Control system and method for automatic production line of hot-dip aluminum-zinc coated steel sheet

By combining the generation of adversarial network model and the blockchain network, the cooling speed of hot-dip galvanized steel plates is dynamically adjusted, which solves the problem that the cooling speed fixed in the existing technology cannot meet customer needs, and realizes an automatic production line efficient and flexible control.

CN118703918BActive Publication Date: 2024-12-06浙江华普新材股份有限公司
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411180555.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

The cooling speed of the existing hot-dip aluminum-galvanized steel sheet production line is based on pre-selected fixed parameters, which cannot be adaptively adjusted according to actual customer needs, resulting in the coating quality and performance that cannot meet the real needs of customers.

Method used

Generative adversarial network model is used to process the design target information of hot-dip aluminum-galvanized steel plates, model training and parameter optimization are performed through blockchain or alliance chain network, and cooling speed is dynamically adjusted to match customer needs.

Benefits of technology

It realizes automatic control of hot-dip aluminum-galvanized steel plates throughout the process, ensures that the coating quality and performance meet customer needs, and improves the flexibility and efficiency of the production line.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118703918B_ABST
    Figure CN118703918B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of smart factories. A control system and method for an automatic production line of hot-dip aluminum-zinc steel plates are provided. The method comprises: controlling an annealing device to anneal the steel plate, and controlling a hot-dip aluminum-zinc coating device to place the annealed steel plate in a zinc pot; obtaining design target information of the hot-dip aluminum-zinc steel plate, inputting the design target information into a generative adversarial network model, and the generative adversarial network model outputs a cooling rate corresponding to the design target information; cooling the steel plate after the hot-dip aluminum-zinc coating according to the cooling rate. The present invention uses a generative adversarial network model to process the design target information of the hot-dip aluminum-zinc steel plate, thereby obtaining an optimal cooling rate corresponding to the design target information, and cooling the steel plate after the hot-dip galvanizing according to the cooling rate, so as to obtain a hot-dip galvanized steel plate that is closer to the actual needs of customers.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart factories, and in particular to a control system and method for an automatic production line of hot-dip aluminum-zinc coated steel plates. Background Art

[0002] Hot-dip galvanized steel sheet is a material with excellent performance. It is composed of aluminum, zinc and a small amount of silicon. The aluminum content is about 55%, the zinc content is about 43.4%, and the silicon content is about 1.6%. The main characteristics of this material include stronger corrosion resistance, good heat resistance, thermal conductivity and heat reflection, formability and weldability. It is usually used in applications that require good reflectivity, such as reflectors inside ovens and reflectors for electric cookers.

[0003] The regulation of cooling speed is an important process parameter of the hot-dip galvanized steel plate production line. Different cooling speeds will lead to large differences in the coating quality and performance of the hot-dip galvanized steel plate. At the same time, different customers have different design goals for hot-dip galvanized steel plates. The above factors have put forward the demand for adaptive regulation of cooling speed. However, in the existing methods, the cooling speed of the hot-dip galvanized steel plate is based on pre-selected fixed parameters and cannot be adaptively adjusted according to actual needs. The present invention aims to solve this technical problem. Summary of the invention

[0004] In this regard, the present invention provides a control method, system, electronic equipment, computer storage medium and computer program product for an automatic production line of hot-dip aluminum-zinc coated steel plates to solve the above-mentioned technical problems.

[0005] The present invention discloses a control method for an automatic production line of hot-dip aluminum-zinc coated steel plates, the method comprising the following steps: controlling an annealing device to anneal a steel plate, and controlling a hot-dip aluminum-zinc coated device to place the annealed steel plate in a zinc pot; obtaining design target information of the hot-dip aluminum-zinc coated steel plate, inputting the design target information into a generative adversarial network model, the generative adversarial network model outputting a cooling speed corresponding to the design target information; and cooling the steel plate after the hot-dip aluminum-zinc coating according to the cooling speed.

[0006] In some embodiments, the design target information includes surface flatness, zinc flower size, and alloy layer thickness.

[0007] In some embodiments, the method also includes: the local node publishes a training invitation for the generative adversarial network model on a shared network, and the training invitation includes an untrained generative adversarial network model; wherein the shared network is a blockchain network or a consortium chain network; other nodes in the shared network collect and organize first training data based on the training invitation, and each other node independently trains the untrained generative adversarial network model based on the first training data, and feeds back the first key parameters of the trained generative adversarial network model to the local node; other nodes in the shared network also feed back the first training data to the local node, and the local node integrates the fed-back first training data to obtain second training data, and uses the second training data to perform local training on the generative adversarial network model to obtain second key parameters of the generative adversarial network model; the local node screens and fuses the second key parameters and the first key parameters based on the test data to obtain third key parameters, and replaces the third key parameters with the generative adversarial network model trained by the local node.

