Pressure control methods, devices and equipment for air knives

Abstract

This invention discloses a pressure control method, apparatus, and device for an air knife. The method includes: processing working condition data through a pre-trained pressure determination model to obtain a target pressure; the working condition data includes the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness; and controlling the air knife pressure based on the target pressure to ensure that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold. This invention solves the technical problem of low rationality in air knife pressure parameter settings.

Description

Technical Field

[0001] This invention belongs to the field of air knife control technology, and particularly relates to a pressure control method, device and equipment for an air knife. Background Technology

[0002] Traditional zinc coating control requires manual setting of air knife pressure parameters based on experience, followed by adjustments based on feedback data from a zinc coating thickness gauge. Inexperienced personnel may set inappropriate pressure parameters, leading to unstable product quality, uncertainty, and unreliability, ultimately resulting in product defects or wasted zinc resources. Therefore, the low accuracy of air knife pressure parameter settings is a pressing technical problem that needs to be addressed. Summary of the Invention

[0003] This invention provides a method, apparatus, and equipment for controlling the pressure of an air knife, which solves the technical problem of low rationality in the setting of air knife pressure parameters.

[0004] In a first aspect, embodiments of the present invention provide a pressure control method for an air knife, comprising: processing working condition data through a pre-trained pressure determination model to obtain a target pressure, wherein the working condition data includes the current strip thickness, the current strip speed, the current average air knife distance, and the target zinc layer thickness; and controlling the pressure of the air knife based on the target pressure so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

[0005] In conjunction with the first aspect of the present invention, in some embodiments, after controlling the pressure of the air knife based on the target pressure, the method further includes: obtaining the current upper surface zinc layer thickness and the current lower surface zinc layer thickness of the strip; if the deviation between the current upper surface zinc layer thickness and the target zinc layer thickness is less than a first thickness deviation threshold, and the deviation between the current lower surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, determining that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than the first thickness deviation threshold.

[0006] In conjunction with the first aspect of the present invention, in some embodiments, the method further includes: acquiring multiple sets of first training data, each set of first training data including air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness; and training the model to be trained based on the multiple sets of first training data to obtain the pressure determination model.

[0007] In conjunction with the first aspect of the present invention, in some embodiments, acquiring multiple sets of first training data includes: acquiring multiple sets of second training data, each set of second training data including air knife pressure, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip; for each set of second training data, the average of the air knife distance on the upper surface (operating side), the air knife distance on the upper surface (driving side), the air knife distance on the lower surface (operating side), and the air knife distance on the lower surface (driving side) is taken as the average air knife distance, and the average of the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface is taken as the average zinc layer thickness, so as to obtain the multiple sets of first training data.

[0008] In conjunction with the first aspect of the present invention, in some embodiments, the acquisition of multiple sets of second training data includes: filtering abnormal data from the first historical production data to obtain second historical production data, wherein the abnormal data includes null data, data exceeding process limits, and data with incorrect format; the first historical production data includes air knife pressure, air knife height, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip at different times; deleting upper surface zinc layer thickness data and lower surface zinc layer thickness data of a preset length from the second historical production data to obtain third historical production data to achieve data alignment; and obtaining the multiple sets of second training data based on the third historical production data.

[0009] In conjunction with the first aspect of the present invention, in some embodiments, obtaining the multiple sets of second training data based on the third historical production data includes: dividing the third historical production data into multiple sets of production data according to a preset strip length; for each set of production data in the multiple sets of production data, if the set of production data meets a preset condition, using the set of production data as a set of second training data of the multiple sets of second training data, wherein the preset condition is that the strip speed deviation is less than a preset speed deviation threshold, the air knife pressure deviation is less than a preset pressure deviation threshold, the air knife distance deviation is less than a preset distance deviation threshold, the air knife height deviation is less than a preset height deviation threshold, and the deviation between the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface of the strip is less than a preset second thickness deviation threshold.

[0010] In conjunction with the first aspect of the present invention, in some embodiments, controlling the pressure of the air knife based on the target pressure includes: transmitting the target pressure to a first-level programmable logic controller (PLC) of the air knife via a TCP protocol; the first-level PLC controlling the pressure of the air knife according to the target pressure.

