Sample library updating method and device for self-learning coefficient calculation model

Abstract

Embodiments of the present application provide a sample library updating method and device of a self-learning coefficient calculation model, and relate to the technical field of rolling force calculation model control. The method comprises: determining a minimum effective capacity; creating a plurality of sample libraries; judging whether the sample libraries meet the requirements based on the minimum effective capacity; calling the sample libraries that meet the requirements, and simultaneously updating other sample libraries. The present application periodically updates the sample data of the sample libraries, guarantees the "freshness" of the sample number, improves the application accuracy of the self-learning coefficient when applied to variable-gauge production, avoids the influence of the original accumulated self-learning coefficient on the current production due to changes in equipment parameters, and further makes the steel rolling production more stable and smooth.

Description

Technical Field

[0001] This application relates to the field of rolling force calculation model control technology, and more specifically, to a sample library update method for a self-learning coefficient calculation model, a sample library update device for a self-learning coefficient calculation model, a computer-readable storage medium, and an electronic device. Background Technology

[0002] In the process of strip steel production, the traditional calculation model will calculate a self-learning coefficient based on the actual rolling force and the rolling force calculated by the model. When the strip steel is produced in different specifications, the model will refer to the self-learning coefficient accumulated in the previous production of this type of steel coil and participate in the calculation of the preset rolling force of the next steel coil. The closer this preset rolling force is to the actual rolling force of this steel coil, the smoother the start-up will be.

[0003] However, with the continuous production of steel coils, some original technical parameters of the rolling mill equipment need to be modified. These changes affect the magnitude of the self-learning coefficients mentioned above. Traditional calculation models cannot recognize this change and will accumulate all self-learning coefficients before and after the parameter modification. Because they cannot react promptly, the self-learning coefficients calculated in the model cannot be corrected in time after the parameter modification. This results in the calculated preset rolling force being either too high or too low, leading to difficulties in starting the rolling mill and affecting the production schedule.

[0004] Therefore, there is an urgent need for an update method that modifies the sample library of the self-learning coefficient calculation model while the parameters are being modified, thereby correcting the calculation of the self-learning coefficient. Summary of the Invention

[0005] The embodiments of this application provide a method for updating the sample library of a self-learning coefficient calculation model, a device for updating the sample library of a self-learning coefficient calculation model, a computer-readable storage medium, and an electronic device. The present invention continuously updates the sample library of the self-learning coefficient calculation model during the continuous production adjustment of steel coils, thereby quickly correcting the accumulated self-learning coefficients and making the rolling production smoother.

[0006] Other features and advantages of this application will become apparent from the following detailed description, or may be learned in part from practice of this application.

[0007] According to a first aspect of the embodiments of this application, a method for updating a sample library of a self-learning coefficient calculation model is provided, including:

[0008] Determine the minimum effective capacity;

[0009] Create multiple sample libraries;

[0010] Determine whether the sample library meets the requirements based on the minimum effective capacity;

[0011] Call the sample library that meets the requirements, and update other sample libraries at the same time.

[0012] In some embodiments of this application, based on the foregoing scheme, the minimum effective capacity is half the capacity of the sample library with the smallest capacity among multiple sample libraries.

[0013] In some embodiments of this application, based on the foregoing scheme, the step of determining whether the sample library meets the requirements based on the minimum effective capacity includes:

[0014] According to the size of the sample database, each sample database is compared with the minimum effective capacity.

[0015] When the number of samples in the comparison database is not less than the minimum effective capacity and the number of samples in other databases exceeds the set value, the comparison database is deemed to meet the requirements.

[0016] In some embodiments of this application, based on the foregoing scheme, updating other sample libraries includes: clearing other sample libraries and re-accumulating data.

[0017] In some embodiments of this application, based on the aforementioned scheme, the process of re-accumulating data further includes: verifying the data.

[0018] In some embodiments of this application, based on the foregoing scheme, the data verification includes:

[0019] Retrieve the raw data for comparison from the sample library;

[0020] The original data is compared and verified with the new data to be added to the sample library;

[0021] After the verification meets the requirements, the new data is added to the sample database.

