Broadspread correction method, device and equipment for rough rolled piece and storage medium
By obtaining the initial temperature and time of the slab in the heating furnace and combining it with historical data of steel grades to calculate the width correction coefficient, the problem of width variation caused by unstable slab temperature was solved, and more precise width control was achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-18
- Publication Date
- 2026-03-24
AI Technical Summary
In production lines with fluctuating production plans and statuses, the temperature of the slab in the roughing zone is unstable, leading to significant changes in the width of the rough-rolled parts and affecting the accuracy of finished product width control.
By acquiring the initial temperature and heating time of the slab in the heating furnace, as well as historical data based on the steel grade, the first and second width correction coefficients are calculated to correct the original width value. Taking into account the deviations in temperature and time, the rolling reduction is precisely adjusted.
It improves the accuracy of rough-rolled part width control, reduces finished product width anomalies, and enhances the stability and precision of the production process.
Smart Images
Figure CN121715422A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application belongs to the field of automatic control of steel rolling, and particularly relates to a rough rolling piece width correction method, device, equipment, computer readable storage medium and computer program product. BACKGROUND
[0002] In a traditional hot rolling model, the difference between the rolling reduction and the width is generally used to calculate the width change of the rough rolling area. The premise of application of this model is that the temperature of the incoming slab is relatively stable. However, in a production line with variable production plans and production states, the core temperature of the slab is not stable in the rough rolling area. Affected by the iron oxide scale, the temperature meter before rough rolling cannot truly reflect the state of the slab, and the measured temperature may fluctuate greatly, thereby causing a significant change in the width of the rough rolling piece, and further causing the width of the finished product to be abnormal. SUMMARY
[0003] The rough rolling piece width correction method, device, equipment, computer readable storage medium and computer program product provided by the embodiments of the present application can realize rough rolling piece width correction without relying on the premise that the temperature of the slab in the rough rolling area is stable, and further improve the width control precision of the rolling finished product.
[0004] In a first aspect, the embodiments of the present application provide a rough rolling piece width correction method, which comprises the following steps: obtaining the starting temperature of a to-be-corrected slab placed in a heating furnace and the real-time heating time of the to-be-corrected slab in the heating furnace, the historical average starting temperature of a steel grade corresponding to the to-be-corrected slab placed in the heating furnace and the historical heating time of the steel grade in the heating furnace, and a set of width correction coefficients determined based on the steel grade; obtaining a first width correction coefficient from the set of width correction coefficients based on the starting temperature and the historical average starting temperature; obtaining a second width correction coefficient from the set of width correction coefficients based on the real-time heating time and the historical heating time; correcting the original width value of the rough rolling piece corresponding to the to-be-corrected slab by using the first width correction coefficient and the second width correction coefficient.
[0005] In a second aspect, the embodiments of the present application provide a rough rolling piece width correction device, which comprises the following modules: an obtaining module, configured to obtain the starting temperature of a to-be-corrected slab placed in a heating furnace and the real-time heating time of the to-be-corrected slab in the heating furnace, the historical average starting temperature of a steel grade corresponding to the to-be-corrected slab placed in the heating furnace and the historical heating time of the steel grade in the heating furnace, and a set of width correction coefficients determined based on the steel grade; a first calculating module, configured to obtain a first width correction coefficient from the set of width correction coefficients based on the starting temperature and the historical average starting temperature, and calculate a first width correction coefficient; The second calculation module is used to obtain the corresponding second widening coefficient from the widening coefficient set based on the real-time heating time and the historical heating time, and to calculate the second widening correction coefficient. The correction module is used to correct the original width value of the rough-rolled part corresponding to the slab to be corrected using a first width correction coefficient and a second width correction coefficient.
[0006] Thirdly, embodiments of this application provide a width correction device for rough-rolled parts, the device comprising: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements a width correction method for rough-rolled parts as described in the first aspect.
[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement a method for widening correction of a rough-rolled part as described in the first aspect.
[0008] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform a method for widening correction of a rough-rolled part as described in the first aspect.