[0008] In some embodiments, other nodes in the shared network collect and organize the first training data based on the training invitation, including: the local node receives response information from several other nodes in the shared network, and the response information includes the number of trainings and average training time data for the model belonging to the generative adversarial network; the local node sorts each of the other nodes from small to large according to the average training time data, and calculates the average number of trainings based on each of the training times, and selects the target number of other nodes from the sorted header data according to the average training times; the local node sends confirmation information to each of the screened other nodes, and the other nodes in the shared network collect and organize the first training data based on the confirmation information.

[0009] In some embodiments, the step of obtaining a target number of other nodes from the sorted header data according to the average number of training times includes: substituting the average number of training times into the following formula to obtain the target number; ; In the formula, is the target quantity, is the benchmark target number, is the average number of training times, is the median value of the training times of each other node; and the target number of other nodes in the sorted header data are screened out.

[0010] In some embodiments, the generative adversarial network model outputs a cooling speed corresponding to the design target information, including: the generative adversarial network model outputs a cooling speed corresponding to the design target information, and the cooling speed includes a first-segment cooling speed, a second-segment cooling speed, and a third-segment cooling speed.

[0011] The present invention also discloses a control system for an automatic production line of hot-dip aluminum-zinc steel plates, the system comprising a first control module, a determination module, and a second control module; the first control module is used to control an annealing device to anneal the steel plates, and to control a hot-dip galvanizing device to place the annealed steel plates in a zinc pot; the determination module is used to obtain design target information of the hot-dip aluminum-zinc steel plates, input the design target information into a generative adversarial network model, and the generative adversarial network model outputs a cooling speed corresponding to the design target information; the second control module is used to cool the steel plates after hot-dip galvanizing according to the cooling speed.

[0012] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the above methods.

[0013] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present invention also discloses a computer program product, which implements any of the above methods when the computer program product is run on a terminal.

[0015] The beneficial technical effects of the present invention are: 1. The present invention controls the production equipment of the main processing steps of the hot-dip aluminum-zinc coated steel sheet, such as annealing, aluminum-zinc coating, and cooling, thereby realizing full-process automatic control of the hot-dip aluminum-zinc coated steel sheet automatic production line.

[0016] 2. The present invention further constructs a generative adversarial network model, which processes the design target information of the hot-dip galvanized steel plate to obtain the optimal cooling rate corresponding to the design target information. The steel plate after hot-dip galvanizing is cooled according to the cooling rate to obtain a hot-dip galvanized steel plate that is closer to the actual needs of customers. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of a control method for an automatic production line of hot-dip aluminum-zinc coated steel plates disclosed in an embodiment of the present invention.

[0019] Figure 2 It is a flowchart of the training process of the generative adversarial network disclosed in an embodiment of the present invention.

[0020] Figure 3 It is a structural schematic diagram of a control system of an automatic production line for hot-dip aluminum-zinc steel plates disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0022] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0023] like Figure 1 As shown, an embodiment of the present invention discloses a method for controlling an automatic production line of hot-dip aluminum-zinc coated steel plates, the method comprising the following steps: controlling an annealing device to anneal the steel plates, and controlling a hot-dip aluminum-zinc coating device to place the annealed steel plates in a zinc pot (usually, the aluminum content in the zinc pot is about 55%, the zinc content is about 43.5%, and the silicon content is about 1.5%); obtaining design target information of the hot-dip aluminum-zinc coated steel plates, inputting the design target information into a generative adversarial network model, and the generative adversarial network model outputting a cooling rate corresponding to the design target information; and cooling the steel plates after the hot-dip aluminum-zinc coating according to the cooling rate.

[0024] The production of hot-dip galvanized steel sheets involves major processing steps such as annealing, galvanizing, and cooling. The present invention automatically controls the production equipment corresponding to the above steps, thereby realizing full-process automatic control of the hot-dip galvanized steel sheet automatic production line. The main improvement of the present invention lies in the cooling stage.

