A self-learning correction method and device for finishing mill model
By judging and updating the rolling force value of the finishing mill, the problem of accuracy deterioration caused by interference with the self-learning of the finishing mill model was solved, and the rolling stability and model accuracy were improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHOUGANG JINGTANG IRON & STEEL CO LTD
- Filing Date
- 2023-01-06
- Publication Date
- 2026-05-26
AI Technical Summary
During the hot strip rolling process, the self-learning results of the finishing mill are affected by on-site working conditions or environmental interference, which leads to the deterioration of the model setting accuracy, affects the rolling stability, and may result in scrap.
By determining whether the actual rolling force of the finishing mill is effective, the set value, measured value and recalculated value of the rolling force are obtained, and it is determined whether they meet the preset relationship. If so, the finishing mill model is updated through self-learning, including correcting the recalculated value of the rolling force and the actual value of the deformation resistance, so as to avoid the self-learning result being opposite to the expected direction.
It improves rolling stability, avoids the problem of insufficient actual rolling force due to excessive looper tension, ensures that the self-learning results are consistent with expectations, and improves the accuracy of model setting.
Smart Images
Figure CN116060456B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of hot rolling technology, and in particular to a method and apparatus for self-learning correction of a finishing rolling model. Background Technology
[0002] In the hot strip mill production process, the setting model of the finishing mill is the core control component. Improving the accuracy of the model setting is the main goal of the staff. Self-learning function is currently the most direct and widely used method. However, measured data is the basis of self-learning. When measured data is affected by on-site working conditions or environmental interference, it will directly affect the self-learning results. In severe cases, the application of self-learning results will directly produce adverse consequences, which will further deteriorate the accuracy of the model setting.
[0003] When rolling thin strip steel, the production line may experience excessive tension in the looper within the rolling head area due to the use of a pull sleeve between the stands of the finishing mill. This results in the actual rolling force detected in the corresponding area being lower than expected. When the finishing mill model performs self-learning calculations by collecting the actual rolling force within the corresponding tension influence range, it leads to anomalies in the finishing mill self-learning process. This manifests as the learning result being opposite to the expected direction. As the learning results are continuously applied, the accuracy of the finishing mill model settings gradually deteriorates, directly affecting rolling stability and even causing problems such as scrap.
[0004] Therefore, how to correct the self-learning of the finishing mill model is a technical problem that urgently needs to be solved. Summary of the Invention
[0005] In view of the above problems, the present invention is proposed to provide a method and apparatus for self-learning correction of a finishing mill model to overcome or at least partially solve the above problems.
[0006] In a first aspect, the present invention also provides a self-learning correction method for a finishing mill model, comprising:
[0007] Determine whether the actual rolling force of the finishing mill is effective;
[0008] If not, obtain the rolling force setting value, rolling force measurement value, and rolling force recalculation value of the finishing mill unit;
[0009] Determine whether the rolling force set value, the rolling force measured value, and the rolling force recalculated value satisfy a preset relationship;
[0010] If so, the finishing mill model of the finishing mill unit is updated through self-learning.
[0011] Furthermore, the determination of whether the actual rolling force of the finishing mill is effective includes:
[0012] Obtain the actual maximum tension and stand reference tension of the finishing mill unit;
[0013] Determine whether the actual maximum tension is greater than the frame reference tension.
[0014] Furthermore, the frame reference tension is specifically the product of the set tension and the preset coefficient.
[0015] Further, determining whether the set rolling force value, the measured rolling force value, and the recalculated rolling force value satisfy a preset relationship includes:
[0016] Determine whether the rolling force set value, the rolling force measured value, and the rolling force recalculated value increase or decrease sequentially.
[0017] Furthermore, the self-learning update of the finishing mill model of the finishing mill unit includes:
[0018] The recalculated value of the rolling force is then corrected;
[0019] The finishing mill model is updated through self-learning based on the corrected recalculated rolling force value.
[0020] Furthermore, based on the revised recalculated rolling force, the finishing mill model is updated through self-learning, including:
[0021] The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model;
[0022] Obtain the actual value and calculated value of deformation resistance;
[0023] Determine whether the actual value of the deformation resistance is equal to the calculated value of the deformation resistance;
[0024] If not, the deformation resistance self-learning update will not be performed.