[0009] This application discloses a method, apparatus, device, computer-readable storage medium, and computer program product for correcting the width spread of a rough-rolled piece. Based on the initial temperature of the slab to be corrected when it enters the heating furnace, and the historical average initial temperature obtained from the historical rolling data of other slabs of the steel grade to which the slab belongs, a first width spread coefficient is obtained from a set of width spread coefficients determined based on the steel grade. This first width spread correction coefficient is then calculated. Simultaneously, based on the actual heating time of the slab after entering the heating furnace and the historical heating time of its steel grade, a second width spread coefficient is obtained from the set of width spread coefficients. This second width spread correction coefficient is then calculated. Finally, the original width spread value is comprehensively corrected based on the two width spread correction coefficients. This application does not consider how the temperature changes after the slab leaves the heating furnace. Instead, it focuses on learning and eliminating the impact of heating furnace process fluctuations on the width of the rough-rolled part. Specifically, considering that the actual starting temperature of the slab entering the heating furnace varies, the actual heating time required to heat the slab to the appropriate target temperature also fluctuates. This application comprehensively considers these two mutually influential factors and corrects the original width value calculated using existing technology. This correction can more closely reflect the actual width of the rough-rolled part, thereby enabling precise control and adjustment of the rolling reduction of the work rolls in the roughing zone and improving the accuracy of finished product width control. Attached Figure Description
[0010] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a schematic flowchart of a method for correcting the width spread of a rough-rolled part according to an embodiment of this application; Figure 2 This is a schematic diagram of a width correction device for a rough-rolled part provided in another embodiment of this application; Figure 3 This is a schematic diagram of a width correction device for rough-rolled parts provided in another embodiment of this application. Detailed Implementation
[0012] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0013] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0014] After refining the molten steel, a solid slab is obtained through continuous casting, preparing it for subsequent rolling. Before rolling, the slab needs to be heated to a uniform high temperature to improve its plasticity. A walking beam or pusher furnace is typically used for heating the slab. Afterwards, high-pressure water is usually used to remove the iron oxide scale from the surface of the hot slab delivered from the furnace. Then, the hot slab undergoes rough rolling, finish rolling, cooling, and coiling. In the rough rolling stage, there are generally two types of work rolls: vertical rolls and horizontal rolls. Horizontal rolls: The roll axis is placed horizontally, applying a vertical force to the workpiece, i.e., squeezing the workpiece from top to bottom (or bottom to top), mainly changing the thickness of the workpiece. Vertical rolls: The roll axis is placed vertically, applying a horizontal force to the workpiece, i.e., squeezing the workpiece from both sides towards the center, mainly changing the width of the workpiece.
[0015] During vertical roll reduction, the metal at the edges flows inward, but most of it remains at the edges, forming a "dog bone." After being rolled by horizontal rolls, this "dog bone" flows back to the edges, a process known as "dog bone recovery." Therefore, when vertical roll reduction is included in the production plan, the effects of dog bone recovery and horizontal width spread need to be considered. Generally, the sum of the dog bone recovery value and the horizontal width spread value is calculated first to obtain the total width spread. Then, the difference between the vertical roll reduction and the total width spread value is used to calculate the width variation of the rough-rolled part in the roughing zone. When vertical roll reduction is not included in the production plan, only the effect of horizontal width spread needs to be considered. This calculation method assumes that the temperature of the incoming slab is relatively stable. However, in actual production, on the one hand, the thermometer before roughing cannot accurately reflect the slab temperature; on the other hand, the core temperature of the slab may fluctuate significantly during roughing. This can lead to large changes in the width spread value of the rough-rolled part in the roughing zone, ultimately resulting in reduced width control accuracy and abnormal width.
[0016] To address the problems of the prior art, embodiments of this application provide a method, apparatus, device, computer-readable storage medium, and computer program product for correcting the width spread of rough-rolled parts. The following first describes a method for correcting the width spread of rough-rolled parts provided by embodiments of this application.
[0017] Figure 1 A schematic flowchart of a method for correcting the width spread of a rough-rolled part according to an embodiment of this application is shown. Figure 1 As shown, the method may include the following steps: S101, obtain the initial temperature of the slab to be corrected placed in the heating furnace and the real-time heating time in the heating furnace, the historical average initial temperature of the steel grade corresponding to the slab to be corrected placed in the heating furnace and the historical heating time in the heating furnace, and the set of width expansion coefficients determined based on the steel grade.
[0018] The original width spread of the slab to be corrected may not accurately reflect the actual situation, thus requiring correction. The original width spread refers to the uncorrected width spread calculated using existing technology; it can be the original horizontal width spread or the original dog-bone recovery value. The horizontal width spread and the dog-bone recovery value each correspond to a set of width spread coefficients. Although the time and temperature data used to correct the original horizontal width spread and the original dog-bone recovery value are consistent, the final calculated width correction coefficients may differ because the width spread coefficients in the sets may vary.
[0019] The initial temperature at which the slab to be corrected is placed in the heating furnace can be called the furnace entry temperature, and the real-time heating time in the heating furnace can be called the furnace time. The steel grade corresponding to the slab to be corrected is a previously rolled steel grade, and correspondingly, historical rolling data will be recorded. The historical rolling data includes the initial temperatures of each slab entering the heating furnace when this steel grade was previously rolled. Based on these several initial temperatures, the historical average initial temperature can be calculated, and then the time required for the heating process can be determined based on the historical average initial temperature, that is, the historical heating time of this steel grade in the heating furnace, a fixed process value.