[0011] In conjunction with the first aspect of the present invention, in some embodiments, the model to be trained includes a neural network model, and the step of training the model to be trained based on the multiple sets of first training data to obtain the stress determination model includes: training the neural network model based on the multiple sets of first training data to obtain neural network parameters; and obtaining the stress determination model based on the neural network parameters.

[0012] Secondly, embodiments of the present invention provide a pressure control device for an air knife, comprising: a data processing unit, configured to process working condition data through a pre-trained pressure determination model to obtain a target pressure, wherein the working condition data includes the current strip thickness, the current strip speed, the current average air knife distance, and the target zinc layer thickness; and a pressure control unit, configured to control the pressure of the air knife based on the target pressure, so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

[0013] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in any of the first aspects.

[0014] The one or more technical solutions provided in the embodiments of the present invention achieve at least the following technical effects or advantages:

[0015] This invention employs a pre-trained pressure determination model to process operating data and obtain a target pressure. The operating data includes the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness. Based on the target pressure, the air knife pressure is controlled to ensure that the deviation between the surface zinc layer thickness and the target zinc layer thickness is less than a preset first thickness deviation threshold. By accurately controlling the air knife pressure according to the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness, the pressure determination model can ensure that the deviation between the surface zinc layer thickness and the target zinc layer thickness is less than the preset first thickness deviation threshold, thus improving the rationality of the air knife pressure parameter settings. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart of the pressure control method for the air knife in an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram illustrating the training of a neural network model in an embodiment of the present invention;

[0019] Figure 3 This is a functional block diagram of the pressure control device for the air knife in an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0022] In this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0023] This invention provides a pressure control method for an air knife, as described in the following embodiment. Figure 1 As shown, the method includes the following steps S101 to S102:

[0024] S101: The working condition data is processed by a pre-trained pressure determination model to obtain the target pressure. The working condition data includes the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness.

[0025] It should be noted that the pressure control method for the air knife also includes: acquiring working condition data. Specifically, acquiring working condition data may include: acquiring the current upper surface operating side air knife distance, the current upper surface driving side air knife distance, the current lower surface operating side air knife distance, and the current lower surface driving side air knife distance of the strip, and taking the average of the current upper surface operating side air knife distance, the current upper surface driving side air knife distance, the current lower surface operating side air knife distance, and the current lower surface driving side air knife distance as the current average air knife distance.

[0026] It should be noted that a pressure determination model needs to be pre-trained before step S101. Therefore, the pressure control method for air knives may also include steps S1011 to S1012:

[0027] Step S1011: Obtain multiple sets of first training data. Each set of first training data includes air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness.

[0028] It should be noted that the first training data for each group is not limited to air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness. It may also include the galvanizing process of the strip, air knife holder angle, air knife height, and strip width, etc.

[0029] In some implementations, the method of step S1011 may include steps A to B:

[0030] Step A: Obtain multiple sets of second training data. Each set of second training data includes air knife pressure, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip.

[0031] In some implementations, step A can be achieved by filtering out abnormal data from the first historical production data to obtain second historical production data. Abnormal data includes null values, data exceeding process limits, and data with incorrect formats. The first historical production data includes air knife pressure, air knife height, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip at different times. Then, the second historical production data is deleted, specifically the upper and lower surface zinc layer thickness data of a predetermined length, to obtain third historical production data for data alignment. Based on the third historical production data, multiple sets of second training data are obtained.

[0032] It should be noted that by processing null data, data exceeding process limits, and data with incorrect formats, abnormal data is avoided from being used as training data, thereby improving the reliability of the stress determination model.

[0033] In some implementations, the preset length can be determined by taking the quotient of the distance between the air knife and the zinc layer thickness gauge and the strip speed as the preset length.

[0034] In some implementations, obtaining multiple sets of second training data based on third historical production data can be achieved by: dividing the third historical production data into multiple sets of production data according to a preset strip length; for each set of production data, if the set of production data meets preset conditions, the set of production data is used as a set of second training data among the multiple sets of second training data. The preset conditions are that the strip speed deviation is less than a preset speed deviation threshold, the air knife pressure deviation is less than a preset pressure deviation threshold, the air knife distance deviation is less than a preset distance deviation threshold, the air knife height deviation is less than a preset height deviation threshold, and the deviation between the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface of the strip is less than a preset second thickness deviation threshold.

