Hot galvanizing control method, device, equipment and medium

Abstract

The invention discloses a hot galvanizing control method, device, equipment and medium, under the condition that a production line control system of a hot galvanizing production line receives target order information, the production line control system generates steel coil set value request information and sends the steel coil set value request information to a pre-trained plating layer distribution control model; the plating layer distribution control model outputs target control parameters matched with target order information according to the target order information in the steel coil set value request information, and sends the target control parameters to a production line control system; and the production line control system monitors welding seams of continuous strip steel on the hot galvanizing production line, and under the condition that the production line control system monitors the strip steel welding seams corresponding to the target order information, the production line control system adjusts control parameters of the hot galvanizing production line to target control parameters. The control precision of the hot galvanizing production line is improved, the consistency and uniformity of the galvanizing thickness of the hot galvanizing production line are improved, and the production quality of the hot galvanizing production line is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hot-dip galvanizing, and in particular to a hot-dip galvanizing control method, device, equipment and medium. Background Art

[0002] Cold-dip galvanizing is a complex process involving temperature control of the strip and the zinc bath, protective atmosphere control, roll system status and adjustment, air knife adjustment, and other process controls. Multiple control points and environmental factors directly or indirectly influence the coating thickness distribution throughout the entire process. Therefore, precise control is essential, or indirect measures must be taken to mitigate these adverse effects.

[0003] In the related art, the control parameters of the hot-dip galvanizing process are mainly adjusted based on manual experience to improve the thickness distribution of the coating. However, this adjustment method is not ideal. Therefore, how to automatically adjust the control parameters of the hot-dip galvanizing process to improve the thickness uniformity of the hot-dip galvanized coating is an urgent problem that needs to be solved. Summary of the Invention

[0004] The embodiments of the present application provide a hot-dip galvanizing control method, device, equipment and medium, which solves the technical problem in the prior art that the control parameters in the hot-dip galvanizing process are mainly adjusted by manual experience to improve the thickness distribution of the coating, but the adjustment effect of this method is not ideal. The embodiment of the present application achieves the technical effect of automatically adjusting the control parameters in the hot-dip galvanizing process to improve the uniformity of the thickness distribution of the hot-dip galvanized coating.

[0005] In a first aspect, the present application provides a hot-dip galvanizing control method, the method comprising:

[0006] When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system generates a steel coil setting value request message and sends it to a pre-trained coating distribution control model; the steel coil setting value request message includes the target order information;

[0007] The coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters matching the target order information according to the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system;

[0008] The production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

[0009] Furthermore, when the production line control system of the hot-dip galvanizing production line receives the target order information, the production line control system generates a steel coil set value request information and sends it to the pre-trained coating distribution control model, including:

[0010] When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system determines a pre-trained target coating distribution control model corresponding to the target order information according to the target coating thickness in the target order information;

[0011] The production line control system generates the steel coil setting value request information according to the target order information, and sends it to the target coating distribution control model that corresponds to the target order information and is pre-trained.

[0012] Furthermore, before the production line control system of the hot-dip galvanizing production line receives the target order information, the method further includes:

[0013] Obtaining original historical production data of the hot-dip galvanizing production line, wherein the original historical production data includes historical order information and historical control parameters;

[0014] Performing data cleaning on the original historical production data to obtain initial historical production data;

[0015] Performing data alignment on corresponding positions of the hot-dip galvanizing production line according to the initial historical production data to obtain target historical production data;

[0016] Classifying the target historical production data according to different target coating thicknesses corresponding to the historical order information to obtain historical production sub-data corresponding to each different target coating thickness;

[0017] Based on the historical production sub-data corresponding to each different target coating thickness, the original coating distribution control model corresponding to each different target coating thickness is trained to obtain the coating distribution control model corresponding to each different target coating thickness.

[0018] Furthermore, the data cleaning of the original historical production data to obtain initial historical production data includes:

[0019] Abnormal data and front and rear strip transition process data in the original historical production data are deleted, and incomplete data in the original historical production data are supplemented to obtain the initial historical production data.

[0020] Furthermore, after obtaining the pre-trained coating distribution control model, during the production process of the hot-dip galvanizing production line, the method further includes:

[0021] Obtaining actual order information and actual control parameters corresponding to various target coating thicknesses during the production process of the hot-dip galvanizing production line;

[0022] Whenever the data volume of the actual order information and the actual control parameters corresponding to any target coating thickness meets the preset requirements, the actual order information and the actual control parameters that meet the preset requirements are used to update and train the coating distribution control model corresponding to the target coating thickness that meets the preset requirements, and obtain the updated coating distribution control model corresponding to the target coating thickness.