[0025] The cooling rate of hot-dip galvanized steel sheet is an important process parameter that affects the quality and performance of the coating. The cooling rate of existing hot-dip galvanized steel sheet is a wide range of values, such as 15-50℃ / s. However, the design goals of hot-dip galvanized steel sheet are different, which is mainly determined according to customer needs. Different design goals require different cooling rates, and the existing technology currently mostly selects the appropriate cooling rate based on empirical values, which results in the final production of hot-dip galvanized steel sheet often failing to meet the actual needs of customers in terms of coating quality and performance.

[0026] In response to the above technical problems, the present invention further constructs a generative adversarial network model, which processes the design target information of the hot-dip galvanized steel plate to obtain the optimal cooling rate corresponding to the design target information. The steel plate after hot-dip galvanizing is cooled according to the cooling rate to obtain a hot-dip galvanized steel plate that is closer to the actual needs of customers.

[0027] In some embodiments, the design target information includes surface flatness, zinc flower size, and alloy layer thickness.

[0028] In this embodiment, the designer can determine the design target information of the hot-dip galvanized steel sheet in advance according to customer needs, mainly including surface flatness, zinc flower size, and alloy layer thickness. The above design target information is affected by the cooling rate. For example, when the cooling rate is low (such as 25°C / s), a coating with a relatively flat surface, uniform zinc flower size, and uniform alloy layer thickness can be obtained.

[0029] In some embodiments, the method also includes: the local node publishes a training invitation for the generative adversarial network model on a shared network, and the training invitation includes an untrained generative adversarial network model; wherein the shared network is a blockchain network or a consortium chain network; other nodes in the shared network collect and organize first training data based on the training invitation, and each other node independently trains the untrained generative adversarial network model based on the first training data, and feeds back the first key parameters of the trained generative adversarial network model to the local node; other nodes in the shared network also feed back the first training data to the local node, and the local node integrates the fed-back first training data to obtain second training data, and uses the second training data to perform local training on the generative adversarial network model to obtain second key parameters of the generative adversarial network model; the local node screens and fuses the second key parameters and the first key parameters based on the test data to obtain third key parameters, and replaces the third key parameters with the generative adversarial network model trained by the local node.

[0030] In this embodiment, the above-mentioned generative adversarial network model needs to be trained before it can accurately predict the optimal cooling rate corresponding to the design target information. The present invention implements the training of the generative adversarial network model based on a shared network constructed based on a blockchain network or a consortium chain network.

[0031] Specifically, Figure 2 As shown, the local node first publishes the training invitation of the generative adversarial network model to the shared network. In addition to the "invitation", the invitation also includes an untrained generative adversarial network model. Other nodes in the shared network can decide whether to accept the invitation according to their own situation. If accepted, they collect and organize their own first training data based on the training invitation, and independently train the untrained generative adversarial network model based on this, and feed back the first key parameters of the trained generative adversarial network model to the local node through the shared network. At the same time, other nodes in the shared network also feed back the first training data to the local node, and the local node can integrate the received first training data to obtain the second training data (for example, according to the relative proportion of the feedback of each first training data, or randomly screen from each first training data until the preset amount of training data is met, or according to the preset amount of training data and the number of other nodes fed back, average screening), and then locally train the generative adversarial network model to obtain the second key parameters of the generative adversarial network model. Finally, the local node uses the test data to screen and fuse the second key parameter obtained locally and the first key parameter obtained by other nodes to obtain the third key parameter, which is then replaced in the generative adversarial network model trained by the local node. Thus, a trained generative adversarial network model is obtained that can accurately predict the optimal cooling speed corresponding to the design target information.

[0032] Among them, the key parameters include but are not limited to the weights of the inter-layer connections in the generative adversarial network model, bias terms, parameters of the convolution kernel or fully connected layer (such as the size of the convolution kernel, pooling layer, and convolution step length), etc. These parameters are continuously optimized during the training process, and the above parameters in the trained generative adversarial network model reach the optimal value. The generative adversarial network model has the ability to accurately predict the optimal cooling speed corresponding to the design target information.

[0033] The local node inputs each first key parameter and second key parameter into the generative adversarial network model trained by the local node, and tests it with test data to obtain the corresponding model output accuracy; and then randomly mixes the first key parameter and the second key parameter to obtain multiple groups of corresponding mixed key parameters, and inputs the mixed key parameters into the generative adversarial network model trained by the local node, and tests it with test data to obtain the corresponding model output accuracy. The key parameter with the highest model output accuracy (i.e., one of the first key parameter, the second key parameter, and the mixed parameter) is determined as the third key parameter, and then the third key parameter is replaced in the generative adversarial network model trained by the local node, thereby completing the training of the generative adversarial network model.