[0035] Specifically, the strip length can be determined by multiplying the distance between the air knife and the zinc coating thickness gauge by a preset coefficient. The preset coefficient is a positive number greater than 1, such as 1.5, 2, or 3.2.

[0036] Specifically, determining whether the strip speed deviation is less than a preset speed deviation threshold can be done by dividing the strip into a first strip, a second strip, and a third strip, obtaining the first speed of the first strip, the second speed of the second strip, and the third speed of the third strip. If the deviation between the first speed and the second speed is less than the speed deviation threshold, or the deviation between the first speed and the third speed is less than the speed deviation threshold, then the strip speed deviation is determined to be less than the preset speed deviation threshold.

[0037] Specifically, determining whether the air knife pressure deviation is less than the preset pressure deviation threshold can be done by dividing the strip into a first strip, a second strip, and a third strip, obtaining the first air knife pressure of the first strip, the second air knife pressure of the second strip, and the third air knife pressure of the third strip. If the deviation between the first air knife pressure and the second air knife pressure is less than the pressure deviation threshold, or the deviation between the first air knife pressure and the third air knife pressure is less than the pressure deviation threshold, then the air knife pressure deviation is determined to be less than the preset pressure deviation threshold.

[0038] Specifically, determining whether the air knife distance deviation is less than a preset distance deviation threshold can be done by dividing the strip into a first strip, a second strip, and a third strip, obtaining the first average air knife distance of the first strip, the second average air knife distance of the second strip, and the third average air knife distance of the third strip. If the deviation between the first average air knife distance and the second average air knife distance is less than the distance deviation threshold, or the deviation between the first average air knife distance and the third average air knife distance is less than the distance deviation threshold, then the air knife distance deviation is determined to be less than the preset distance deviation threshold.

[0039] Specifically, determining whether the air knife height deviation is less than a preset height deviation threshold can be done by dividing the strip into a first strip, a second strip, and a third strip, obtaining the first air knife height of the first strip, the second air knife height of the second strip, and the third air knife height of the third strip. If the deviation between the first air knife height and the second air knife height is less than the height deviation threshold, or the deviation between the first air knife height and the third air knife height is less than the height deviation threshold, then the air knife height deviation is determined to be less than the preset height deviation threshold.

[0040] It should be noted that among multiple sets of production data, there may be data with excessively large deviations in strip speed or excessively large deviations in the thickness of the zinc layer on the upper and lower surfaces. These data indicate that the strip production line is under abnormal operating conditions. Using this data to train the pressure determination model would lead to inaccuracies and reduce its reliability. Therefore, only data that meets preset conditions is selected as training data to avoid using abnormal data and improve the reliability of the pressure determination model.

[0041] Step B: For each set of second training data in multiple sets of second training data, the average of the air knife distance on the upper surface operating side, the air knife distance on the upper surface driving side, the air knife distance on the lower surface operating side, and the air knife distance on the lower surface driving side is taken as the average air knife distance, and the average of the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface is taken as the average zinc layer thickness, so as to obtain multiple sets of first training data.

[0042] Step S1012: Train the model to be trained based on multiple sets of first training data to obtain a stress determination model.

[0043] In some implementations, the model to be trained includes a neural network model. Training the model to be trained based on multiple sets of first training data to obtain a stress determination model may include: training the neural network model based on multiple sets of first training data to obtain neural network parameters; and obtaining the stress determination model based on the neural network parameters.

[0044] Specifically, the neural network model is trained based on multiple sets of initial training data to obtain the neural network parameters, which can be: (Refer to...) Figure 2As shown, a neural network is designed using the PyTorch neural network framework in Python. It consists of a 4×500 Linear fully connected layer, 11 Block residual network layers, and a 500×1 Linear fully connected layer. Each Block contains a 500×500 Linear fully connected layer and a Sigmoid activation function. The Block output is equal to block(x) × (coefficient between 0 and 1) + Block input. The loss function is the MSE loss function, and the optimization function is the AdamW optimizer. The neural network model is trained to obtain the neural network parameters.

[0045] S102: Control the pressure of the air knife based on the target pressure so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

[0046] In some implementations, controlling the pressure of the air knife based on a target pressure may include: transmitting the target pressure to the first-level programmable logic controller (PLC) of the air knife via a TCP protocol; and the PLC controlling the pressure of the air knife according to the target pressure.

