temperature domain corresponding to the strip rolling temperature array by the discrete sparse matrix;

The processing module 402 is further used to obtain the roll shifting amount and the roll temperature, perform finite element analysis according to the roll shifting amount and the roll temperature, obtain the strip bending roll resistance, and then determine the bending roll deformation temperature rise degree according to the strip bending roll resistance;

The processing module 402 is further used to determine the medium heat transfer coefficient of the steel strip, and to perform temperature aggregation based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient to obtain a rolling temperature aggregation value;

The automatic adjustment module 403 in the present application is mainly used for automatically adjusting the roller temperature of the strip rolling mill by the artificial intelligence control center when the rolling temperature aggregation value is not in the preset rolling temperature range.

The above describes in detail the examples of the rolling control device and method based on artificial intelligence and finite element analysis provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and/or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned rolling control method based on artificial intelligence and finite element analysis.

In some embodiments, referring to FIG5, the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device for a rolling control method based on artificial intelligence and finite element analysis provided in an embodiment of the present application. The rolling control method based on artificial intelligence and finite element analysis in the above embodiment can be implemented by the computer device shown in FIG5, and the computer device 500 includes at least one processor 501, a memory 502, and at least one communication unit 505, and the computer device 500 can be a terminal device, a server, or a chip.

The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

For example, the computer device 500 may be a chip, the communication unit 505 may be an input and/or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned rolling control method based on artificial intelligence and finite element analysis when executed.

Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. 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 present application.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the present invention.

Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims (5)

1. A rolling control method based on artificial intelligence and finite element analysis, characterized in that it comprises the following steps: Start the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtain the strip rolling temperature array; Determine a discrete vector of the strip rolling temperature array, obtain a discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine a strip sparse temperature domain corresponding to the strip rolling temperature array through the discrete sparse matrix; Obtaining the roll shifting amount and the roll temperature, performing finite element analysis according to the roll shifting amount and the roll temperature, obtaining the strip bending roll resistance, and then determining the bending roll deformation temperature rise degree according to the strip bending roll resistance; Determine the medium heat transfer coefficient of the steel strip, perform temperature aggregation based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient, and obtain a rolling temperature aggregation value; When the rolling temperature aggregate value is not within the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill; Among them, starting the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtaining the strip rolling temperature array specifically includes: For each strip surface point, determine the temperature mutation value corresponding to the strip surface point according to the initial rolling temperature corresponding to the strip surface point at all acquisition moments, and then obtain the temperature mutation value corresponding to each strip surface point; Eliminate all initial rolling temperatures corresponding to the strip surface points whose temperature mutation values are higher than a preset mutation threshold, thereby obtaining the strip surface temperature missing points; Filling the missing points on the surface temperature of the strip steel by using all the initial rolling temperatures corresponding to the surface points of the strip steel whose temperature mutation values are lower than the preset mutation threshold, and then forming a strip steel rolling temperature array by using the initial rolling temperatures corresponding to all the surface points of the strip steel; Wherein, determining the strip steel sparse temperature domain corresponding to the strip steel rolling temperature array by the discrete sparse matrix specifically includes: Performing eigenvalue decomposition on the discrete sparse matrix to obtain eigenvalues and eigenvectors; Constructing a rolling temperature projection matrix according to the eigenvalues and the eigenvectors; Projecting the strip steel rolling temperature array through the rolling temperature projection matrix, thereby obtaining a strip steel sparse temperature domain corresponding to the strip steel rolling temperature array; Among them, the finite element analysis is performed according to the roll shifting amount and the roll temperature to obtain the strip bending resistance, which specifically includes: Obtain the finite element model of strip rolling in the finite element analysis software; Inputting the roll shifting amount and the roll temperature into the finite element model of the strip rolling to simulate the strip rolling stress, thereby obtaining the strip bending roll resistance; The rolling temperature aggregation value obtained by performing temperature aggregation on the rarefaction temperature domain of the strip steel, the bending roll deformation temperature rise and the medium heat transfer coefficient specifically includes: Determining the strip rolling temperature according to the strip rarefaction temperature domain; The bending roll deformation temperature rise is converted into the strip temperature rise through the medium heat transfer coefficient; Aggregating the steel strip rolling temperature and the steel strip temperature rise into a rolling temperature aggregate value; Wherein, when the rolling temperature aggregate value is not within the preset rolling temperature range, the artificial intelligence control center automatically adjusts the roll temperature of the strip rolling mill, specifically including: When the rolling temperature aggregate value is higher than the upper limit of the preset rolling temperature range, increasing the roll temperature of the strip rolling mill; When the rolling temperature aggregate value is lower than the preset lower limit of the rolling temperature range, the roll temperature of the strip rolling mill is reduced. 2. The method as claimed in claim 1 is characterized in that the roller shifting amount is obtained by a laser rangefinder and the roller temperature is obtained by an infrared thermometer. 3. A rolling control device based on artificial intelligence and finite element analysis, which is controlled by the method of claim 1, characterized in that the rolling control device based on artificial intelligence and finite element analysis includes a temperature control unit, and the temperature control unit includes: The acquisition module is used to start the artificial intelligence client to collect the initial rolling temperature of each point on the strip surface during the rolling process, and then obtain the strip rolling temperature array; A processing module, used to determine a discrete vector of the strip rolling temperature array, obtain a discrete sparse matrix of the strip rolling temperature array through the discrete vector, and determine a strip sparse temperature domain corresponding to the strip rolling temperature array from the discrete sparse matrix; The processing module is further used to obtain the roll shifting amount and the roll temperature, perform finite element analysis according to the roll shifting amount and the roll temperature, obtain the strip bending roll resistance, and then determine the bending roll deformation temperature rise degree through the strip bending roll resistance; The processing module is further used to determine the medium heat transfer coefficient of the steel strip, and to perform temperature aggregation based on the rarefaction temperature domain of the steel strip, the bending roll deformation temperature rise and the medium heat transfer coefficient to obtain a rolling temperature aggregation value; The automatic adjustment module is used to automatically adjust the roller temperature of the strip rolling mill by the artificial intelligence control center when the rolling temperature aggregation value is not in the preset rolling temperature range. 4. A computer device, characterized in that the computer device comprises a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the rolling control method based on artificial intelligence and finite element analysis as described in any one of claims 1 to 2. 5. A computer-readable storage medium, wherein instructions or codes are stored in the computer-readable storage medium. When the instructions or codes are executed on a computer, the computer implements the rolling control method based on artificial intelligence and finite element analysis as described in any one of claims 1 to 2.