[0034] In some embodiments, other nodes in the shared network collect and organize the first training data based on the training invitation, including: the local node receives response information from several other nodes in the shared network, and the response information includes the number of trainings and average training time data for the model belonging to the generative adversarial network; the local node sorts each of the other nodes from small to large according to the average training time data, and calculates the average number of trainings based on each of the training times, and selects the target number of other nodes from the sorted header data according to the average training times; the local node sends confirmation information to each of the screened other nodes, and the other nodes in the shared network collect and organize the first training data based on the confirmation information.

[0035] In this embodiment, other nodes in the shared network analyze the received training invitations, and when they have the training conditions, they can send response information to the local node, which includes the number of training times and average training time data for the model belonging to the generative adversarial network. These data characterize the number of times the other nodes train the model belonging to the adversarial network and the average training time required, reflecting the training ability of the other nodes for the model belonging to the adversarial network. The local node can sort the other nodes from small to large according to the average training time data, and the head of the sorting team is the other nodes with short average training time, and the tail is the other nodes with long average training time. At the same time, the local node also calculates the average training number based on the training times of all other nodes in the sorting team, and filters out the target number of other nodes from the head of the sorting team based on the average training number.

[0036] In some embodiments, the step of obtaining a target number of other nodes from the sorted header data according to the average number of training times includes: substituting the average number of training times into the following formula to obtain the target number; ; In the formula, is the target quantity, is the benchmark target number, is the average number of training times, is the median value of the training times of each other node; and the target number of other nodes in the sorted header data are screened out.

[0037] In this embodiment, the target number is negatively correlated with the average training times of all other nodes that respond to the local node, that is, the larger the average training times, the more abundant the training capabilities of these other nodes for the generative adversarial network, and in this case, only a smaller number of other nodes need to be obtained to participate in the training of the generative adversarial network model; on the contrary, the smaller the average training times, the worse the training capabilities of these other nodes for the generative adversarial network, and in this case, a larger number of other nodes need to be obtained to participate in the training of the generative adversarial network model.

[0038] In addition, the above formula of the present invention also takes into account the median value of the number of training times of each other node. By combining the median value with the average number of training times, the target number finally obtained is less likely to have excessive deviation.

[0039] It should be noted that the above-mentioned training capabilities are mainly reflected in the speed of acquiring training data, the diversity of the acquired training data, and the training rate.

[0040] In some embodiments, the generative adversarial network model outputs a cooling speed corresponding to the design target information, including: the generative adversarial network model outputs a cooling speed corresponding to the design target information, and the cooling speed includes a first-segment cooling speed, a second-segment cooling speed, and a third-segment cooling speed.

[0041] In this embodiment, the present invention adopts a three-stage cooling process, that is, the cooling speed is set to include a first stage cooling speed, a second stage cooling speed and a third stage cooling speed. Such a setting can achieve more refined processing of the cooling speed, which is conducive to obtaining a hot-dip aluminum-zinc steel plate that is more matched with the design target information.

[0042] The training data (including the first training data, the second training data, and the third training data) include target labels and cooling rates, wherein the target labels include three aspects: surface flatness, zinc flower size, and alloy layer thickness, and the cooling rates include the first cooling rate, the second cooling rate, and the third cooling rate. The training data is obtained in the following manner: a set of three-stage cooling rates is set, and based on the cooling rates, a steel plate with a specific ratio and treated with hot-dip aluminum-zinc is cooled, and the surface flatness, zinc flower size, and alloy layer thickness of the treated steel plate are measured, and the measured values ​​are determined as the labels of the three-stage cooling rates, namely, the surface flatness label, zinc flower size label, and alloy layer thickness label. The above training data can be used to fully train the generative adversarial network model.

[0043] like Figure 3 As shown, an embodiment of the present invention also discloses a control system for an automatic production line of hot-dip aluminum-zinc steel plates, the system comprising a first control module, a determination module, and a second control module; the first control module is used to control an annealing device to anneal the steel plates, and to control a hot-dip galvanizing device to place the annealed steel plates in a zinc pot; the determination module is used to obtain design target information of the hot-dip aluminum-zinc steel plates, input the design target information into a generative adversarial network model, and the generative adversarial network model outputs a cooling speed corresponding to the design target information; the second control module is used to cool the steel plates after hot-dip galvanizing according to the cooling speed.

