A method and system for segmented acquisition of measured values ​​at a measurement station based on a self-learning model.

Abstract

This invention discloses a method and system for segmented acquisition of measured values ​​at a measuring station based on a self-learning model. The method includes acquiring preset strip data at the entry and exit points of the finishing mill; segmenting the strip at the finishing mill exit according to the preset strip data; acquiring measured values ​​for each segment using a measuring device; and inputting the measured values ​​into a preset self-learning model for learning to obtain the resulting data. This solves the problems in existing technologies where different thickness specifications cannot meet the requirements of different sampling segments, and where poor uniformity affects the acquisition of measured values. It improves the accuracy of the finishing mill model and avoids the influence of intermediate billet temperature non-uniformity on the sampling point temperature.

Description

Technical Field

[0001] This invention relates to the technical field of finishing rolling inspection, and in particular to a method and system for segmented acquisition of measured values ​​at a measuring station based on a self-learning model. Background Technology

[0002] With increasing demands for dimensional accuracy in strip steel products, stringent requirements have been placed on the center point thickness control accuracy, generally requiring ±0.1mm. The thickness tolerance for key pickling processes is ±0.08mm, and for more stringent requirements, it may even need to reach ±0.06mm. However, the problem with existing technologies is that the center thickness accuracy is not high, especially the head thickness accuracy, and the production line has a high rate of cutting damage and rework.

[0003] The finishing rolling force model is the most crucial calculation model in the hot strip rolling control model, and its prediction accuracy directly affects the accuracy of finished strip thickness control. In existing technologies, to improve the model's control accuracy, after each steel strip is rolled, the finishing rolling self-learning model (refer to the paper titled "Self-learning Function and Application of the Finishing Rolling Model of Shougang Jingtang 1580 Hot Strip Rolling Mill; Authors: He Lingyun, Gong Caijun; Journal: Metallurgical Automation; Vol. 37, No. 6) collects the measured values ​​of the current pass, such as intermediate billet temperature, rolling force, rolling torque, rolling speed, process water volume and temperature, finishing mill exit temperature and thickness, etc., and continuously corrects the calculation accuracy of the finishing rolling model through self-learning calculations. Currently, the measured values ​​are generally collected by specifying a certain range at the finishing mill exit (e.g., 5 to 10 meters). This method of collecting measured values ​​at a fixed finishing mill exit length cannot meet the requirements of different thickness specifications for different sampling sections and is not conducive to improving the accuracy of the finishing rolling model. Furthermore, since the temperature uniformity of the intermediate billet is relatively high, if the temperature uniformity of the head is poor, it is not conducive to the acquisition of measured values, leading to a decrease in the accuracy of model control. Therefore, a method and system for segmented acquisition of measured values ​​by measurement stations based on a self-learning model is needed. Summary of the Invention

[0004] This application provides a method and system for segmented acquisition of measured values ​​at a measurement station based on a self-learning model. This at least partially solves the technical problems in the prior art, such as the inability to meet the requirements of different thickness specifications for different sampling segments, poor uniformity, and the impact on the acquisition of measured values. It achieves the technical effect of improving the accuracy of the finishing mill model and avoiding the influence of the temperature non-uniformity of the intermediate billet on the temperature of the sampling point.

[0005] Firstly, to solve the above-mentioned technical problems, embodiments of the present invention provide the following technical solutions:

[0006] A method for segmented acquisition of measured values ​​at a measurement station based on a self-learning model, the method comprising:

[0007] Obtain the preset strip data for the entry and exit points of the finishing mill;

[0008] Based on the above-mentioned preset strip data, the strip at the finishing mill exit is segmented, and the measured value of each segment is obtained using measuring equipment.

[0009] The measured values ​​are input into a preset self-learning model to obtain the result data.

[0010] Optionally, the step of segmenting the strip at the finishing mill exit according to the preset strip data further includes:

[0011] Based on the pre-set strip steel exit speed and pre-set effective acquisition time in the above-mentioned preset strip steel data, the acquisition length of each segment is calculated.

[0012] Optionally, the step of obtaining measured values ​​for each of the above segments using measuring equipment further includes:

[0013] Based on the entry and exit thickness of the finishing mill and the aforementioned acquisition length, the actual length of the strip passing through the measuring equipment is calculated based on a preset algebraic relationship, and the actual measurement data in the measuring equipment corresponding to the aforementioned actual length is obtained.

[0014] Optionally, the step of inputting the measured values ​​into a preset self-learning model to obtain the result data further includes:

[0015] Data acquired from multiple racks containing measuring equipment is input into the aforementioned self-learning model to obtain the resulting data.

