Zinc layer thickness control method and system for continuous hot galvanizing based on self-learning

Abstract

The invention provides a zinc layer thickness control method and system for continuous hot galvanizing based on self-learning, and relates to the technical field of hot galvanizing strip steel production. Calculating a layer number according to the production parameters; reading result data of short-term self-learning, long-term self-learning and inherited self-learning corresponding to the layer number of the current strip steel; when the spacing distance between the head of to-be-galvanized strip steel adjacent to the current strip steel and the air knife is a first preset distance and the layer numbers are different, performing calculation of long-term self-learning and inheriting self-learning, and performing zero clearing on short-term self-learning result data corresponding to the layer number of the current strip steel; when the head of the to-be-galvanized strip steel passes through the zinc layer thickness gauge and is a second preset distance away from the zinc layer thickness gauge, short-term self-learning calculation of the to-be-galvanized strip steel is carried out; summing learning results obtained by calculation, and calculating a self-learning sum value representing the predicted thickness of the zinc layer; and controlling the thickness of the zinc layer in the hot galvanizing process according to the predicted thickness of the zinc layer.

Description

Technical Field

[0001] The present invention relates to the technical field of hot-dip galvanized strip production, and particularly to a zinc layer thickness control method and system for continuous hot-dip galvanizing based on self-learning. Background Art

[0002] With the wide application of galvanized sheets in multiple industries, especially in the automotive manufacturing industry, their corrosion resistance has become crucial for ensuring long-term use and enhancing structural durability. The quality of galvanized sheets is mainly evaluated by the thickness and uniformity of the zinc layer, and the thickness of the zinc layer directly affects the anti-corrosion ability and durability of the steel sheet. Therefore, it is extremely important to strictly control the zinc layer thickness.

[0003] However, the existing zinc layer thickness control methods mainly rely on traditional preset models and fixed algorithms, and cannot adapt to the changes in the production environment and working conditions in real time, resulting in insufficient accuracy of zinc layer thickness control.

[0004] In addition, the existing zinc layer thickness prediction models do not comprehensively consider all factors that may affect the zinc layer thickness during the production process, and the accuracy of the model prediction values will be limited due to changes in system characteristics and the environment, with a certain deviation from the actual values, making it impossible to control the zinc layer thickness in a timely and effective manner, thereby affecting product quality. Summary of the Invention

[0005] In order to solve the technical problems in the prior art that mainly rely on traditional preset models and fixed algorithms, cannot adapt to the changes in the production environment and working conditions in real time, resulting in insufficient accuracy of zinc layer thickness control, and do not comprehensively consider all factors that may affect the zinc layer thickness during the production process, and the accuracy of the model prediction values will be limited due to changes in system characteristics and the environment, with a certain deviation from the actual values, making it impossible to control the zinc layer thickness in a timely and effective manner, thereby affecting product quality, the present invention provides a zinc layer thickness control method and system for continuous hot-dip galvanizing based on self-learning.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] A zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning provided by an embodiment of the present invention includes:

[0009] S1: Obtain a plurality of production parameters during the hot-dip galvanizing process;

[0010] S2: Calculate the layer number of the strip to be galvanized according to each of the production parameters;

[0011] S3: Read the result data of three learning processes, namely short-term self-learning, long-term self-learning, and inherited self-learning, corresponding to the layer number of the current strip from the database;

[0012] S4: When the distance between the head of the strip to be galvanized adjacent to the current strip and the air knife is the first preset distance, and the layer numbers of the current strip and the strip to be galvanized are different, calculate the long-term self-learning of the current strip and the inherited self-learning of the strip to be galvanized respectively according to the result data of the long-term self-learning and the inherited self-learning corresponding to the layer number of the current strip, and clear the result data of the short-term self-learning corresponding to the layer number of the current strip;

[0013] S5: When the head of the strip to be galvanized passes the zinc coating thickness gauge and is at the second preset distance from the zinc coating thickness gauge, calculate the short-term self-learning of the strip to be galvanized;

[0014] S6: Store the learning results of the calculated long-term self-learning, inherited self-learning, and short-term self-learning in the database;

[0015] S7: Sum up each of the learning results to calculate the self-learning sum value representing the predicted zinc coating thickness of the strip to be galvanized;

[0016] S8: Control the zinc coating thickness during the hot-dip galvanizing process according to the predicted zinc coating thickness.