[0025] Furthermore, based on the revised recalculated rolling force, the finishing mill model is updated through self-learning, including:
[0026] The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model;
[0027] Obtain the thickness deviation at the finish rolling exit;
[0028] Determine whether the thickness deviation at the finishing mill exit is 0;
[0029] If not, then roll gap self-learning update will not be performed.
[0030] Secondly, the present invention also provides a finishing mill model self-learning correction device, comprising:
[0031] The first judgment module is used to determine whether the actual rolling force of the finishing mill is effective;
[0032] The acquisition module is used to acquire, if not, the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value of the finishing mill unit;
[0033] The second judgment module is used to determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet preset conditions;
[0034] The update module is used to update the finishing mill model of the finishing mill unit through self-learning if the condition is met.
[0035] Thirdly, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described method steps.
[0036] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described method steps.
[0037] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
[0038] This invention provides a self-learning correction method for a finishing mill model, comprising: determining whether the actual rolling force of the finishing mill is effective; if not, acquiring the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value of the finishing mill; determining whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet preset conditions; if so, updating the self-learning of the finishing mill model, thereby effectively avoiding the situation where the loop tension in the rolling head range between the stands of the finishing mill is too large and the actual rolling force detected in the corresponding area is too small, resulting in the self-learning result of the finishing mill model being opposite to the expected direction, thereby improving rolling stability. Attached Figure Description
[0039] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:
[0040] Figure 1 This diagram illustrates the steps of the self-learning correction method for the finishing mill model in an embodiment of the present invention.
[0041] Figure 2 A schematic diagram of the structure of the finishing mill model self-learning correction device in an embodiment of the present invention is shown;
[0042] Figure 3A schematic diagram of the computer device for implementing the self-learning correction method for the finishing mill model in an embodiment of the present invention is shown. Detailed Implementation
[0043] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
[0044] Example 1
[0045] Embodiments of the present invention provide a self-learning correction method for a finishing mill model, such as... Figure 1 As shown, it includes:
[0046] S101, Determine whether the actual rolling force of the finishing mill is effective;
[0047] S102, if not, obtain the rolling force setting value, rolling force measurement value, and rolling force recalculation value of the finishing mill;
[0048] S103, determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet the preset conditions;
[0049] S104, if so, update the finishing mill model of the finishing mill through self-learning.
[0050] First, obtain the measured data of the head of the finishing mill. This measured data includes the actual maximum tension of the finishing mill and the reference tension of the stand. The reference tension of the stand is the product of a set tension and a coefficient, where the coefficient A is set to 1.5 to 2.0, for example, it can take values such as 2.0, 1.9, 1.8, 1.7, 1.6, 1.5, etc.
[0051] In a specific implementation, the frame tension evaluation table below is shown:
[0052]
[0053]
[0054] Next, execute S101 to determine whether the actual rolling force of the finishing mill is effective.
[0055] Specifically, it is determined whether the actual maximum tension is greater than the reference tension of the stand. As shown in the table above, since the actual maximum tension of F34 is greater than its reference tension, the actual rolling force of the F34 stand is determined to be invalid.
[0056] When it is determined that the actual rolling force of the finishing mill is invalid, execute S102 to obtain the rolling force setting value, rolling force measurement value, and rolling force recalculation value of the finishing mill.
[0057] The recalculated rolling force value is obtained by using measured data and recalculating the stand exit thickness, reduction rate, contact arc length, etc. based on the measured data, and then applying the rolling force formula.
[0058] Next, execute S103 to determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value satisfy the preset relationship.
[0059] Specifically, it is determined whether the rolling force setpoint (force_set), the rolling force measured value (force_act), and the rolling force recalculated value (force_acal) increase or decrease sequentially, specifically by satisfying the following formula:
[0060] force_set > force_act > force_acal or force_acal > force_act > force_set
[0061] As shown in the table below, with the above-mentioned F3 stand's rolling force setting value (17962) > actual rolling force value (17333) > recalculated rolling force value (16908), it is determined that the F3 stand self-learning needs to be corrected.