[0016] Optionally, after inputting the measured values ​​into a preset self-learning model to obtain the result data, the method further includes:

[0017] Based on the data collected from each segment, a first requirement threshold is set, and segments that meet the first threshold are saved as references for storing the temperature self-learning coefficient.

[0018] Optionally, after inputting the measured values ​​into a preset self-learning model to obtain the result data, the method further includes:

[0019] Based on the data collected from each segment, a second requirement threshold is set, and segments that meet the second threshold are saved as a reference for storing the self-learning coefficient of the stand rolling force.

[0020] Optionally, the step of segmenting the strip at the finishing mill exit according to the preset strip data further includes:

[0021] The data obtained from the first detection of the above segments are discarded.

[0022] Secondly, a system for segmented acquisition of measured values ​​at measurement stations based on a self-learning model is provided. This system includes:

[0023] The data acquisition module is used to acquire preset strip data at the entry and exit points of the finishing mill;

[0024] The segment calculation module is used to segment the strip at the finishing mill exit according to the above-mentioned preset strip data, and to obtain the measured value for each segment using a measuring device.

[0025] The self-learning module is used to input the above measured values ​​into a preset self-learning model to learn and obtain the result data.

[0026] Thirdly, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the steps corresponding to the method described in the first aspect.

[0027] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the steps corresponding to the method described in the first aspect.

[0028] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0029] This invention, through segmented acquisition of measured data, allows direct data acquisition of a specific segment of the strip steel. This enables the setting of threshold values ​​for different sampling segments with varying thicknesses, based on specific needs. Simultaneously, it triggers a self-learning model, inputting these data into the model to improve its accuracy. Furthermore, the segmented detection method allows for the selection of a suitable segment as reference data, ensuring precise thickness control. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating a method for segmented acquisition of measured values ​​at a measurement station based on a self-learning model, provided in this application;

[0032] Figure 2 A schematic diagram of the structure of a measurement station segmented data acquisition system based on a self-learning model provided in this application;

[0033] Figure 3 This is a schematic diagram of the structure of an electronic device provided in this application. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0035] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0036] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0037] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the term "setup" should be interpreted broadly. For example, it can refer to a fixed setup, a detachable setup, or an integral setup; it can refer to a direct setup or an indirect setup via an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0038] It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of this application, rather than limitations on the technical solutions of this application. Unless otherwise specified, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0039] This application provides a method and system for segmented acquisition of measured values ​​at measurement stations based on a self-learning model. This improves upon the technical problems in the prior art, which cannot meet the requirements of different thickness specifications for different sampling segments and suffer from poor uniformity affecting the acquisition of measured values. It achieves the technical effect of improving the accuracy of the finishing mill model and avoiding the influence of intermediate billet temperature non-uniformity on the sampling point temperature.

[0040] The technical solution of this application embodiment is to solve the above-mentioned technical problems, and the general idea is as follows:

[0041] This invention, through segmented acquisition of measured data, allows direct data acquisition of a specific segment of the strip steel. This enables the setting of threshold values ​​for different sampling segments with varying thicknesses, based on specific needs. Simultaneously, it triggers a self-learning model, inputting these data into the model to improve its accuracy. Furthermore, the segmented detection method allows for the selection of a suitable segment as reference data, ensuring precise thickness control.

[0042] In the embodiments of this application, the following are provided: Figure 1 The method shown is a segmented acquisition method for measured values ​​at a measurement station based on a self-learning model. The method includes steps S101 to S103:

[0043] Step S101: Obtain the preset strip data for the entry and exit of the finishing mill;

[0044] The preset strip data includes the exit length of the finished strip, the entry thickness of the finished strip, the exit thickness of the finished strip, and the exit speed of the finished strip.

[0045] Step S102: The strip at the finishing mill exit is segmented according to the preset strip data, and the measured value is obtained for each segment using a measuring device.

[0046] The purpose of segmenting the strip steel is to meet the different requirements of different sampling segments based on varying thickness specifications. This allows for the accurate acquisition of data for specific segments, thereby improving the accuracy of data sampling. The measuring equipment used is an MPi measuring station; for example, field pyrometers, pressure gauges, and tracking devices can all be considered measuring stations.

[0047] Step S103: Input the above measured values ​​into the preset self-learning model to learn and obtain the result data.