[0047] In some embodiments, after controlling the pressure of the air knife based on the target pressure, the method further includes: obtaining the current upper surface zinc layer thickness and the current lower surface zinc layer thickness of the strip; if the deviation between the current upper surface zinc layer thickness and the target zinc layer thickness is less than a first thickness deviation threshold, and the deviation between the current lower surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, determining that the deviation between the surface zinc layer thickness and the target zinc layer thickness of the strip is less than the first thickness deviation threshold.

[0048] It is understandable that obtaining the current zinc layer thickness on the upper and lower surfaces of the strip can be achieved by using a zinc layer thickness gauge.

[0049] It should be noted that the process continuously collects data on the strip thickness, target zinc layer thickness, distances between the air knife on the upper and lower surfaces of the strip (operating and driving sides), strip speed, air knife pressure, air knife height, and the zinc layer thicknesses on both the upper and lower surfaces measured by a zinc layer thickness gauge. This data is then processed using the aforementioned data processing and alignment algorithms to eliminate spatiotemporal inconsistencies between the zinc layer thickness gauge and air knife equipment data, and finally stored in a database. During production line maintenance, the newly accumulated sample data in the database is used to incrementally train the neural network, optimizing the model.

[0050] This invention employs a pre-trained pressure determination model to process operating data and obtain a target pressure. The operating data includes the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness. Based on the target pressure, the air knife pressure is controlled to ensure that the deviation between the surface zinc layer thickness and the target zinc layer thickness is less than a preset first thickness deviation threshold. By accurately controlling the air knife pressure according to the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness, the pressure determination model can ensure that the deviation between the surface zinc layer thickness and the target zinc layer thickness is less than the preset first thickness deviation threshold, thus improving the rationality of the air knife pressure parameter settings.

[0051] Based on the same inventive concept, and referring to Figure 3 As shown, this embodiment of the invention provides a pressure control device 10 for an air knife, comprising: a data processing unit 110, used to process working condition data through a pre-trained pressure determination model to obtain a target pressure, wherein the working condition data includes the current strip thickness, the current strip speed, the current average air knife distance, and the target zinc layer thickness; and a pressure control unit 120, used to control the pressure of the air knife based on the target pressure, so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

[0052] It is understood that the pressure control device 10 of the air knife also includes: a determination unit, used to obtain the current upper surface zinc layer thickness and the current lower surface zinc layer thickness of the strip steel; if the deviation between the current upper surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, and the deviation between the current lower surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, it is determined that the deviation between the surface zinc layer thickness of the strip steel and the target zinc layer thickness is less than the first thickness deviation threshold.

[0053] It is understood that the air knife pressure control device 10 also includes: a data acquisition unit for acquiring multiple sets of first training data, each set of first training data including air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness; and a training unit for training the model to be trained based on the multiple sets of first training data to obtain the pressure determination model.

[0054] It is understood that the data acquisition unit includes: an acquisition subunit, used to acquire multiple sets of second training data, each set of second training data including air knife pressure, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip; and a conversion subunit, used for each set of second training data in the multiple sets of second training data, taking the average of the air knife distance on the upper surface (operating side), the air knife distance on the upper surface (driving side), the air knife distance on the lower surface (operating side), and the lower surface (driving side) as the average air knife distance, and taking the average of the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface as the average zinc layer thickness, to obtain the multiple sets of first training data.

[0055] It is understood that the acquisition sub-unit includes: a filtering module, used to filter abnormal data from the first historical production data to obtain the second historical production data, wherein the abnormal data includes null data, data exceeding process limits, and data with incorrect format; the first historical production data includes air knife pressure, air knife height, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip at different times; a deletion module, used to delete upper surface zinc layer thickness data and lower surface zinc layer thickness data of a preset length from the second historical production data to obtain the third historical production data to achieve data alignment; and a historical data processing module, used to obtain the multiple sets of second training data based on the third historical production data.