[0017] Second aspect:

[0018] A zinc coating thickness control system for continuous hot-dip galvanizing based on self-learning provided by an embodiment of the present invention includes:

[0019] A processor;

[0020] A memory, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor, the zinc coating thickness control method for continuous hot-dip galvanizing based on self-learning as described in the first aspect is implemented.

[0021] Third aspect:

[0022] A computer-readable storage medium provided by an embodiment of the present invention, on which a computer program is stored. When the program is executed by the processor, the zinc coating thickness control method for continuous hot-dip galvanizing based on self-learning as described in the first aspect is implemented.

[0023] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0024] In an embodiment of the present invention, by obtaining a plurality of production parameters during the hot-dip galvanizing process and calculating the layer number of the strip to be galvanized according to each production parameter, it no longer relies on traditional preset models and fixed algorithms, can adapt to changes in the production environment and working conditions in real time, improves the control accuracy of the zinc layer thickness. By performing long-term self-learning of the current strip, calculating the inherited self-learning of the strip to be galvanized, and performing short-term self-learning calculation of the strip to be galvanized, and summing up the learning results of the long-term self-learning, inherited self-learning, and short-term self-learning obtained by the calculation, calculating the self-learning sum value representing the predicted zinc layer thickness of the strip to be galvanized, and controlling the zinc layer thickness during the hot-dip galvanizing process according to the predicted zinc layer thickness, all possible factors affecting the zinc layer thickness during the production process can be comprehensively considered, and the accuracy of the model prediction value will not be limited due to changes in system characteristics and the environment, reducing the deviation from the actual value, enabling the zinc layer thickness to be controlled in a timely and effective manner, and thus improving the product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0026] Figure 1 It is a schematic flow chart of a method for controlling the zinc layer thickness of continuous hot-dip galvanizing based on self-learning provided by an embodiment of the present invention;

[0027] Figure 2 It is a schematic structural diagram of a system for controlling the zinc layer thickness of continuous hot-dip galvanizing based on self-learning provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will describe the technical solutions in the present invention with reference to the drawings.

[0029] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0030] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same. "of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, their intended meanings are the same.

[0031] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, their intended meanings are the same.

[0032] To make the technical problems to be solved, technical solutions, and advantages of the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0033] Refer to the attached drawings of the specification Figure 1 , which shows a schematic flowchart of a method for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning provided by an embodiment of the present invention.

[0034] The embodiments of the present invention provide a method for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning. This method can be implemented by a device for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning, and this device for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning can be a terminal or a server. The processing flow of the method for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning can include the following steps:

[0035] S1: Obtain a plurality of production parameters during the hot-dip galvanizing process.

[0036] Optionally, the process parameters include: air knife gas source, coating specification, strip width, strip thickness, and strip steel type.

[0037] In the present invention, by obtaining a plurality of production parameters during the hot-dip galvanizing process, the influence of various factors on the thickness of the zinc layer can be comprehensively considered, thereby improving the accuracy and adaptability of the self-learning system. Calculating the layer number based on these parameters helps to achieve precise zinc layer control in a complex and changing production environment, ensuring the quality and stability of the final product.

[0038] S2: Calculate the layer number of the strip to be galvanized according to each production parameter.

[0039] It should be noted that the air knife gas source, coating specification, strip width, strip thickness, and strip steel type each include multiple grades.

[0040] Optionally, the air knife gas source includes 2 grades: air grade (G takes the value of 0) and nitrogen grade (G takes the value of 1).