[0023] Furthermore, after obtaining the pre-trained coating distribution control model, the method further includes:

[0024] Obtaining historical control parameters and historical order information corresponding to the target coating thickness to be studied in the hot-dip galvanizing production line;

[0025] Inputting the historical control parameters corresponding to the target coating thickness to be studied into the coating distribution control model corresponding to the target coating thickness to be studied, to obtain predicted order information corresponding to the target coating thickness to be studied;

[0026] According to the difference between the historical order information and the predicted order information, the degree of influence of the historical control parameters corresponding to the target coating thickness to be studied on the hot-dip galvanized coating thickness distribution is analyzed.

[0027] Furthermore, the target control parameter includes at least one of the temperature of the zinc liquid in the zinc pot in the hot-dip galvanizing production line and an air knife control parameter.

[0028] In a second aspect, the present application provides a hot-dip galvanizing control device, the device comprising:

[0029] An order processing module is configured to generate steel coil setting value request information and send it to a pre-trained coating distribution control model when a production line control system of a hot-dip galvanizing production line receives target order information; the steel coil setting value request information includes the target order information;

[0030] a control parameter determination module, configured for the coating distribution control model to receive and respond to the steel pipe set value request information, output target control parameters matching the target order information according to the target order information in the steel coil set value request information, and send the target control parameters to the production line control system;

[0031] The galvanizing control module is used for the production line control system to monitor the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

[0032] In a third aspect, the present application provides an electronic device, comprising:

[0033] processor;

[0034] a memory for storing instructions executable by the processor;

[0035] Wherein, the processor is configured to execute to implement a hot-dip galvanizing control method provided in the first aspect.

[0036] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a hot-dip galvanizing control method as provided in the first aspect.

[0037] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0038] In an embodiment of the present application, when the production line control system of a hot-dip galvanizing production line receives target order information, the production line control system generates steel coil setting value request information and sends it to a pre-trained coating distribution control model; the coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters matching the target order information based on the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system; the production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line, and when the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters. It can be seen that the embodiment of the present application uses big data analysis and modeling technology, which can analyze and process the target order information in a short time, and then output the corresponding relevant control parameters of the hot-dip galvanizing production line, improve the control accuracy of the hot-dip galvanizing production line, avoid the poor production quality of the hot-dip galvanizing production line caused by human experience factors, improve the consistency and uniformity of the galvanizing thickness of the hot-dip galvanizing production line, and improve the production quality of the hot-dip galvanizing production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 A schematic flow chart of a hot-dip galvanizing control method provided in an embodiment of the present application;

[0041] Figure 2 This is a schematic diagram of the operation of the hot-dip galvanizing production line provided in an embodiment of the present application;

[0042] Figure 3 A flow chart of the coating distribution prediction model training provided in the embodiment of the present application;

[0043] Figure 4 A flow chart showing the prediction of control parameters for the hot-dip galvanizing process provided in an embodiment of the present application;

[0044] Figure 5 This is a flowchart of the incremental self-learning of the hot-dip galvanizing coating distribution prediction model provided in the embodiment of the present application;

[0045] Figure 6 A flow chart for predicting the distribution of hot-dip galvanized coatings provided in an embodiment of the present application;

[0046] Figure 7 The contribution of process parameters of the hot-dip galvanizing process provided in the embodiment of the present application;

[0047] Figure 8 A coating distribution prediction diagram for the hot-dip galvanizing process provided in an embodiment of the present application;

[0048] Figure 9 A flowchart of the hot-dip galvanizing process parameter and coating distribution prediction process middleware provided in an embodiment of the present application;

[0049] Figure 10 A schematic structural diagram of a hot-dip galvanizing control device provided in an embodiment of the present application;

[0050] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The embodiment of the present application provides a hot-dip galvanizing control method, which solves the technical problem that in the prior art, the control parameters in the hot-dip galvanizing process are mainly adjusted by manual experience to improve the thickness distribution of the coating, but the adjustment effect of this method is not ideal.

[0052] The technical solution of the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0053] In an embodiment of the present application, when the production line control system of a hot-dip galvanizing production line receives target order information, the production line control system generates steel coil setting value request information and sends it to a pre-trained coating distribution control model; the coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters matching the target order information based on the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system; the production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line, and when the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters. It can be seen that the embodiment of the present application uses big data analysis and modeling technology, which can analyze and process the target order information in a short time, and then output the corresponding relevant control parameters of the hot-dip galvanizing production line, improve the control accuracy of the hot-dip galvanizing production line, avoid the poor production quality of the hot-dip galvanizing production line caused by human experience factors, improve the consistency and uniformity of the galvanizing thickness of the hot-dip galvanizing production line, and improve the production quality of the hot-dip galvanizing production line.