[0022] In some embodiments of this application, based on the foregoing scheme, the comparison and verification of the original data with the new data to be added to the sample library includes:

[0023] The credibility of the new data is obtained through formula (1), and the self-learning coefficient of the new data is obtained through formula (2);

[0024] ; (1)

[0025] ; (2)

[0026] in, To ensure the credibility of the original data, To ensure the credibility of the new data, The self-learning coefficients for the new data. The self-learning coefficients of the original data. This represents the number of strip coils in the current batch. This refers to adaptive correlation data obtained from actual production data during the rolling process;

[0027] when When the new data is deemed to meet the verification requirements, then... It is a constant value.

[0028] According to a second aspect of the embodiments of this application, a sample library update apparatus for a self-learning coefficient calculation model is provided, comprising:

[0029] Create a unit to create multiple sample libraries;

[0030] The judgment unit is used to determine whether the sample library meets the requirements based on the minimum effective capacity.

[0031] The calling unit is used to call a sample library that meets the requirements;

[0032] The update unit is used to update the sample library.

[0033] According to a third aspect of the embodiments of this application, a computer-readable storage medium is provided, characterized in that the computer-readable storage medium stores computer instructions, which, when executed on a computer, cause the computer to perform the method described in the first aspect.

[0034] According to a fourth aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor;

[0035] The memory is used to store instructions;

[0036] The processor is configured to invoke instructions in the memory to cause the electronic device to execute the method described in the first aspect.

[0037] The technical solution of this application periodically updates the sample data in the sample library, ensuring the "freshness" of the sample number. When applied to variable specification production, it improves the accuracy of the self-learning coefficient. It avoids the impact of the original accumulated self-learning coefficient on the current production situation due to changes in equipment parameters, making steel rolling production more stable and smooth.

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0040] Figure 1 A schematic flowchart of a sample library update method for a self-learning coefficient calculation model according to an embodiment of this application is shown.

[0041] Figure 2 A schematic diagram of the sample library update method of a conventional self-learning coefficient calculation model provided in an embodiment of this application is shown.

[0042] Figure 3 A schematic diagram of a sample library update method for an innovative self-learning coefficient calculation model provided in an embodiment of this application is shown.

[0043] Figure 4 A schematic diagram of an example flow of a sample library update method for an innovative self-learning coefficient calculation model provided in one embodiment of this application is shown.

[0044] Figure 5 A schematic diagram showing a comparison of the improvement effects of conventional and innovative methods on a preset rolling force according to an embodiment of this application is provided. Detailed Implementation

[0045] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0046] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0047] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0048] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0049] It should be noted that "multiple" as mentioned in this article refers to two or more.

[0050] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0051] The following detailed description of some embodiments of this application will be provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0052] See Figure 1 The diagram illustrates a flowchart of a sample library update method for a self-learning coefficient calculation model according to an embodiment of this application.

[0053] like Figure 1 As shown, a sample library update method for a self-learning coefficient calculation model is demonstrated, specifically including steps S100 to S400.

[0054] Step S100: Determine the minimum effective capacity.

[0055] Continue to refer to Figure 1 Step S200: Create multiple sample libraries.

[0056] It is understandable that the sample sizes of the multiple sample libraries created are different, and the sample sizes of these sample libraries are all larger than the minimum effective capacity.

[0057] In some feasible embodiments, the minimum effective capacity is half the capacity of the smallest sample library among a plurality of sample libraries.

[0058] For example, if three sample libraries are created in total, with the first sample library N1 having a capacity of 20 (meaning it can store 20 data items), the second sample library N2 having a capacity of 25, and the third sample library N3 having a capacity of 30, then the minimum effective capacity should be half the capacity of sample library N1, which is 10.

[0059] Continue to refer to Figure 1 Step S300: Determine whether the sample library meets the requirements based on the minimum effective capacity.

[0060] In some feasible embodiments, step S300 specifically includes steps S310 to S320.

[0061] Step S310: According to the size of the sample library, compare each sample library with the minimum effective capacity.

[0062] It is understandable that in this embodiment, the smaller sample library needs to be processed first, and then the larger sample library needs to be processed. This can improve the fault tolerance rate and avoid the situation where the smaller sample library does not meet the requirements after the larger sample library is cleared.

[0063] It is understood that the processing includes operations such as comparing the sample library with the minimum effective capacity, clearing the sample library, and re-accumulating data in the sample library.

[0064] Step S320: When the number of samples in the comparison sample library is not less than the minimum effective capacity and the number of samples in other sample libraries exceeds the set value, it is determined that the comparison sample library meets the requirements.