[0020] S102, based on the starting temperature and the historical average starting temperature, obtain the corresponding first widening coefficient from the widening coefficient set, and calculate the first widening correction coefficient.
[0021] S103, based on the real-time heating time and the historical heating time, obtain the corresponding second widening coefficient from the widening coefficient set, and calculate the second widening correction coefficient.
[0022] In practical applications of this method, S102 and S103 can be performed simultaneously or in any order.
[0023] Considering that in actual production, the initial temperature of the slab placed in the heating furnace may fluctuate around the historical average initial temperature, and the actual heating time required to heat the slab to the target temperature for subsequent rolling and shaping may be inconsistent with the historical heating time previously set based on historical rolling data, the actual furnace temperature of the slab will affect its actual furnace time, causing changes in the heating furnace process state corresponding to the current slab, which in turn leads to a deviation between the original width and spread value calculated based on stable heating furnace process parameters and the actual situation.
[0024] Therefore, this method comprehensively considers the actual heating conditions of the slab to be corrected, as well as the historical heating conditions of the corresponding steel grade of the slab to be corrected. Based on the temperature deviation and time deviation between the actual heating conditions and the historical heating conditions, a width correction coefficient is calculated to make a more comprehensive and accurate correction to the original width value.
[0025] S104, the original width spread value of the rough-rolled part corresponding to the slab to be corrected is corrected using the first width spread correction factor and the second width spread correction factor.
[0026] The correction of the original horizontal width value and the original dog bone restoration value can be performed simultaneously or in any order. Regardless of the method, the correction processes are independent of each other and do not interfere with each other.
[0027] In one embodiment, the set of width extension coefficients can be obtained by training a width extension correction model using historical rolling data of the steel grade corresponding to the slab to be corrected.
[0028] Regarding the acquisition of historical rolling data: If the steel grade has been rolled, there will inevitably be historical rolling data, so the width correction model can be trained directly based on the recorded historical rolling data; if the steel grade has not been rolled and there is no reference grade, then rolling should be carried out first, and field data should be collected and organized to obtain historical rolling data for training the width correction model; if the steel grade has not been rolled but there is a reference grade, then the ready-made width coefficient set corresponding to the reference grade can be obtained directly.
[0029] The relationship between steel grade designation and steel grade code is as follows: the steel grade code is higher in rank. A single steel grade code may contain two or more steel grade designations. When the mechanical properties and other parameters of certain steel grades are similar, these grades are grouped under the same steel grade code. Steel grade designations under the same steel grade code that already have an optimized set of expansion coefficients can serve as reference designations for other steel grade designations. If a steel grade code contains only one steel grade designation, then the steel grade code is equivalent to the steel grade designation.
[0030] In fact, the width expansion coefficient set can also be initially assigned values and then manually adjusted based on historical rolling data, but this is less efficient. Therefore, the method in this embodiment uses an artificial intelligence network model to achieve efficient width expansion coefficient optimization, reducing labor costs and errors caused by manual adjustment.
[0031] In one embodiment, the training process of the widening correction model may include the following steps: Obtain historical rolling data for the steel grade corresponding to the slab to be corrected. The historical rolling data includes the historical starting temperature of the slab in the heating furnace and the historical real-time heating time in the heating furnace, the historical average starting temperature of the steel grade in the heating furnace and the historical heating time in the heating furnace, as well as the historical true width and historical original width of the rough rolled piece corresponding to the slab.
[0032] A width expansion correction model is constructed, which includes: a first calculation function based on a first width expansion coefficient, historical starting temperature and historical average starting temperature, and a second calculation function based on a second width expansion coefficient, historical real-time heating time and historical heating time.
[0033] Historical rolling data is input into the constructed width correction model. During the training process of the width correction model, the first width coefficient of the previous iteration is adjusted. Based on the historical starting temperature and historical average starting temperature, the first width correction coefficient of the current iteration is calculated using the first calculation function. At the same time, the second width coefficient of the previous iteration is adjusted, and based on the historical real-time heating time and historical heating time, the second width correction coefficient of the current iteration is calculated using the second calculation function.
[0034] The historical original width value is corrected based on the first width correction coefficient of the current iteration to obtain the width value of the current iteration. The loss function value of the current iteration is calculated based on the width value of the current iteration and the corresponding historical true width value.
[0035] When the loss function value meets the preset conditions, a trained widening correction model is obtained. The trained widening correction model contains a set of widening coefficients consisting of the optimized first widening coefficient and the second widening coefficient.