[0054] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0055] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0056] Cold-dip galvanizing is a complex process involving temperature control of the strip and the zinc bath, protective atmosphere control, roll system status and adjustment, air knife adjustment, and other process controls. Multiple control points and environmental factors directly or indirectly influence the coating thickness distribution throughout the entire process. Therefore, precise control is essential, or indirect measures must be taken to mitigate these adverse effects.

[0057] In related technologies, fluid mechanics is often used to analyze the physical changes in the air knife jet flow and the factors affecting the coating thickness during the galvanizing process, and to establish a coating thickness mechanism model to improve the uniformity of the coating thickness. However, in actual production, in addition to the control parameters of the air knife, the influence of environmental factors and equipment status during the hot-dip galvanizing production process is also crucial. These often require manual experience to compensate for and are most easily overlooked in theoretical research. For example, the air knife's gas spray does not have a heating device, and the air knife's effect on blowing away the zinc liquid on the strip will be affected differently at different ambient temperatures. For example, in winter, the low-temperature zinc liquid has poor fluidity, resulting in uneven coating thickness, while in summer, the high-temperature zinc liquid has excessive fluidity, resulting in uneven coating thickness.

[0058] The current mainstream technical solutions are basically centered around air knives, based on the fixed basic processes such as the strip entering the pot temperature, the zinc liquid temperature, and the zinc liquid composition. Specifically, closed-loop control is achieved by changing the shape of the air knife lip, adding edge baffles, and accurately positioning the air knife to achieve control of the coating distribution. However, the air knife position, airflow pressure, etc. need to be manually set by the operator, which means that these operations currently rely heavily on the operator's accumulated production experience, resulting in a certain lag and variability in the control parameters, resulting in poor product quality stability. In addition, manual control cannot effectively quantify the contribution of process control parameters, and the ability to pre-control the coating distribution is insufficient. The design of new product control solutions relies heavily on the personal experience of engineers, resulting in a low test success rate.

[0059] Therefore, how to automatically adjust the control parameters in the hot-dip galvanizing process to improve the thickness distribution uniformity of the hot-dip galvanizing coating is an urgent problem that needs to be solved.

[0060] In order to solve the above problems, the embodiment of the present application provides a hot dip galvanizing control method, which includes steps S11 to S13. Figure 1 shown.

[0061] Step S11, when the production line control system of the hot-dip galvanizing production line receives the target order information, the production line control system generates a steel coil setting value request information and sends it to the pre-trained coating distribution control model; the steel coil setting value request information includes the target order information.

[0062] In step S12, the coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters that match the target order information according to the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system.

[0063] In step S13, the production line control system monitors the welds of the continuous steel strips on the hot-dip galvanizing production line. When the production line control system detects the steel strip welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the steel strips corresponding to the target order information according to the target control parameters.

[0064] A hot-dip galvanizing control method provided in an embodiment of the present application can be implemented by a controller such as a host computer of a hot-dip galvanizing production line.

[0065] Regarding step S11, when the production line control system of the hot-dip galvanizing production line receives the target order information, the production line control system generates steel coil setting value request information and sends it to the pre-trained coating distribution control model; the steel coil setting value request information includes the target order information.

[0066] Hot dip galvanizing production line is usually a continuous production line. Figure 2 The following is a schematic diagram of the operation of a hot-dip galvanizing production line. The hot-dip galvanizing production line mainly includes a zinc pot, a sinking roller, an air knife, and a transmission system that controls the transportation of strip steel on the production line. It should be noted that Figure 2 The transmission system that controls the transport of the strip on the production line is not shown. Figure 2 In this process, a sinking roller is placed in a zinc pot. The strip enters the zinc pot from the left side of the roller, wraps around the roller, and exits the zinc pot. At least two sets of air knives are placed on either side of the strip exiting the zinc pot. After the strip enters the zinc pot, the strip surface is coated with molten zinc. The air knives blow the molten zinc away from the strip surface, ensuring that the molten zinc evenly covers the strip surface.

[0067] The strip steel that needs to be processed is usually rolled up, and the ends of two adjacent rolls are welded together before being passed through a zinc pot for hot-dip galvanizing. Therefore, hot-dip galvanizing production lines usually operate continuously.

[0068] If a new order is received while the hot-dip galvanizing line is producing the previous order, the target order information for the new order is entered into the production line control system. This target order information includes, but is not limited to, the thickness and width of the strip to be processed, the thickness of the zinc coating on the strip, and the overall thickness of the strip after galvanizing.

[0069] When a production control system of a hot-dip galvanizing line receives target order information, it generates coil setpoint request information based on the target order information. The coil setpoint request information includes the target order information. The production control system sends the coil setpoint request information to a pre-trained coating distribution control model, enabling the coating distribution control model to calculate hot-dip galvanizing process control parameters that match the target order information.