[0065] It should be noted that in this embodiment, the set value refers to the sample library capacity threshold. When the number of samples stored in a sample library is not less than the minimum effective capacity, and the number of samples in other sample libraries exceeds their own capacity threshold, it means that this sample library meets the requirements.

[0066] For example, based on the foregoing example, when the number of samples in sample library N1 is not less than 10, the number of samples in sample library N2 exceeds 25, and the number of samples in sample library N3 exceeds 30, it indicates that sample library N1 meets the requirements; or when the number of samples in sample library N2 is not less than 10, the number of samples in sample library N1 exceeds 20, and the number of samples in sample library N3 exceeds 30, it indicates that sample library N2 meets the requirements; or when the number of samples in sample library N3 is not less than 10, the number of samples in sample library N1 exceeds 20, and the number of samples in sample library N2 exceeds 25, it indicates that sample library N3 meets the requirements.

[0067] Continue to refer to Figure 1In step S400, the sample library that meets the requirements is called, and other sample libraries are updated at the same time.

[0068] It is understandable that updating other sample libraries is for the purpose of calling these sample libraries later, thus forming a loop to ensure that the sample libraries are continuously updated as the data is updated.

[0069] In some feasible embodiments, updating other sample libraries includes: clearing other sample libraries and re-accumulating data.

[0070] Understandably, sample libraries that do not meet the requirements will no longer be used, and the sample data stored in these sample libraries is no longer useful. Therefore, it is necessary to clear this data to avoid confusion with the data that is subsequently re-accumulated.

[0071] Specifically, in this embodiment, the process of re-accumulating data also includes: verifying the data.

[0072] Understandably, all data re-accumulated in the sample library needs to be validated to ensure data reliability.

[0073] In some feasible embodiments, the data verification includes:

[0074] Retrieve the raw data for comparison from the sample library;

[0075] The original data is compared and verified with the new data to be added to the sample library;

[0076] After the verification meets the requirements, the new data is added to the sample database.

[0077] Understandably, the original data is reliable because it meets the requirements of the sample database. By comparing the new data with the original data, it can be determined whether the new data meets the requirements of the sample database.

[0078] In some feasible embodiments, the comparison and verification of the original data with the new data to be added to the sample library includes:

[0079] The credibility of the new data is obtained through formula (1), and the self-learning coefficient of the new data is obtained through formula (2);

[0080] ; (1)

[0081] ; (2)

[0082] in, To ensure the credibility of the original data, To ensure the credibility of the new data, The self-learning coefficients for the new data. The self-learning coefficients of the original data. This represents the number of strip coils in the current batch. This refers to adaptive correlation data obtained from actual production data during the rolling process;

[0083] when When the new data is deemed to meet the verification requirements, then... It is a constant value.

[0084] It should be noted that the adaptive relevant data obtained from actual production data during the rolling process includes data related to strip rolling, such as rolling force, rolling torque, forward slip, roll gap, and actual thickness.

[0085] In another aspect, this application also provides a sample library update device for a self-learning coefficient calculation model, comprising:

[0086] Create a unit to create multiple sample libraries;

[0087] The judgment unit is used to determine whether the sample library meets the requirements based on the minimum effective capacity.

[0088] The calling unit is used to call a sample library that meets the requirements;

[0089] The update unit is used to update the sample library.

[0090] In another aspect, this application also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions, which, when executed on a computer, cause the computer to perform a sample library update method for a self-learning coefficient calculation model as described in the above embodiments.

[0091] In another aspect, this application also provides an electronic device, including a memory and a processor;

[0092] The memory is used to store instructions;

[0093] The processor is used to call instructions in the memory to cause the electronic device to execute the sample library update method of the self-learning coefficient calculation model described in the above embodiments.

[0094] The following is a specific implementation example.

[0095] This example uses two years of production data from a 20-roll feeder to illustrate the calculation method and comparison results.

[0096] Traditional computational models are designed such that shorter sample databases store a maximum of 21 data points. When this capacity limit is reached, the program clears the accumulated data and starts accumulating again. Longer sample databases, however, continuously accumulate production data. Figure 2 However, the production parameters for the same steel coil are not static. If these parameters are modified, the previously accumulated self-learning coefficients become less meaningful. This leads to the inability of traditional calculation models to meet the needs of long-term production, resulting in loopholes. First, as the production of steel coils accumulates, the difference between the means of the two sample databases widens. Second, the relatively shorter sample database contains data that closely approximates actual production data, but the traditional calculation model can no longer access this data due to long-term production, causing the preset rolling force to be either too high or too low.