[0036] As mentioned earlier, the original width spread value can be either the original horizontal width spread value or the original dog-bone recovery value. Similarly, the historical true width spread value in historical rolling data can be either the historical true horizontal width spread value or the historical true dog-bone recovery value. Correspondingly, the historical original width spread value can be either the historical original horizontal width spread value or the historical original dog-bone recovery value. The learning of the width spread coefficient sets for the original horizontal width spread value and the original dog-bone recovery value can be performed separately or coupled, with the latter having higher learning complexity. If there is no plan for vertical roll pressing of the steel grade corresponding to the slab to be corrected, the width spread coefficient set corresponding to the original horizontal width spread value can be learned first, because there is no interference from dog-bone recovery at this time. If there is a plan for vertical roll pressing later, the width spread coefficient set corresponding to the original dog-bone recovery value can then be learned. In short, it is necessary to ensure the learning accuracy of the width spread correction model so that a good correction effect can be achieved when the model is formally applied.
[0037] During the learning process of the width expansion coefficient set, the initial values of the width expansion coefficient sets corresponding to the original horizontal width expansion value and the original dog bone restoration value can be kept consistent. For example, assuming the width expansion coefficient set is (k,m,g,h), with the values of k and g both ranging from [0.1-0.3] and the values of m and h both ranging from [0-0.1], the initial values of k1, g1, k2, and g2 in the width expansion coefficient set (k1,m1,g1,h1) corresponding to the original horizontal width expansion value and the width expansion coefficient set (k2,m2,g2,h2) corresponding to the original dog bone restoration value can be set to 0.2, and the initial values of m1, h1, m2, and h2 can be set to 0.03. Then, the training of the width expansion correction model can begin. In this example, both the first and second calculation functions are piecewise functions. The first calculation function is divided into two first-branch calculation functions based on the historical starting temperature and the historical average starting temperature. The second calculation function is divided into two second-branch calculation functions based on the historical real-time heating time and the historical heating time. Each first-branch calculation function has a corresponding first broadening coefficient, and each second-branch calculation function has a corresponding second broadening coefficient. During training, the first broadening coefficient in the corresponding first-branch calculation function is adjusted based on the historical starting temperature and the historical average starting temperature, and the second broadening coefficient in the corresponding second-branch calculation function is adjusted based on the historical real-time heating time and the historical heating time. This calculates the first and second broadening correction coefficients for the current iteration. Then, the historical original broadening value is corrected based on these two broadening correction coefficients to obtain the broadening value for the current iteration. A loss function is constructed based on the current iteration's broadening value and its corresponding historical true broadening value. Training is completed when the loss function converges to a preset condition. It can be understood that the input of historical rolling data is generally batch input; therefore, the loss function is also constructed based on several historical true broadening values in the batch input data and the corresponding broadening value for the current iteration.
[0038] In one embodiment, the historical rolling data may also include the steel grade code, rolling thickness range, and rolling width range of the steel grade corresponding to the slab to be corrected.
[0039] As mentioned earlier, steel grade codes can also include steel grade designations, or the steel grade code is equivalent to the steel grade designation. Steel grade codes can be set from 1 to N, with one code for each steel grade. Rolling thickness ranges can be categorized according to product specifications, production line capacity, and standard rolling thickness ranges, such as (0, 1.15], (1.15, 1.3]...(24, 25.4]. Rolling width ranges can also be categorized according to product specifications, production line capacity, and standard rolling thickness ranges, such as (900, 1050], (1050, 1180]...(1900, 2130).
[0040] Thus, the historical rolling data includes the heating furnace process parameters recorded in the secondary mill system corresponding to the heating furnace: steel grade code, rolling thickness range, rolling width range, historical average initial temperature of the steel grade in the heating furnace, and historical heating time in the heating furnace, as shown in Table 1. This provides a process parameter table built within the secondary mill system of the heating furnace, used to assist the roughing rolling calculation model in calculating the slab width control parameters. It is easy to understand that the method steps of this invention can be implemented in the roughing rolling calculation model, which includes a pre-trained width correction model.
[0041] Table 1. Process parameters established within the secondary heating furnace system. Normally, the process parameters of the heating furnace can be maintained and updated within the secondary mill system of the heating furnace. However, considering that the roughing mill model in this method needs to call these parameters, it is necessary to build the same data table in both databases. Therefore, a synchronization flag can be added to the process parameters of the secondary mill system of the heating furnace. When a data record is updated in the secondary mill system of the heating furnace, the synchronization flag is set to 1. Then, a scheduler is created, such as through DB-Link or electronic message, to periodically update the data records with the synchronization flag set to 1 to the secondary mill database of the corresponding rolling line of the roughing mill model. After successful synchronization, the synchronization flag is set to 0; otherwise, it needs to wait for the next synchronization time to prevent data inconsistency between the secondary mill system database and the secondary mill database of the rolling line in the event of communication failure.
[0042] It's understandable that not all data input into the width correction model will be used for iterative calculations. For example, steel grade codes or steel grade designations, rolling thickness ranges, and rolling width ranges may simply serve as labels.