[0062]
[0063] After the rolling force set value (force_set), rolling force measured value (force_act), and rolling force recalculated value (force_acal) satisfy the above-mentioned preset relationship, S104 is executed to update the finishing mill model of the finishing mill through self-learning.
[0064] This update includes three aspects.
[0065] The first aspect of the update involves correcting the recalculated rolling force value; based on the corrected recalculated rolling force value, the finishing mill model is updated through self-learning.
[0066] The correction to the recalculated rolling force is specifically performed according to the following formula:
[0067] force_acal (corrected) = force_set * coefficient B + force_acal * (1.0 – coefficient B)
[0068] The coefficient B ranges from 0.0 to 1.0. For racks F1 to F7, the coefficient B is 0.7, 0.7, 0.7, 0.6, 0.6, and 0.6, respectively.
[0069] Specifically, taking the rolling force correction coefficient B = 0.7 for the F3 stand as an example, the corrected recalculated rolling force value = 1.7962 * 0.7 + 1.6908 * (1.0 - 0.7) = 17645.8. Based on this corrected recalculated rolling force value, the finishing mill model is updated through self-learning.
[0070] Secondly, after applying the corrected recalculated rolling force value to the self-learning of the rolling force in the finishing mill model, the actual value and the calculated value of the deformation resistance are obtained; it is determined whether the actual value of the deformation resistance is equal to the calculated value of the deformation resistance; if not, the deformation resistance self-learning update is not performed.
[0071] Of course, if the actual value of the deformation resistance is not equal to the calculated value, it can be corrected using the traditional correction method.
[0072] For example, as shown in the table below:
[0073]
[0074] According to the table, the actual value of the deformation resistance of the F3 frame is not equal to the calculated value of the deformation resistance. Therefore, it is determined that the deformation resistance self-learning of the F3 frame does not need to be updated.
[0075] Thirdly, after applying the corrected recalculated rolling force value to the self-learning of the rolling force in the finishing mill model, the thickness deviation at the finishing mill exit is obtained. For example, the head thickness deviation (actual thickness - target thickness) = 0.015mm. Since the thickness deviation is greater than 0, no roll gap self-learning update is performed.
[0076] Therefore, the results before and after the finishing mill model self-learning update are shown in the table below:
[0077]
[0078]
[0079] This shows that the changes before and after the self-learning update of each rack are consistent with the expectations.
[0080] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:
[0081] This invention provides a self-learning correction method for a finishing mill model, comprising: determining whether the actual rolling force of the finishing mill is effective; if not, acquiring the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value of the finishing mill; determining whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet preset conditions; if so, updating the self-learning of the finishing mill model, thereby effectively avoiding the situation where the loop tension in the rolling head range between the stands of the finishing mill is too large and the actual rolling force detected in the corresponding area is too small, resulting in the self-learning result of the finishing mill model being opposite to the expected direction, thereby improving rolling stability.
[0082] Example 2
[0083] Based on the same inventive concept, embodiments of the present invention also provide a self-learning correction device for a finishing mill model, such as... Figure 2 As shown, it includes:
[0084] The first judgment module 201 is used to determine whether the actual rolling force of the finishing mill is effective;
[0085] The acquisition module 202 is used to acquire, if not, the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value of the finishing mill unit;
[0086] The second judgment module 203 is used to determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet the preset conditions;
[0087] The update module 204 is used to update the finishing mill model of the finishing mill unit through self-learning if the condition is met.
[0088] In one optional implementation, the first determination module 201 is used to: obtain the actual maximum tension and the stand reference tension of the finishing mill;
[0089] Determine whether the actual maximum tension is greater than the frame reference tension.
[0090] In one optional implementation, the frame reference tension is specifically the product of a set tension and a preset coefficient.
[0091] In one optional implementation, the second judgment module 203 is used to: determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value increase or decrease sequentially.