[0048] The preset self-learning model is an existing model (for details, please refer to the paper titled "Self-learning Function and Application of Shougang Jingtang 1580 Hot Strip Mill Finishing Model"; authors: He Lingyun, Gong Caijun; journal: Metallurgical Automation; Vol. 37, No. 6). More accurate measured values ​​are input into the self-learning model for calculation, thereby improving the model's accuracy. The specific segmented implementation method is as follows:

[0049] Furthermore, the step of segmenting the strip at the finishing mill exit according to the aforementioned preset strip data also includes: segmenting the strip at the finishing mill exit speed V and the preset effective acquisition time dummytime from the aforementioned preset strip data. i Calculate the acquisition length L of each segment. i The calculation formula is as follows:

[0050] L i =V×dummytimei

[0051] Since the exit speed of the finishing mill is constant, different effective acquisition times can be set for each segment. This allows the acquisition length of each segment to be obtained. Simultaneously, for positioning purposes, the total number of measurement station triggers and the corresponding trigger stations for each segment are set. The aim is to use the sensors to obtain trigger signals and then perform positioning based on the set effective acquisition time, thereby accurately determining the position of the acquisition segment.

[0052] Furthermore, the step of obtaining measured values ​​for each of the aforementioned segments using measuring equipment further includes: calculating the measured length of the strip passing through the measuring equipment based on a preset algebraic relationship, according to the finishing mill inlet thickness, outlet thickness, and the aforementioned acquisition length, and obtaining the measured data in the measuring equipment corresponding to the measured length. The specific calculation process is as follows:

[0053] First, based on the elongation coefficient σ of the finishing mill inlet thickness δ1 and outlet thickness δ2:

[0054]

[0055] Then, based on the length L of the collected data... i The measured length L of the measuring equipment is calculated using the elongation coefficient σ. MPie (i.e., the length measured by the measuring device):

[0056]

[0057] Therefore, combining formulas (1) and (2), we can know that the presupposed algebraic relation is:

[0058]

[0059] Furthermore, in the step of inputting the measured values ​​into the preset self-learning model to learn and obtain the result data, the method further includes: inputting the data obtained from multiple racks containing measuring equipment into the self-learning model to learn and obtain the result data.

[0060] It should be noted that setting up multiple racks containing measuring equipment aims to prevent errors in the data acquired by the self-learning model from occurring if the accuracy of a single rack becomes inaccurate due to prolonged use or accidents. Therefore, the purpose of multiple racks is that the measuring station on each rack inspects the strip steel, the self-learning model calculates the data from each rack, and then uses cross-comparison or deep learning methods to eliminate erroneous data. This effectively increases the model's prediction accuracy, ensures the precision of exit thickness control, and completes the correction process.

[0061] Based on the above implementation method, the actual processing data is as follows:

[0062] The data for the exit length L of the finished strip, the entry thickness δ1 and exit thickness δ2 of the finished strip, and the exit speed V of the finished strip are shown in Table 1 below:

[0063] Exit length L (m) of finished strip steel 672.941 <![CDATA[Thickness δ1 at the entrance of the finishing mill (mm)]]> 30.0 <![CDATA[Final rolling exit thickness δ2 (mm)]]> 3.0 Finishing mill exit speed V (m / s) 9.33

[0064] The extension coefficient σ is calculated to be 10.048 according to the above formula (3), and the segment lengths are shown in Table 2 below:

[0065] Section Name Length (m) lSegmentIn0 3.84 lSegmentIn1 9.61 lSegmentIn2 9.61 lSegmentIn3 38.4 lSegmentIn4 19.2

[0066] The number of trigger stations and the specific trigger stations for different segments are set as shown in Table 3 below:

[0067]

[0068]

[0069] The measured values ​​for each segment are collected, taking the final rolling temperature and F1 rolling force as examples, as shown in Table 4 below;

[0070] Segmentation Final rolling temperature F1 rolling force FDTSegmentIn0 882.2 14.62 FDTSegmentIn1 913.9 17.9 FDTSegmentIn2 905.9 18.7 FDTSegmentIn3 895.8 19.8 FDTSegmentIn4 891.4 20.1

[0071] After being input into the learning model for calculation, the temperature coefficient cofaTM and rolling force coefficient cofaFr are shown in Table 5 below:

[0072]

[0073] It should be noted that in the segmented representation, the last digit of the expression indicates a one-to-one correspondence between the same segment, for example: lSegmentIn0, FDTSegmentIn0, and cofaFrsegment0.

[0074] Furthermore, after inputting the measured values ​​into the preset self-learning model to obtain the result data, the method further includes: setting a first requirement threshold based on the data collected in each segment, and saving the segments that meet the first threshold as a reference for saving the temperature self-learning coefficient.

[0075] Furthermore, after inputting the measured values ​​into a preset self-learning model to obtain the result data, the process also includes:

[0076] Based on the data collected from each segment, a second requirement threshold is set, and segments that meet the second threshold are saved as a reference for storing the self-learning coefficient of the stand rolling force.