[0043] In one embodiment, determining the width extension coefficient set based on the steel grade may include: Obtain the steel grade code, rolling thickness range, and rolling width range of the steel grade corresponding to the slab to be corrected. Based on at least one dimension of the data, including the steel grade code, rolling thickness range, rolling width range, historical average starting temperature of the steel grade, and historical heating time, obtain the set of width expansion coefficients.
[0044] Based on the above, after technicians input label data in one or more dimensions, they can retrieve the corresponding trained width correction model, which includes an optimized set of width coefficients. Because actual production typically involves many types of steel, each steel grade code or designation corresponds to a trained width correction model, label data is needed for routing to quickly locate the appropriate width correction model. Then, the relevant data of the slab to be corrected is input into the width correction model to output the corrected width value. Alternatively, after locating the width coefficient set of the width correction model, the width correction coefficients are directly calculated based on the constructed calculation function, thereby correcting the original width value.
[0045] In one embodiment, obtaining a first broadening coefficient from a broadening coefficient set based on the initial temperature and the historical average initial temperature, and calculating a first broadening correction coefficient, may include: If the initial temperature is not less than the historical average initial temperature, calculate the temperature ratio between the initial temperature and the historical average initial temperature, and calculate the first broadening correction coefficient based on the temperature ratio and the corresponding first broadening coefficient. When the starting temperature is lower than the historical average starting temperature, the first temperature difference between the starting temperature and the historical average starting temperature is calculated, the second temperature difference between the preset temperature threshold and the historical average starting temperature is calculated, and the first widening correction coefficient is calculated based on the ratio of the first temperature difference to the second temperature difference and the corresponding first widening coefficient.
[0046] In one embodiment, obtaining a first broadening coefficient from a broadening coefficient set based on the initial temperature and the historical average initial temperature, and calculating a first broadening correction coefficient, may include: (1); in, This represents the first width correction factor. This indicates the initial temperature at which the slab to be corrected is placed in the heating furnace. This indicates the historical average starting temperature of the corresponding steel grade of the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This indicates the preset temperature threshold, which can be set to 1000.
[0047] To calculate the first width correction factor corresponding to the original horizontal width value, the following formula can be used: (2); in, This represents the first width correction factor corresponding to the original horizontal width value. express In this case, the first expansion coefficient corresponding to the original horizontal expansion value, express In this case, the first expansion coefficient corresponding to the original horizontal expansion value, This indicates the preset temperature threshold corresponding to the original horizontal width value.
[0048] To calculate the first width correction factor corresponding to the original dog bone restoration value, the following formula can be used: (3); in, This represents the first width correction factor corresponding to the original dog bone restoration value. express In this case, the first expansion coefficient corresponding to the original dog bone restoration value, express In this case, the first expansion coefficient corresponding to the original dog bone restoration value, This indicates the preset temperature threshold corresponding to the original dog bone recovery value.
[0049] In one embodiment, based on the real-time heating time and the historical heating time, obtaining the corresponding second widening coefficient from the widening coefficient set and calculating the second widening correction coefficient may include: If the real-time heating time is not less than the historical heating time, calculate the time ratio of the real-time heating time to the historical heating time, and calculate the second broadening correction coefficient based on the time ratio and the corresponding second broadening coefficient. When the real-time heating time is less than the historical heating time, the first time difference between the real-time heating time and the historical heating time is calculated, the second time difference between the preset time threshold and the historical heating time is calculated, and the second widening correction coefficient is calculated based on the ratio of the first time difference to the second time difference and the corresponding second widening coefficient.
[0050] In one embodiment, based on the real-time heating time and the historical heating time, a corresponding second widening coefficient is obtained from the widening coefficient set, and a second widening correction coefficient is calculated, including: (4); in, This represents the second width correction factor. This indicates the real-time heating time of the slab to be corrected in the heating furnace. This indicates the historical heating time of the steel grade corresponding to the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This represents the preset time threshold, which can be 1000.
[0051] To calculate the second width correction factor corresponding to the original horizontal width value, the following formula can be used: (5); in, This represents the second width correction factor corresponding to the original horizontal width value. express In this case, the second expansion coefficient corresponding to the original horizontal expansion value, express In this case, the second expansion coefficient corresponding to the original horizontal expansion value, This represents the preset time threshold corresponding to the original horizontal width value.
[0052] To calculate the second width correction factor corresponding to the original dog bone restoration value, the following formula can be used: (6); in, This represents the second width correction factor corresponding to the original dog bone restoration value. express In this case, the second expansion coefficient corresponding to the original dog bone restoration value, express In this case, the second expansion coefficient corresponding to the original dog bone restoration value, This indicates the preset time threshold corresponding to the original dog bone recovery value.