[0041] Optionally, the coating specification includes 6 grades: coating specification ≤ 80 grade (W takes the value of 0), 80 < coating specification ≤ 100 grade (W takes the value of 1), 100 < coating specification ≤ 120 grade (W takes the value of 2), 120 < coating specification ≤ 140 grade (W takes the value of 3), 140 < coating specification ≤ 160 grade (W takes the value of 4), and 160 < coating specification grade (W takes the value of 5). (Unit: g / m 2 )

[0042] Optionally, the strip width includes 6 grades: strip width ≤ 800 grade (B takes the value of 0), 800 < strip width ≤ 1000 grade (B takes the value of 1), 1000 < strip width ≤ 1200 grade (B takes the value of 2), 1200 < strip width ≤ 1400 grade (B takes the value of 3), 1400 < strip width ≤ 1600 grade (B takes the value of 4), and 1600 < strip width grade (B takes the value of 5). (Unit: mm).

[0043] Optionally, the strip thickness includes 7 grades: strip thickness ≤ 0.4 grade (H takes the value of 0), 0.4 < strip thickness ≤ 0.8 grade (H takes the value of 1), 0.8 < strip thickness ≤ 1.2 grade (H takes the value of 2), 1.2 < strip thickness ≤ 1.6 grade (H takes the value of 3), 1.6 < strip thickness ≤ 2.0 grade (H takes the value of 4), 2.0 < strip thickness ≤ 2.4 grade (H takes the value of 5), and 2.4 < strip thickness grade (H takes the value of 6). (Unit: mm).

[0044] Optionally, the strip steel grade includes 15 grades: DC04 - 1 grade (S takes the value of 0), DC04H - 1 grade (S takes the value of 1), DC05G - 1 grade (S takes the value of 2), DC51D - 1 grade (S takes the value of 3), DC51DQ - 1 grade (S takes the value of 4), DC51DZ1 - 1 grade (S takes the value of 5), DC51DZ3 - 1 grade (S takes the value of 6), DC52D - 1 grade (S takes the value of 7), DC52DL - 1 grade (S takes the value of 8), F590QX - 1 grade (S takes the value of 9), H180BH1 - 1 grade (S takes the value of 10), HC180BH - 1 grade (S takes the value of 11), HC180YD - 1 grade (S takes the value of 12), and spare grade (S takes the value of 13 or 14).

[0045] Specifically, according to the air knife gas source grade, coating specification grade, strip width grade, strip thickness grade, and strip steel grade corresponding to the strip to be galvanized, calculate the layer number of the strip to be galvanized.

[0046] In the present invention, by calculating production parameters in multiple grades, the influence of different production conditions on the zinc layer thickness can be accurately reflected. This helps to achieve higher control precision and adaptability, enables handling of complex production environments and variable strip specifications, and improves the stability of the galvanizing process and product quality.

[0047] In a possible implementation manner, the calculation formula for the layer number is specifically:

[0048] N i = G i ×W num ×B num ×H num ×S num

[0049] + W i ×B num ×H num ×S num

[0050] + B i ×H num ×S num + S i + 1

[0051] Wherein, N i represents the layer number of the i-th coil of strip, G i represents the grade of the air knife gas source corresponding to the i-th coil of strip, W num represents the total number of grades of the coating specification, B num represents the total number of grades of the strip width, H num represents the total number of grades of the strip thickness, S num represents the total number of grades of the strip steel type, W i represents the grade of the coating specification corresponding to the i-th coil of strip, B i represents the grade of the strip width corresponding to the i-th coil of strip, S i represents the grade of the strip steel type corresponding to the i-th coil of strip.

[0052] In the present invention, by converting each production parameter into a grade and using the layer number calculation formula, the production conditions of each strip can be accurately mapped to a unique layer number. This method can systematically classify strips of different specifications, helps to optimize the self-learning process, improves the precision of zinc layer thickness control and the adaptability of the production line, and ensures stable product quality.

[0053] S3: Read the result data of the three learning processes of short-term self-learning, long-term self-learning, and inherited self-learning corresponding to the layer number of the current strip from the database.