[0056] Understandably, the historical data processing module is specifically used to: divide the third historical production data into multiple groups of production data according to a preset strip length; for each group of production data, if the group of production data meets preset conditions, use the group of production data as a set of second training data of the multiple groups of second training data, wherein the preset conditions are that the strip speed deviation is less than a preset speed deviation threshold, the air knife pressure deviation is less than a preset pressure deviation threshold, the air knife distance deviation is less than a preset distance deviation threshold, the air knife height deviation is less than a preset height deviation threshold, and the deviation between the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface of the strip is less than a preset second thickness deviation threshold.

[0057] It is understood that the pressure control unit 120 is specifically used to: transmit the target pressure to the first-level programmable logic controller of the air knife via TCP protocol; the first-level programmable logic controller controls the pressure of the air knife according to the target pressure.

[0058] It is understood that the training unit is specifically used for: training the neural network model based on the multiple sets of first training data to obtain neural network parameters; and obtaining the pressure determination model based on the neural network parameters.

[0059] It should be understood that further implementation details of the pressure control device 10 of the air knife in the embodiments of the present invention are described in the aforementioned pressure control method of the air knife, and will not be repeated here for the sake of brevity.

[0060] Based on the same inventive concept, embodiments of the present invention also provide an electronic device, such as... Figure 4 As shown, it includes a memory 404, a processor 402, and a computer program stored in the memory 404 and executable on the processor 402. The processor 402 executes the program to implement the steps described in any embodiment of the air knife pressure control method.

[0061] Among them, Figure 4 In this document, a bus architecture (represented by bus 400) is used. Bus 400 may include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 402 and memory represented by memory 404. Bus 400 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 405 provides an interface between bus 400 and receiver 401 and transmitter 403. Receiver 401 and transmitter 403 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 402 is responsible for managing bus 400 and general processing, while memory 404 can be used to store data used by processor 402 during operation.

[0062] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and embodiments are within the scope and spirit of this invention and the appended claims. For example, due to the nature of software, the functions described above can be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination thereof. Furthermore, the functional units can be integrated into a single processing unit, or each unit can exist physically separately, or two or more units can be integrated into a single unit.

[0063] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0064] The units described as separate components may or may not be physically separate. Similarly, the components of the control device may or may not be physical units; they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0065] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or 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 capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0066] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A method for controlling the pressure of an air knife, characterized in that, include: The pressure determination model is processed using pre-trained pressure determination model to obtain the target pressure from working condition data, including current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness. Multiple sets of first training data are acquired, each set including air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness. The model to be trained is then trained based on these multiple sets of first training data to obtain the pressure determination model. Acquiring the multiple sets of first training data includes acquiring multiple sets of second training data, each set including air knife pressure, strip thickness, strip speed, and strip upper surface operation. The distances of the side air knife, the distance of the driving side air knife on the upper surface of the strip, the distance of the operating side air knife on the lower surface of the strip, the distance of the driving side air knife on the lower surface of the strip, the zinc layer thickness on the upper surface of the strip, and the zinc layer thickness on the lower surface of the strip are used to obtain the multiple sets of first training data. For each set of second training data, the average of the distances of the operating side air knife on the upper surface, the driving side air knife on the upper surface, the operating side air knife on the lower surface, and the driving side air knife on the lower surface is used as the average air knife distance. The average of the zinc layer thicknesses on the upper and lower surfaces is used as the average zinc layer thickness. The acquisition of the multiple sets of second training data includes filtering out abnormal data from the first historical production data to obtain... The second historical production data includes null data, data exceeding process limits, and data with incorrect formats. The first historical production data includes air knife pressure, air knife height, strip thickness, strip speed, air knife distance on the upper surface of the strip (operating side), air knife distance on the upper surface of the strip (driving side), air knife distance on the lower surface of the strip (operating side), air knife distance on the lower surface of the strip (driving side), zinc layer thickness on the upper surface of the strip, and zinc layer thickness on the lower surface of the strip at different times. The second historical production data is then deleted by deleting the upper and lower surface zinc layer thickness data of a preset length to obtain the third historical production data, thus achieving data alignment. Based on the third historical production data, the multiple sets of second training data are obtained. The process of obtaining the multiple sets of second training data based on the third historical production data includes: dividing the third historical production data into multiple sets of production data according to a preset strip length; for each set of production data, if the set of production data meets a preset condition, using the set of production data as a set of second training data for the multiple sets of second training data, wherein the preset condition is that the strip speed deviation is less than a preset speed deviation threshold, the air knife pressure deviation is less than a preset pressure deviation threshold, the air knife distance deviation is less than a preset distance deviation threshold, the air knife height deviation is less than a preset height deviation threshold, and the deviation between the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface of the strip is less than a preset second thickness deviation threshold; The pressure of the air knife is controlled based on the target pressure so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