[0053] In one embodiment, correcting the original width of the rough-rolled part corresponding to the slab to be corrected using a first width correction factor and a second width correction factor may include: (7); in, This represents the corrected width extension value obtained after correcting the original width extension value of the rough-rolled part corresponding to the slab to be corrected. This represents the original width spread of the rough-rolled part corresponding to the slab to be corrected.
[0054] To correct the original horizontal width spread of the rough-rolled slab, the following formula can be used: (8); in, This represents the corrected horizontal width value obtained after correcting the original horizontal width value of the rough-rolled part corresponding to the slab to be corrected. This represents the original horizontal width spread of the rough-rolled part corresponding to the slab to be corrected.
[0055] To correct the original dogbone recovery value of the rough-rolled slab, the following formula can be used: (9); in, This represents the corrected dogbone recovery value obtained after correcting the original dogbone recovery value of the rough-rolled part corresponding to the slab to be corrected. This represents the original dogbone recovery value of the rough-rolled part corresponding to the slab to be corrected.
[0056] If the calculation method described in this embodiment is used to correct the original width value in a practical application, it can be understood that this calculation method is also used to calculate the width value of the current iteration during the training process of the width correction model.
[0057] Formulas (1)-(9) are merely examples. In actual application of this invention, the formulas can be adjusted as needed based on the principle of the correction method. That is, the above-shown calculation formulas are not the only ones that can achieve the solution of this invention.
[0058] Based on the method for correcting the width spread of a rough-rolled part provided in the above embodiments, this application also provides a specific implementation of a device for correcting the width spread of a rough-rolled part. Please refer to the following embodiments.
[0059] First see Figure 2 The width correction device for rough rolled parts provided in this application embodiment may include an acquisition module 201, a first calculation module 202, a second calculation module 203, and a correction module 204.
[0060] The acquisition module 201 is used to acquire the initial temperature of the slab to be corrected placed in the heating furnace and the real-time heating time in the heating furnace, the historical average initial temperature of the steel grade corresponding to the slab to be corrected placed in the heating furnace and the historical heating time in the heating furnace, and the set of width expansion coefficients determined based on the steel grade. The first calculation module 202 is used to obtain the corresponding first broadening coefficient from the broadening coefficient set based on the starting temperature and the historical average starting temperature, and to calculate the first broadening correction coefficient. The second calculation module 203 is used to obtain the corresponding second widening coefficient from the widening coefficient set based on the real-time heating time and the historical heating time, and to calculate the second widening correction coefficient. The correction module 204 is used to correct the original width value of the rough-rolled part corresponding to the slab to be corrected using a first width correction coefficient and a second width correction coefficient.
[0061] In one embodiment, the first computing module 202 can be used to implement the following steps: If the initial temperature is not less than the historical average initial temperature, calculate the temperature ratio between the initial temperature and the historical average initial temperature, and calculate the first broadening correction coefficient based on the temperature ratio and the corresponding first broadening coefficient. When the starting temperature is lower than the historical average starting temperature, the first temperature difference between the starting temperature and the historical average starting temperature is calculated, the second temperature difference between the preset temperature threshold and the historical average starting temperature is calculated, and the first widening correction coefficient is calculated based on the ratio of the first temperature difference to the second temperature difference and the corresponding first widening coefficient.
[0062] In one embodiment, the first calculation module 202 can specifically be used to execute the following calculation formula: (1); in, This represents the first width correction factor. This indicates the initial temperature at which the slab to be corrected is placed in the heating furnace. This indicates the historical average starting temperature of the corresponding steel grade of the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This indicates the preset temperature threshold.
[0063] In one embodiment, the second computing module 203 can be used to implement the following steps: If the real-time heating time is not less than the historical heating time, calculate the time ratio of the real-time heating time to the historical heating time, and calculate the second broadening correction coefficient based on the time ratio and the corresponding second broadening coefficient. When the real-time heating time is less than the historical heating time, the first time difference between the real-time heating time and the historical heating time is calculated, the second time difference between the preset time threshold and the historical heating time is calculated, and the second widening correction coefficient is calculated based on the ratio of the first time difference to the second time difference and the corresponding second widening coefficient.
[0064] In one embodiment, the second calculation module 203 can specifically be used to execute the following calculation formula: (4); in, This represents the second width correction factor. This indicates the real-time heating time of the slab to be corrected in the heating furnace. This indicates the historical heating time of the steel grade corresponding to the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This indicates a preset time threshold.
[0065] In one embodiment, the correction module 204 can specifically be used to implement the following calculation formula: (7); in, This represents the corrected width extension value obtained after correcting the original width extension value of the rough-rolled part corresponding to the slab to be corrected. This represents the original width spread of the rough-rolled part corresponding to the slab to be corrected.
[0066] In one embodiment, a width correction device for a rough-rolled section may further include a determining module 205 for: Obtain the steel grade code, rolling thickness range, and rolling width range of the steel grade corresponding to the slab to be corrected; Based on data from at least one dimension, including steel grade code, rolling thickness range, rolling width range, historical average starting temperature of the steel grade, and historical heating time, the set of width expansion coefficients can be obtained.