[0054] In the present invention, by reading the result data of different self - learning processes from the database, the historical learning achievements can be obtained in real - time, ensuring that the current production process can be adjusted and optimized based on previous experience, thereby improving the accuracy of zinc layer thickness prediction and the control precision.

[0055] S4: When the distance between the head of the strip to be galvanized adjacent to the current strip and the air knife is the first preset distance, and the layer numbers of the current strip and the strip to be galvanized are different, calculate the long - term self - learning of the current strip and the inherited self - learning of the strip to be galvanized respectively according to the result data of the long - term self - learning and the inherited self - learning corresponding to the layer number of the current strip, and clear the result data of the short - term self - learning corresponding to the layer number of the current strip.

[0056] It should be noted that when the calculation of the long - term self - learning of the current strip is completed, the result data of the short - term self - learning corresponding to the layer number of the current strip is cleared.

[0057] It should be noted that those skilled in the art can set the size of the first preset distance according to actual needs, and the present invention does not make a limitation here.

[0058] Optionally, the value range of the first preset distance is 50 - 150 meters.

[0059] In the present invention, by calculating the long - term self - learning and the inherited self - learning according to the strip layer number, and clearing the short - term self - learning data after the long - term self - learning is completed, the interference between the self - learning results of strips with different layer numbers can be avoided, ensuring that the learning process of each coil of strip is independent and accurate. At the same time, setting a flexible first preset distance helps to adapt to the actual situation of different production lines, further improving the precision of zinc layer thickness control and the adaptability of the system.

[0060] In a possible implementation manner, the calculation of the long - term self - learning of the current strip and the inherited self - learning of the strip to be galvanized respectively according to the result data of the long - term self - learning and the inherited self - learning corresponding to the layer number of the current strip in S4 specifically includes sub - steps S401 and S402:

[0061] S401: Calculate the long - term self - learning of the current strip according to the result data of the long - term self - learning corresponding to the layer number of the current strip.

[0062] Optionally, S401 is specifically:

[0063] Calculate the long - term self - learning of the current strip according to the following formula:

[0064] βl(j + 1)=βl(j)+α1·βs(j + 1)

[0065] Where, β l(j + 1) represents the long-term self-learning amount of the zinc layer thickness of the (j + 1)-th galvanizing unit with the same strip layer number as the current one, β l (j) represents the long-term self-learning amount of the zinc layer thickness of the j-th galvanizing unit with the same strip layer number as the current one, α1 represents the long-term self-learning smoothing coefficient, β s (j + 1) represents the short-term self-learning amount of the zinc layer thickness of the (j + 1)-th galvanizing unit with the same strip layer number as the current one.

[0066] It should be noted that those skilled in the art can set the magnitude of the long-term self-learning smoothing coefficient according to actual needs, and the present invention does not make any limitation here.

[0067] It should be noted that the galvanizing unit refers to a batch of strips that are continuously produced and have the same layer number.

[0068] For example, assume the strip production sequence is A—A—A—B—B—A—A—C—C (A, B, C represent different layer numbers). Among them, the first continuous production of A—A—A constitutes the first galvanizing unit, and the subsequent B—B, A—A, C—C form the second, third, and fourth galvanizing units respectively. Although the first unit (A—A—A) and the third unit (A—A) are both A-layer strips, due to the interruption of production continuity by the B-layer strip, they are regarded as independent galvanizing units. If the first galvanizing unit (A—A—A) is labeled as j, then the subsequent continuously produced A-layer strip (A—A) will be updated to j + 1, and only when the layer number of the next roll of strip switches (such as A → B or A → C), will the calculation of the long-term self-learning of the strip be triggered.

[0069] Optionally, the value range of the long-term self-learning smoothing coefficient is 0.3 - 0.7.