[0092] In one alternative implementation, the update module 204 is used to:
[0093] The recalculated value of the rolling force is then corrected;
[0094] The finishing mill model is updated through self-learning based on the corrected recalculated rolling force value.
[0095] In one alternative implementation, the update module 204 is used to:
[0096] The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model;
[0097] Obtain the actual value and calculated value of deformation resistance;
[0098] Determine whether the actual value of the deformation resistance is equal to the calculated value of the deformation resistance;
[0099] If not, the deformation resistance self-learning update will not be performed.
[0100] In one alternative implementation, the update module 204 is used to:
[0101] The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model;
[0102] Obtain the thickness deviation at the finish rolling exit;
[0103] Determine whether the thickness deviation at the finishing mill exit is 0;
[0104] If not, then roll gap self-learning update will not be performed.
[0105] Example 3
[0106] Based on the same inventive concept, embodiments of the present invention provide a computer device, such as... Figure 3 As shown, it includes a memory 304, a processor 302, and a computer program stored in the memory 304 and executable on the processor 302. When the processor 302 executes the program, it implements the steps of the above-mentioned self-learning correction method for the finishing mill model.
[0107] Among them, Figure 3 In this document, a bus architecture (represented by bus 300) is used. Bus 300 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 306 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.
[0108] Example 4
[0109] Based on the same inventive concept, embodiments of the present invention provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described self-learning correction method for the finishing mill model.
[0110] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages is for the purpose of disclosing the best mode of implementation of the invention.
[0111] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0112] Similarly, it should be understood that, in order to simplify this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.
[0113] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.
[0114] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
[0115] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the finishing mill model self-learning correction device or computer device according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the present invention can be stored on a computer-readable medium or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.
[0116] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names.
Claims
1. A self-learning correction method for a finishing mill model, characterized in that, include: Determine whether the actual rolling force of the finishing mill is effective; If not, obtain the rolling force setting value, rolling force measurement value, and rolling force recalculation value of the finishing mill unit; Determine whether the rolling force set value, the rolling force measured value, and the rolling force recalculated value satisfy a preset relationship; If so, the finishing mill model of the finishing mill unit is updated through self-learning; The determination of whether the actual rolling force of the finishing mill is effective includes: obtaining the actual maximum tension of the finishing mill and the reference tension of the stand; Determine whether the actual maximum tension is greater than the frame reference tension, which is specifically the product of the set tension and the preset coefficient.
2. The method as described in claim 1, characterized in that, The step of determining whether the set rolling force value, the measured rolling force value, and the recalculated rolling force value satisfy a preset relationship includes: Determine whether the rolling force set value, the rolling force measured value, and the rolling force recalculated value increase or decrease sequentially.
3. The method as described in claim 1, characterized in that, The self-learning update of the finishing mill model of the finishing mill unit includes: The recalculated value of the rolling force is then corrected; The finishing mill model is updated through self-learning based on the corrected recalculated rolling force value.
4. The method as described in claim 3, characterized in that, Based on the revised recalculated rolling force, the finishing mill model is updated through self-learning, including: The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model; Obtain the actual value and calculated value of deformation resistance; Determine whether the actual value of the deformation resistance is equal to the calculated value of the deformation resistance; If not, the deformation resistance self-learning update will not be performed.
5. The method as described in claim 3, characterized in that, Based on the revised recalculated rolling force, the finishing mill model is updated through self-learning, including: The corrected recalculated rolling force value is applied to the self-learning of rolling force in the finishing mill model; Obtain the thickness deviation at the finish rolling exit; Determine whether the thickness deviation at the finishing mill exit is 0; If not, then roll gap self-learning update will not be performed.
6. A self-learning correction device for a finishing mill model, characterized in that, The apparatus for performing the method as described in any one of claims 1-5 includes: The first judgment module is used to determine whether the actual rolling force of the finishing mill is effective; The acquisition module is used to acquire, if not, the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value of the finishing mill unit; The second judgment module is used to determine whether the rolling force setting value, the rolling force measurement value, and the rolling force recalculation value meet preset conditions; The update module is used to update the finishing mill model of the finishing mill unit through self-learning if the condition is met.
7. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-5.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.