[0067] In one embodiment, a width correction device for rough-rolled parts may further include a training module 206 for: Obtain historical rolling data for the steel grade corresponding to the slab. The historical rolling data includes the historical starting temperature of the slab in the heating furnace and the historical real-time heating time in the heating furnace, the historical average starting temperature of the steel grade in the heating furnace and the historical heating time in the heating furnace, as well as the historical true width and historical original width of the rough rolled piece corresponding to the slab. A width expansion correction model is constructed, which includes: a first calculation function based on a first width expansion coefficient, historical starting temperature and historical average starting temperature, and a second calculation function based on a second width expansion coefficient, historical real-time heating time and historical heating time; Historical rolling data is input into the constructed width correction model. During the training process of the width correction model, the first width coefficient of the previous iteration is adjusted. Based on the historical starting temperature and historical average starting temperature, the first width correction coefficient of the current iteration is calculated using the first calculation function. At the same time, the second width coefficient of the previous iteration is adjusted, and based on the historical real-time heating time and historical heating time, the second width correction coefficient of the current iteration is calculated using the second calculation function. The historical original width value is corrected based on the first width correction coefficient of the current iteration to obtain the width value of the current iteration. The loss function value of the current iteration is calculated based on the width value of the current iteration and the corresponding historical true width value. When the loss function value meets the preset conditions, a trained widening correction model is obtained. The trained widening correction model contains a set of widening coefficients consisting of the optimized first widening coefficient and the second widening coefficient.
[0068] Figure 3 This diagram illustrates the hardware structure of a roughing mill width correction device according to an embodiment of this application. The roughing mill width correction device may include a processor 301 and a memory 302 storing computer program instructions.
[0069] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0070] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.
[0071] In a particular embodiment, memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.
[0072] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the roughing-rolled part width correction methods in the above embodiments.
[0073] In one example, a width correction device for a rough-rolled part may further include a communication interface 303 and a bus 310. Wherein, as Figure 3 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.
[0074] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.
[0075] Bus 310 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.
[0076] The width expansion correction device for the rough-rolled slab can, based on the currently acquired initial temperature of the slab to be corrected in the furnace and its real-time heating time in the furnace, the historical average initial temperature of the steel grade corresponding to the slab to be corrected in the furnace and its historical heating time in the furnace, and the width expansion coefficient set determined based on the steel grade, execute the online data flow billing method in this application embodiment, thereby achieving a combination of... Figure 1 and Figure 2 This describes a method for correcting the width spread of a rough-rolled part.
[0077] Furthermore, in conjunction with the method for width correction of a rough-rolled part in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the methods for width correction of rough-rolled parts in the above embodiments.
[0078] This application also provides a computer program product, including a computer program that, when executed, implements any of the methods for width correction of rough-rolled parts described in the above embodiments.
[0079] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0080] The functional modules shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0081] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0082] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.
[0083] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. A method for correcting the width spread of a rough-rolled part, characterized in that, The method includes: The starting temperature of the slab to be corrected placed in the heating furnace and the real-time heating time in the heating furnace are obtained, as well as the historical average starting temperature of the steel grade corresponding to the slab to be corrected placed in the heating furnace and the historical heating time in the heating furnace, and the set of width expansion coefficients determined based on the steel grade are obtained. Based on the starting temperature and the historical average starting temperature, the corresponding first width expansion coefficient is obtained from the width expansion coefficient set, and the first width expansion correction coefficient is calculated. Based on the real-time heating time and the historical heating time, the corresponding second widening coefficient is obtained from the widening coefficient set, and the second widening correction coefficient is calculated. The original width spread of the rough-rolled part corresponding to the slab to be corrected is corrected using the first width spread correction coefficient and the second width spread correction coefficient.
2. The method according to claim 1, characterized in that, Based on the starting temperature and the historical average starting temperature, a corresponding first width expansion coefficient is obtained from the width expansion coefficient set, and a first width expansion correction coefficient is calculated, including: If the starting temperature is not less than the historical average starting temperature, calculate the temperature ratio between the starting temperature and the historical average starting temperature, and calculate the first broadening correction coefficient based on the temperature ratio and the corresponding first broadening coefficient. When the starting temperature is less than the historical average starting temperature, a first temperature difference between the starting temperature and the historical average starting temperature is calculated, a second temperature difference between a preset temperature threshold and the historical average starting temperature is calculated, and a first widening correction coefficient is calculated based on the ratio of the first temperature difference to the second temperature difference and the corresponding first widening coefficient.