[0097] To solve these two problems, a database needs to be constantly accessible and callable, but it becomes unusable when its data is cleared. Using a single data repository is insufficient; therefore, a second database needs to be created. When the first database is deleted, the second database can accumulate enough samples for the system to use. When the first database has accumulated a certain number of samples, it is used. When the first database is used, the second database is cleared, and data accumulation begins again. This cycle repeats to ensure the validity and freshness of the sample data. The process is as follows: Figure 3 As shown.

[0098] Below, taking a 20-roll mill as an example, and using the program flow as an example, the following solutions are proposed after a series of optimizations, such as... Figure 4 As shown.

[0099] Step 1: Determine the minimum effective capacity as 10; (that is, the sample database can be used once it has accumulated ten data points, at which point another sample database can also be cleared)

[0100] Step 2: Set the capacity of the first sample library to 20 and the capacity of the second sample library to 40; (20 and 40 are the ideal empty capacity, the actual capacity may exceed this value)

[0101] Step 3: When the capacity of the first sample library is no less than 20 and the capacity of the second sample library is no less than 10, clear the data in the first sample library and re-accumulate the data in the first sample library; (at this point, start calling the second sample library).

[0102] Step 4: When the first sample database has a capacity of at least 10 and the second sample database has a capacity of at least 40, clear the data in the second sample database and re-accumulate the data in the second sample database. (At this point, the first sample database is started.)

[0103] Finally, based on the actual comparison results, such as Figure 5 As shown, it is easy to see that with the continuous accumulation of samples, the innovative computational model is significantly better than the traditional computational model.

[0104] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0105] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0106] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0107] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0108] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0109] Other embodiments of this application will readily conceive of by those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for updating a sample database for a self-learning coefficient calculation model, characterized in that, include: Determine the minimum effective size of the sample library; Create multiple sample libraries; each sample library is set with corresponding settings, which are the sample library capacity thresholds. According to the size of the sample database, each sample database is compared with the minimum effective capacity. When the number of samples in the comparison sample library is not less than the minimum effective capacity and the number of samples in other sample libraries exceeds the set value, the comparison sample library is deemed to meet the requirements. Call the sample library that meets the requirements, while clearing other sample libraries and re-accumulating data; During the process of re-accumulating data, the original data for comparison is retrieved from the sample library; the original data is compared and verified with the new data to be added to the sample library; after the verification meets the requirements, the new data is added to the sample library. The process of comparing multiple sample databases one by one with the minimum effective capacity, clearing other sample databases and re-accumulating data is repeated cyclically.

2. The method according to claim 1, characterized in that, The minimum effective capacity is half the capacity of the smallest sample library among multiple sample libraries.

3. The method according to claim 1, characterized in that, The comparison and verification of the original data with the new data to be added to the sample library includes: The credibility of the new data is obtained through formula (1), and the self-learning coefficient of the new data is obtained through formula (2); ； （1） ； （2） in, To ensure the credibility of the original data, To ensure the credibility of the new data, The self-learning coefficients for the new data. The self-learning coefficients of the original data. This represents the number of strip coils in the current batch. This refers to adaptive correlation data obtained from actual production data during the rolling process; when When the new data is deemed to meet the verification requirements, then... It is a constant value.

4. A sample library update device for a self-learning coefficient calculation model, characterized in that, The sample library updating device is used to implement the sample library updating method as described in claim 1, and the sample library updating device includes: A creation unit is used to create multiple sample libraries; each sample library is set with corresponding settings, which are the sample library capacity thresholds. The judgment unit is used to compare multiple sample libraries one by one with the minimum effective capacity in order of their capacity. When the number of samples in the sample library being compared is not less than the minimum effective capacity and the number of samples in other sample libraries exceeds a set value, the sample library being compared is determined to meet the requirements. The calling unit is used to call a sample library that meets the requirements; The update unit is used to clear other sample libraries and re-accumulate data; during the re-accumulation of data, the original data for comparison is retrieved from the sample library; the original data is compared and verified with the new data to be added to the sample library; after the verification meets the requirements, the new data is put into the sample library.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the computer to perform the method of any one of claims 1-3.

6. An electronic device, characterized in that, Including memory and processor; The memory is used to store instructions; The processor is configured to invoke instructions in the memory to cause the electronic device to perform the method of any one of claims 1-3.

Images