[0070] In the present invention, the long-term self-learning smoothing coefficient is used to calculate the long-term self-learning amount of the strip, which can dynamically adjust the prediction of the zinc layer thickness according to historical data, ensuring that the control system can more smoothly adapt to production changes. By setting the value range of the smoothing coefficient, it can be flexibly adjusted according to actual production needs, thereby improving the robustness and adaptability of the system, reducing fluctuations, and improving the control accuracy of the zinc layer thickness.

[0071] S402: Calculate the inherited self-learning of the strip to be galvanized according to the result data of the inherited self-learning corresponding to the layer number of the current strip.

[0072] Optionally, S402 is specifically:

[0073] Calculate the inherited self-learning of the strip to be galvanized according to the following formula:

[0074] βr(i + 1) = βr(i) + α2·ΔTh(i)

[0075] Among them, β r (i + 1) represents the inheritance learning amount of the zinc layer thickness of the (i + 1)-th coil of strip steel in the same galvanizing unit as the strip steel to be galvanized, α2 represents the inheritance learning smoothing coefficient, and ΔT h (i) represents the deviation between the predicted value and the measured value of the zinc layer thickness of the i-th coil of strip steel in the same galvanizing unit as the strip steel to be galvanized.

[0076] It should be noted that those skilled in the art can set the magnitude of the inheritance learning smoothing coefficient according to actual needs, and the present invention does not limit this here.

[0077] Optionally, the value range of the long-term self-learning smoothing coefficient is 0.1 - 0.3.

[0078] In the present invention, using the inheritance learning smoothing coefficient to calculate the inheritance learning amount of the strip steel can effectively adjust the deviation between the predicted value of the zinc layer thickness and the actual measured value. This method can smoothly transition the thickness differences between different batches of strip steel, improve the adaptability of the control system to new strip steel, and reduce the instability during the production process. By setting the smoothing coefficient range, it can be flexibly adjusted according to actual production conditions to optimize the control accuracy and stability.

[0079] In a possible implementation manner, when the distance between the head of the strip steel to be galvanized adjacent to the current strip steel and the air knife is the first preset distance, and the layer numbers of the current strip steel and the strip steel to be galvanized are the same, there is no need to calculate the long-term self-learning of the current strip steel (the long-term self-learning amount is 0), and only the inheritance learning and short-term self-learning of the strip steel to be galvanized need to be calculated.

[0080] S5: When the head of the strip steel to be galvanized passes through the zinc layer thickness gauge and is at the second preset distance from the zinc layer thickness gauge, calculate the short-term self-learning of the strip steel to be galvanized.

[0081] It should be noted that those skilled in the art can set the magnitude of the second preset distance according to actual needs, and the present invention does not limit this here.

[0082] Optionally, the value range of the second preset distance is 30 - 100 meters.

[0083] In the present invention, by setting the second preset distance, the calculation timing of the short-term self-learning can be flexibly adjusted according to the actual requirements of the production line. This helps to perform short-term self-learning in a timely manner after the strip steel passes through the zinc layer thickness gauge, improving the real-time performance and accuracy of zinc layer thickness control.

[0084] Optionally, S5 is specifically:

[0085] According to the following formula, calculate the short-term self-learning of the strip steel to be galvanized:

[0086] βs (i + 1)= β s (i)+α3·ΔT h (i + 1)

[0087] where, β s (i + 1) represents the short-term self-learning amount of the zinc layer thickness of the (i + 1)-th coil of strip steel in the same galvanizing unit as the strip steel to be galvanized, and β s (i) represents the short-term self-learning amount of the zinc layer thickness of the i-th coil of strip steel in the same galvanizing unit as the strip steel to be galvanized, α3 represents the short-term self-learning smoothing coefficient, and ΔT h (i + 1) represents the deviation between the predicted value and the measured value of the zinc layer thickness of the (i + 1)-th coil of strip steel in the same galvanizing unit as the strip steel to be galvanized.

[0088] It should be noted that those skilled in the art can set the magnitude of the short-term self-learning smoothing coefficient according to actual needs, and the present invention does not make any limitation here.