3. The method according to claim 1, characterized in that, Based on the real-time heating time and the historical heating time, a corresponding second widening coefficient is obtained from the widening coefficient set, and a second widening correction coefficient is calculated, including: If the real-time heating time is not less than the historical heating time, calculate the time ratio of the real-time heating time to the historical heating time, and calculate the second broadening correction coefficient based on the time ratio and the corresponding second broadening coefficient. When the real-time heating time is less than the historical heating time, a first time difference between the real-time heating time and the historical heating time is calculated, a second time difference between a preset time threshold and the historical heating time is calculated, and a second widening correction coefficient is calculated based on the ratio of the first time difference to the second time difference and the corresponding second widening coefficient.
4. The method according to claim 2, characterized in that, Based on the starting temperature and the historical average starting temperature, a corresponding first width expansion coefficient is obtained from the width expansion coefficient set, and a first width expansion correction coefficient is calculated, including: ； in, This represents the first width correction factor. This indicates the initial temperature at which the slab to be corrected is placed in the heating furnace. This indicates the historical average starting temperature of the corresponding steel grade of the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This indicates the preset temperature threshold.
5. The method according to claim 3, characterized in that, Based on the real-time heating time and the historical heating time, a corresponding second widening coefficient is obtained from the widening coefficient set, and a second widening correction coefficient is calculated, including: ； in, This represents the second width correction factor. This indicates the real-time heating time of the slab to be corrected in the heating furnace. This indicates the historical heating time of the steel grade corresponding to the slab to be corrected in the heating furnace. express The first expansion factor under the condition, express The first expansion factor under the condition, This indicates a preset time threshold.
6. The method according to any one of claims 1-5, characterized in that, The set of width extension coefficients is obtained by training the width extension correction model using historical rolling data of the steel grade corresponding to the slab to be corrected.
7. The method according to claim 6, characterized in that, The training process of the widening correction model includes: Obtain historical rolling data of the steel grade corresponding to the slab to be corrected. The historical rolling data includes the historical starting temperature of the slab in the heating furnace and the historical real-time heating time in the heating furnace, the historical average starting temperature of the steel grade in the heating furnace and the historical heating time in the heating furnace, as well as the historical true width and historical original width of the rough rolled piece corresponding to the slab. A width expansion correction model is constructed, which includes: a first calculation function based on a first width expansion coefficient, the historical starting temperature and the historical average starting temperature, and a second calculation function based on a second width expansion coefficient, the historical real-time heating time and the historical heating time; The historical rolling data is input into the constructed width correction model. During the training process of the width correction model, the first width coefficient of the previous iteration is adjusted. Based on the historical starting temperature and the historical average starting temperature, the first width correction coefficient of the current iteration is calculated using the first calculation function. At the same time, the second width coefficient of the previous iteration is adjusted, and based on the historical real-time heating time and the historical heating time, the second width correction coefficient of the current iteration is calculated using the second calculation function. The historical original width value is corrected according to the first width correction coefficient of the current iteration and the first width correction coefficient of the current iteration to obtain the width value of the current iteration. The loss function value of the current iteration is calculated based on the width value of the current iteration and the corresponding historical true width value. When the loss function value meets the preset conditions, a trained widening correction model is obtained. The trained widening correction model includes a widening coefficient set composed of the optimized first widening coefficient and the second widening coefficient.
8. The method according to claim 1, characterized in that, The set of width extension coefficients is determined based on the steel grade, including: Obtain the steel grade code, rolling thickness range, and rolling width range of the steel grade corresponding to the slab to be corrected; Based on data from at least one of the following dimensions—steel grade code, rolling thickness range, rolling width range, historical average starting temperature of the steel grade, and historical heating time—a set of width expansion coefficients can be obtained.
9. A width correction device for rough-rolled parts, characterized in that, The device includes: The acquisition module is used to acquire the initial temperature of the slab to be corrected placed in the heating furnace and the real-time heating time in the heating furnace, the historical average initial temperature of the steel grade corresponding to the slab to be corrected placed in the heating furnace and the historical heating time in the heating furnace, and the width expansion coefficient set determined based on the steel grade; The first calculation module is used to obtain the corresponding first widening coefficient from the widening coefficient set based on the starting temperature and the historical average starting temperature, and to calculate the first widening correction coefficient. The second calculation module is used to obtain the corresponding second widening coefficient from the widening coefficient set based on the real-time heating time and the historical heating time, and to calculate the second widening correction coefficient. The correction module is used to correct the original width value of the rough-rolled part corresponding to the slab to be corrected by using the first width correction coefficient and the second width correction coefficient.
10. A width correction device for rough-rolled parts, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements a method for correcting the width spread of a rough-rolled part as described in any one of claims 1-8.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement a method for correcting the width spread of a rough-rolled part as described in any one of claims 1-8.
12. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs a method for correcting the width of a rough-rolled part as described in any one of claims 1-8.