[0044] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0045] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0046] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the method described in the above embodiment is implemented.

[0047] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the device according to an embodiment of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0048] References herein to "one embodiment," "embodiment," or "one or more embodiments" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present invention. In addition, please note that examples of the term "in one embodiment" herein do not necessarily all refer to the same embodiment.

[0049] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0050] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0051] In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or limiting the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative rather than restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the appended claims.

Claims

1. A control method for an automatic production line of hot-dip galvanized steel sheets. It is characterized in that The method comprises the following steps: Control the annealing equipment to anneal the steel plate, and control the hot-dip galvanizing equipment to place the annealed steel plate in the zinc pot; Acquire design target information of the hot-dip galvanized steel plate, input the design target information into a generative adversarial network model, and the generative adversarial network model outputs a cooling rate corresponding to the design target information; Cooling the steel plate after hot-dip galvanizing according to the cooling rate; The design target information includes surface flatness, zinc flower size, and alloy layer thickness; The method further comprises: The local node publishes a training invitation for the generative adversarial network model on a shared network, wherein the training invitation includes an untrained generative adversarial network model; wherein the shared network is a blockchain network or a consortium chain network; The other nodes in the shared network collect and organize the first training data based on the training invitation, and each other node independently trains the untrained generative adversarial network model based on the first training data, and feeds back the first key parameter of the trained generative adversarial network model to the local node; Other nodes in the shared network also feed back the first training data to the local node, and the local node integrates the fed-back first training data to obtain second training data, and uses the second training data to perform local training on the generative adversarial network model to obtain second key parameters of the generative adversarial network model; The local node screens and fuses the second key parameter and each of the first key parameters based on the test data to obtain a third key parameter, and replaces the third key parameter into the generative adversarial network model trained by the local node.

2. According to claim 1, a method for controlling an automatic production line of hot-dip galvanized steel sheets, Features: Other nodes in the sharing network collect and organize the first training data based on the training invitation, including: The local node receives response information from several other nodes in the shared network, wherein the response information includes the number of trainings and average training time data for the model belonging to the generative adversarial network; The local node sorts the other nodes from small to large according to the average training time data, calculates the average training times according to the training times, and selects the target number of other nodes from the sorted head data according to the average training times; The local node sends confirmation information to each of the screened other nodes, and the other nodes in the shared network collect and organize the first training data based on the confirmation information.

3. A control method for an automatic production line of hot-dip galvanized steel sheet according to claim 2, Features: Screening out a target number of the other nodes from the sorted header data according to the average number of training times includes: Substituting the average number of training times into the following formula, the target number is obtained; ; In the formula, is the target quantity, is the benchmark target number, is the average number of training times, is the median value of the training times of other nodes; The target number of other nodes in the sorted header data are filtered out.

4. A control method for an automatic production line of hot-dip galvanized steel sheet according to claim 1, Features: The generative adversarial network model outputs a cooling rate corresponding to the design target information, including: The generative adversarial network model outputs a cooling rate corresponding to the design target information, and the cooling rate includes a first-stage cooling rate, a second-stage cooling rate, and a third-stage cooling rate.

5. A hot-dip galvanized steel sheet automatic production line control system based on the method according to any one of claims 1 to 4, the system comprising a first control module, a determination module, and a second control module; Features: The first control module is used to control the annealing equipment to anneal the steel plate, and control the hot-dip galvanizing equipment to place the annealed steel plate in the zinc pot; The determination module is used to obtain design target information of the hot-dip galvanized steel plate, input the design target information into a generative adversarial network model, and the generative adversarial network model outputs a cooling rate corresponding to the design target information; The second control module is used to cool the steel plate after hot-dip galvanizing according to the cooling speed.

6. An electronic device, include: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 4.

7. A computer storage medium storing a computer program, Features: The computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

8. A computer program product, Features: When the computer program product runs on a terminal, the method according to any one of claims 1 to 4 is implemented.

Citation Information

Patent Citations

  • Block chain-based data training method and apparatus, storage medium and block chain node

    CN108323200A

  • Production method of hot-dip aluminum-zinc coated steel plate

    CN110872676A

  • Automatic spangle adjusting system for aluminum-zinc plated steel plate

    CN117248171A

  • Temperature control method and system of reaction kettle based on artificial intelligence

    CN118170184A

  • Aluminum-zinc plated steel plate finished product image data identification processing method

    CN118247580A