[0089] Optionally, the value range of the long-term self-learning smoothing coefficient is 0.3 - 0.7.

[0090] In the present invention, by using the short-term self-learning smoothing coefficient to adjust the self-learning amount of the zinc layer thickness, the smoothness of the learning process can be flexibly controlled according to actual production conditions. Setting the range of the smoothing coefficient can help optimize the response speed of the system to the thickness prediction deviation, avoid over-adjustment, thereby improving the prediction accuracy and reducing the fluctuations in the production process.

[0091] S6: Store the learning results of the calculated long-term self-learning, inherited self-learning, and short-term self-learning into the database.

[0092] In the present invention, storing the results of long-term self-learning, inherited self-learning, and short-term self-learning into the database can ensure the persistence of historical learning data, which is convenient for subsequent query and use. This helps to update the system in real time, improve the prediction accuracy, and optimize the future zinc layer thickness control.

[0093] S7: Sum up each learning result to calculate the self-learning sum value representing the predicted zinc layer thickness of the strip steel to be galvanized.

[0094] In the present invention, by summing up the results of long-term self-learning, inherited self-learning, and short-term self-learning, the influences of different learning processes can be comprehensively considered, so as to more accurately predict the zinc layer thickness of the strip steel to be galvanized. This improves the accuracy and stability of the control, and ensures the quality of the galvanizing process.

[0095] Optionally, S7 is specifically:

[0096] Calculate the self-learning sum value representing the predicted zinc layer thickness of the strip steel to be galvanized according to the following formula:

[0097] β T = β l + β s + β r

[0098] Wherein, β T represents the self-learning sum value representing the predicted zinc coating thickness of the strip to be galvanized, β l represents the long-term self-learning amount, β s represents the short-term self-learning amount, β r represents the inherited self-learning amount.

[0099] In the present invention, by adding the results of long-term self-learning, short-term self-learning and inherited self-learning, the influence of different self-learning processes can be comprehensively considered to form a more comprehensive prediction of the zinc coating thickness. This method not only improves the accuracy of the prediction, but also can effectively adapt to the changes under different production conditions, thereby optimizing the control of the galvanizing process and ensuring the quality stability of the final product.

[0100] S8: Control the zinc coating thickness during hot-dip galvanizing according to the predicted zinc coating thickness.

[0101] In the present invention, by controlling according to the predicted zinc coating thickness, the air knife parameters during hot-dip galvanizing can be adjusted in real time to ensure that the zinc coating thickness always remains within the target range. This improves the accuracy and stability of the production process and effectively guarantees the product quality.

[0102] Refer to the appended drawings of the specification Figure 2 which shows a schematic structural diagram of a zinc coating thickness control system for continuous hot-dip galvanizing based on self-learning provided by the present invention.

[0103] The present invention also provides a zinc coating thickness control system 20 for continuous hot-dip galvanizing based on self-learning, which is applied to the above-mentioned zinc coating thickness control method for continuous hot-dip galvanizing based on self-learning, and includes:

[0104] A processor 201;

[0105] A memory 202, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor 201, the zinc coating thickness control method for continuous hot-dip galvanizing based on self-learning as described in the method embodiment is implemented.

[0106] The zinc coating thickness control system 20 for continuous hot-dip galvanizing based on self-learning provided by the present invention can execute the above-mentioned zinc coating thickness control method for continuous hot-dip galvanizing based on self-learning and achieve the same or similar technical effects. To avoid repetition, the present invention will not be described in detail herein.