2. The pressure control method for an air knife according to claim 1, characterized in that, Following the control of the air knife pressure based on the target pressure, the method further includes: Obtain the current upper surface zinc layer thickness and the current lower surface zinc layer thickness of the strip steel; If the deviation between the current upper surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, and the deviation between the current lower surface zinc layer thickness and the target zinc layer thickness is less than the first thickness deviation threshold, it is determined that the deviation between the surface zinc layer thickness and the target zinc layer thickness of the strip is less than the first thickness deviation threshold.

3. The pressure control method for an air knife according to claim 1, characterized in that, The pressure control of the air knife based on the target pressure includes: The target pressure is transmitted to the first-level programmable logic controller of the air knife via TCP protocol; The first-level programmable logic controller controls the pressure of the air knife according to the target pressure.

4. The pressure control method for an air knife according to claim 1, characterized in that, The model to be trained includes a neural network model, and the step of training the model to be trained based on the multiple sets of first training data to obtain the stress determination model includes: The neural network model is trained based on the multiple sets of first training data to obtain neural network parameters; The pressure determination model is obtained based on the neural network parameters.

5. A pressure control device for an air knife, characterized in that, include: A data processing unit is used to process working condition data through a pre-trained pressure determination model to obtain the target pressure. The working condition data includes the current strip thickness, current strip speed, current average air knife distance, and target zinc layer thickness. The unit acquires multiple sets of first training data, each set including air knife pressure, strip thickness, strip speed, average air knife distance, and average zinc layer thickness. Based on these multiple sets of first training data, the unit trains the model to be trained to obtain the pressure determination model. Acquiring the multiple sets of first training data includes acquiring multiple sets of second training data, each set including air knife pressure, strip thickness, strip speed, and average zinc layer thickness. The distances of the upper surface operating side air knife, the upper surface driving side air knife, the lower surface operating side air knife, the lower surface driving side air knife, the upper surface zinc layer thickness, and the lower surface zinc layer thickness of the strip are used to obtain the multiple sets of first training data. For each set of second training data, the average of the upper surface operating side air knife distance, the upper surface driving side air knife distance, the lower surface operating side air knife distance, and the lower surface driving side air knife distance is used as the average air knife distance. The average of the upper surface zinc layer thickness and the lower surface zinc layer thickness is used as the average zinc layer thickness to obtain the multiple sets of first training data. The acquisition of multiple sets of second training data includes filtering out abnormal data from the first historical production data. The process involves obtaining second historical production data, where abnormal data includes null values, data exceeding process limits, and data with incorrect formats. The first historical production data includes air knife pressure, air knife height, strip thickness, strip speed, air knife distance on the upper surface (operating side), air knife distance on the upper surface (driving side), air knife distance on the lower surface (operating side), air knife distance on the lower surface (driving side), zinc layer thickness on the upper surface, and zinc layer thickness on the lower surface of the strip at different times. The second historical production data is then deleted, with preset lengths of upper and lower surface zinc layer thickness data, to obtain third historical production data for data alignment. Based on the third historical production data, the multiple sets of second training data are obtained. The step of obtaining the multiple sets of second training data based on the third historical production data includes: dividing the third historical production data into multiple sets of production data according to a preset strip length; for each set of production data in the multiple sets of production data, if the set of production data meets a preset condition, the set of production data is used as a set of second training data of the multiple sets of second training data. The preset condition is that the strip speed deviation is less than a preset speed deviation threshold, the air knife pressure deviation is less than a preset pressure deviation threshold, the air knife distance deviation is less than a preset distance deviation threshold, the air knife height deviation is less than a preset height deviation threshold, and the deviation between the zinc layer thickness on the upper surface and the zinc layer thickness on the lower surface of the strip is less than a preset second thickness deviation threshold. The pressure control unit is used to control the pressure of the air knife based on the target pressure, so that the deviation between the surface zinc layer thickness of the strip and the target zinc layer thickness is less than a preset first thickness deviation threshold.

6. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-4.

Images