[0077] It should be noted that, based on the segmented measured data acquisition and model self-learning process, a segment can be set to store the temperature self-learning coefficient cofaTM, and another segment can be set to store the rolling force self-learning coefficient cofaFr for each stand. This setting is primarily customized according to user needs, allowing operators to decide which segment's temperature coefficient cofaTM and rolling force coefficient cofaFr to use, thus improving convenience.

[0078] Furthermore, the step of segmenting the strip at the finishing mill exit according to the aforementioned preset strip data also includes:

[0079] The data obtained from the first detection of the above segments are discarded.

[0080] It should be noted that due to the instability of the head during thin-gauge rolling, the AGC adjustment may experience significant correction issues, leading to excessive self-learning correction of the roll gap in the model and reducing the accuracy of the roll gap setting in the finishing mill model. Therefore, when setting up data acquisition, the data from the first detected segment can be directly discarded to avoid inaccurate data detection caused by uneven and large fluctuations in head temperature, thereby further improving the accuracy of the model.

[0081] Based on the same inventive concept, embodiments of this application provide a system for segmented acquisition of measured values ​​at a measurement station based on a self-learning model, such as... Figure 2 As shown, it includes:

[0082] The data acquisition module is used to acquire preset strip data at the entry and exit points of the finishing mill;

[0083] The segment calculation module is used to segment the strip at the finishing mill exit according to the above-mentioned preset strip data, and to obtain the measured value for each segment using a measuring device.

[0084] The self-learning module is used to input the above measured values ​​into a preset self-learning model to learn and obtain the result data.

[0085] Based on the same inventive concept, such as Figure 3 As shown, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements a method for segmented acquisition of measured values ​​at a measurement station based on a self-learning model.

[0086] Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing a computer program, characterized in that, when the program is executed by a processor, it implements a method for segmented acquisition of measured values ​​at a measurement station based on a self-learning model.

[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0090] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0091] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for segmented acquisition of measured values ​​at a measurement station based on a self-learning model, characterized in that, The method includes: Obtain the preset strip data for the entry and exit points of the finishing mill; The strip at the finishing mill exit is segmented according to the preset strip data; Based on the finishing mill exit speed and preset effective acquisition time in the preset strip steel data, the acquisition length of each segment is calculated; different effective acquisition times can be set for each segment; Set the total number of measurement station triggers and the corresponding trigger stations for each segment; The elongation coefficient is calculated based on the entry and exit thicknesses of the finishing mill. Based on the extension coefficient and the acquisition length of each segment, the measured length of each segment through the measuring device is calculated; Obtain the measured data from the measuring device corresponding to the measured length to obtain the measured value of each segment; Data acquired from multiple racks containing measuring equipment is input into the self-learning model for learning to obtain result data; Based on the data collected from each segment, a second requirement threshold is set, and segments that meet the second threshold are saved as a reference for storing the self-learning coefficient of the stand rolling force.

2. The method as described in claim 1, characterized in that, After inputting the measured values ​​into a preset self-learning model to obtain the result data, the method further includes: Based on the data collected from each segment, a first requirement threshold is set, and segments that meet the first threshold are saved as references for storing the temperature self-learning coefficient.

3. The method as described in claim 1, characterized in that, The step of segmenting the strip at the finishing mill exit according to the preset strip data further includes: The data obtained from the first detected segment is discarded.

4. A system for segmented acquisition of measured values ​​at a measurement station based on a self-learning model, characterized in that, The system includes: The data acquisition module is used to acquire preset strip data at the entry and exit points of the finishing mill; The segmented calculation module is used to segment the strip steel at the finishing mill exit according to the preset strip steel data; calculate the acquisition length of each segment based on the finishing mill exit speed and preset effective acquisition time in the preset strip steel data; set different effective acquisition times for each segment; set the total number of measurement station triggers and corresponding trigger stations for each segment; calculate the elongation coefficient based on the finishing mill inlet thickness and outlet thickness; calculate the measured length of each segment through the measuring equipment based on the elongation coefficient and the acquisition length of each segment; obtain the measured data in the measuring equipment corresponding to the measured length to obtain the measured value of each segment; the measured value of each segment includes data acquired from multiple stands containing the measuring equipment. The self-learning module is used to input data acquired from multiple racks containing measuring equipment into the self-learning model to learn and obtain result data; Based on the data collected from each segment, a second requirement threshold is set, and segments that meet the second threshold are saved as a reference for storing the self-learning coefficient of the stand rolling force.

5. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 3.

6. 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 steps corresponding to the method as described in any one of claims 1 to 3.

Images