[0107] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0108] In an embodiment of the present invention, by obtaining a plurality of production parameters during the hot-dip galvanizing process and calculating the layer number of the strip to be galvanized according to each production parameter, it no longer relies on traditional preset models and fixed algorithms, can adapt to changes in the production environment and working conditions in real time, improves the control accuracy of the zinc layer thickness. By performing long-term self-learning of the current strip, calculation of inherited self-learning of the strip to be galvanized, and calculation of short-term self-learning of the strip to be galvanized, and summing up the learning results of the long-term self-learning, inherited self-learning, and short-term self-learning obtained by the calculation, calculating the self-learning sum value representing the predicted zinc layer thickness of the strip to be galvanized, and controlling the zinc layer thickness during the hot-dip galvanizing process according to the predicted zinc layer thickness, all possible factors that may affect the zinc layer thickness during the production process can be comprehensively considered, the accuracy of the model prediction value will not be limited due to changes in system characteristics and the environment, the deviation from the actual value is reduced, the zinc layer thickness can be controlled in a timely and effective manner, and thus the product quality is improved.

[0109] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0110] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0111] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0112] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be understood specifically with reference to the context before and after.

[0113] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0114] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0115] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0116] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0117] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, the functional units in various embodiments of the present invention can be integrated in one processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0120] When the above-mentioned functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0121] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and is characterized in that when the program is executed by a processor, it implements the zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning as described in the method embodiment.

[0122] The computer-readable storage medium provided by the present invention can implement the steps and effects of the zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning in the above method embodiment. To avoid repetition, the present invention will not elaborate further.

[0123] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0124] In the embodiments of the present invention, by obtaining multiple production parameters during the hot-dip galvanizing process and calculating the layer number of the strip to be galvanized according to each production parameter, it no longer relies on traditional preset models and fixed algorithms, can adapt to changes in the production environment and working conditions in real time, improves the zinc layer thickness control accuracy. By performing long-term self-learning of the current strip, inheritance self-learning calculation of the strip to be galvanized, and short-term self-learning calculation of the strip to be galvanized, and summing up the learning results of the long-term self-learning, inheritance self-learning, and short-term self-learning obtained by the calculation, calculating the self-learning sum value representing the predicted zinc layer thickness of the strip to be galvanized, and controlling the zinc layer thickness during the hot-dip galvanizing process according to the predicted zinc layer thickness, it can comprehensively consider all factors that may affect the zinc layer thickness during the production process, will not be limited by the changes in system characteristics and environment in terms of the accuracy of the model prediction value, reduces the deviation from the actual value, enables the zinc layer thickness to be controlled timely and effectively, and thus improves the product quality.

[0125] As described above, it is only the specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0126] The following points need to be explained:

[0127] (1) The drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0128] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of the layer or region is enlarged or reduced, that is, these drawings are not drawn according to the actual scale. It can be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be an intermediate element.

[0129] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0130] As mentioned above, it is only the specific implementation manners of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for controlling the thickness of the zinc layer in continuous hot-dip galvanizing based on self-learning, characterized in that, Including: S1: Obtain multiple production parameters during hot-dip galvanizing; S2: Calculate the layer number of the strip to be galvanized according to each of the production parameters; S3: Read the result data of three learning processes, namely short-term self-learning, long-term self-learning, and inherited self-learning, corresponding to the layer number of the current strip from the database; S4: When the distance between the head of the strip to be galvanized adjacent to the current strip and the air knife is the first preset distance, and the layer numbers of the current strip and the strip to be galvanized are different, calculate the long-term self-learning of the current strip and the inherited self-learning of the strip to be galvanized respectively according to the result data of long-term self-learning and inherited self-learning corresponding to the layer number of the current strip, and clear the result data of short-term self-learning corresponding to the layer number of the current strip; S5: When the head of the strip to be galvanized passes through the zinc layer thickness gauge and is at the second preset distance from the zinc layer thickness gauge, calculate the short-term self-learning of the strip to be galvanized; S6: Store the calculated learning results of long-term self-learning, inherited self-learning, and short-term self-learning in the database; S7: Sum up each of the learning results and calculate the self-learning sum value representing the predicted zinc layer thickness of the strip to be galvanized; S8: Control the zinc layer thickness during the hot-dip galvanizing process according to the predicted zinc layer thickness.

2. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 1, wherein The process parameters include: air knife gas source, coating specification, strip width, strip thickness, and strip steel type.

3. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 2, characterized in that, The specific calculation formula for the layer number is: N i = G i × W num × B num × H num × S num + W i × B num × H num × S num + B i × H num × S num + S i + 1 Among them, N i represents the layer number of the i-th coil of strip steel, G i represents the gear position of the air knife gas source corresponding to the i-th coil of strip steel, W num represents the total number of gear positions of the coating specification, B num represents the total number of gear positions of the strip width, H num represents the total number of gear positions of the strip thickness, S num represents the total number of gear positions of the strip steel grades, W i represents the gear position of the coating specification corresponding to the i-th coil of strip steel, B i represents the gear position of the strip width corresponding to the i-th coil of strip steel, S i represents the gear position of the strip steel grade corresponding to the i-th coil of strip steel.

4. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 1, characterized in that, The calculation in S4 of respectively performing the long-term self-learning of the current strip and the inherited self-learning of the strip to be galvanized according to the result data of long-term self-learning and inherited self-learning corresponding to the layer number of the current strip specifically includes: S401: Calculate the long-term self-learning of the current strip according to the result data of long-term self-learning corresponding to the layer number of the current strip; S402: Calculate the inherited self-learning of the strip to be galvanized according to the result data of inherited self-learning corresponding to the layer number of the current strip.

5. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 4, characterized in that, S401 is specifically: Calculate the long-term self-learning of the current strip according to the following formula: βl(j + 1) = βl(j) + α1·βs(j + 1) Among them, β l (j + 1) represents the long-term self-learning amount of the zinc layer thickness of the (j + 1)-th galvanizing unit with the same strip layer number as the current one, β l (j) represents the long-term self-learning amount of the zinc layer thickness of the j-th galvanizing unit with the same strip layer number as the current one, α1 represents the long-term self-learning smoothing coefficient, β s (j + 1) represents the short-term self-learning amount of the zinc layer thickness of the (j + 1)-th galvanizing unit with the same strip layer number as the current one.

6. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 4, characterized in that, S402 is specifically: Calculate the inherited self-learning of the strip to be galvanized according to the following formula: βr(i + 1) = βr(i) + α2·ΔTh(i) Among them, β r (i + 1) represents the learning amount inherited from the zinc layer thickness of the (i + 1)-th strip in the same galvanizing unit as the strip to be galvanized, α2 represents the learning smoothing coefficient inherited, and ΔT h (i) represents the deviation between the predicted value and the measured value of the zinc layer thickness of the i-th strip in the same galvanizing unit as the strip to be galvanized.

7. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 1, characterized in that, S5 is specifically: Calculate the short-term self-learning of the strip to be galvanized according to the following formula: β s (i + 1) = β s (i) + α3·ΔT h (i + 1) Among them, β s (i + 1) represents the short-term self-learning amount of the zinc layer thickness of the (i + 1)-th strip in the same galvanizing unit as the strip to be galvanized, β s (i) represents the short-term self-learning amount of the zinc layer thickness of the i-th strip in the same galvanizing unit as the strip to be galvanized, α3 represents the short-term self-learning smoothing coefficient, ΔT h (i + 1) represents the deviation between the predicted value and the measured value of the zinc layer thickness of the (i + 1)-th strip in the same galvanizing unit as the strip to be galvanized.

8. The zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning according to claim 1, characterized in that, S7 is specifically: Calculate the self-learning sum value representing the predicted zinc layer thickness of the strip to be galvanized according to the following formula: β T ＝β l +β s +β r Among them, β T represents the self-learning sum value representing the predicted zinc coating thickness of the strip to be galvanized, β l represents the long-term self-learning amount, β s represents the short-term self-learning amount, β r represents the inherited self-learning amount.

9. A zinc layer thickness control system for continuous hot-dip galvanizing based on self-learning, characterized in that, Including: A processor; A memory, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by the processor, implement the zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning as described in any one of claims 1 to 8.

10. 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 zinc layer thickness control method for continuous hot-dip galvanizing based on self-learning as described in any one of claims 1 to 8.

Images