[0070] The pre-trained coating distribution control model is obtained before the production line control system of the hot-dip galvanizing production line receives the target order information. The coating distribution control model training method includes steps S111 to S115. The coating distribution control model can be a neural network model.

[0071] Step S111: acquiring original historical production data of the hot-dip galvanizing production line, wherein the original historical production data includes historical order information and historical control parameters.

[0072] Step S112: performing data cleaning on the original historical production data to obtain initial historical production data.

[0073] Step S113: aligning data at corresponding positions on the hot-dip galvanizing production line according to the initial historical production data to obtain target historical production data.

[0074] Step S114 , classifying the target historical production data according to the different target coating thicknesses corresponding to the historical order information, and obtaining historical production sub-data corresponding to each different target coating thickness.

[0075] Step S115 , based on the historical production sub-data corresponding to each different target coating thickness, the original coating distribution control model corresponding to each different target coating thickness is trained to obtain the coating distribution control model corresponding to each different target coating thickness.

[0076] Regarding step S111, the original historical production data of the hot-dip galvanizing production line in the historical production process is obtained from the relevant storage device. The original historical production data includes historical order information and historical control parameters. The historical order information includes but is not limited to the thickness and width of the strip to be processed, the thickness of the zinc layer galvanized on the strip, the overall thickness of the strip after galvanizing, etc. The historical control parameters include but are not limited to the transportation speed of the strip, the control parameters of the sinking roller, the temperature data of the zinc liquid in the zinc pot, the ambient temperature, the control parameters related to the air knife, etc. The control parameters related to the air knife may include the opening distance of the air knife lip, the straight-line distance between the air knife lip and the galvanized strip, the distance between the air knife lip and the surface of the zinc liquid in the zinc pot, the size of the air pressure of the air knife, etc. In addition, the original historical production data may also include the galvanizing quality of the hot-dip galvanized finished product after production, such as the actual galvanizing thickness, the actual galvanizing surface quality, etc.

[0077] Regarding step S112, the original historical production data is preprocessed to obtain initial historical production data. For example, the abnormal data and the front and rear strip transition process data in the original historical production data are deleted, and the incomplete data in the original historical production data are supplemented to obtain the initial historical production data. On this basis, the original historical production data can also be further screened according to the galvanizing quality of the hot-dip galvanized finished product. For example, the historical order information and historical control parameters corresponding to the hot-dip galvanized finished product with better galvanizing quality are screened out as the initial historical production data. The quality of the initial historical production data obtained in this way is better, and thus the control parameters output by the coating distribution control model obtained by the final training are more accurate, so as to further improve the uniformity of the galvanizing thickness of the hot-dip galvanized product and improve the production quality of the hot-dip galvanized product.

[0078] Regarding step S113, each piece of data in the initial historical production data may be collected at a preset time frequency. However, the transport speed of the strip steel on the hot-dip galvanizing production line may vary, sometimes fast and sometimes slow. Although the chronological order of the initial historical production data is regular, the different strip steel transport speeds on the hot-dip galvanizing production line lead to deviations in the relationship between the initial historical production data and the position of the hot-dip galvanizing production line. Therefore, data alignment can be performed according to the corresponding position of the initial historical production data on the hot-dip galvanizing production line to obtain the target historical production data.

[0079] For example, during a specific historical production run on a hot-dip galvanizing line, the initial historical production data for the head region (0-100 meters), middle region (100-900 meters), and tail region (900-1000 meters) of the fifth strip produced on the line are Groups A1, A2, and A3, respectively. The length of the seventh strip differs significantly from that of the fifth, so the initial historical production data for the head region (0-100 meters), middle region (100-2000 meters), and tail region (2000-2100 meters) of the seventh strip produced on the line are Groups B1, B2, and B3, respectively. If time patterns are used, the initial historical production data for the fifth and seventh strips are independent of each other, making it impossible to determine the correlation between the production data of different strips. Therefore, this application aligns the initial historical production data at corresponding positions on the hot-dip galvanizing production line, that is, the initial historical production data of the head, middle, and tail regions of different strips are aligned, that is, Group A1 corresponds to Group B1, Group A2 corresponds to Group B2, and Group A3 corresponds to Group B3. Since the production data of the head and tail of the strip have a large impact on the quality of hot-dip galvanizing, they can be removed, and only the production data of the middle region of the strip is retained as the target historical production data.

[0080] Regarding step S114, after obtaining the target historical production data, the target historical production data can be classified according to the different target coating thicknesses in the historical order information. For example, there are 7 target coating thicknesses corresponding to the target historical production data, namely 10g / m 2 , 15g / m 2 , 20g / m 2 , 22g / m 2 , 30g / m 2 , 40g / m 2 , 50g / m 2 Then, the target historical production data corresponding to the seven target coating thicknesses are grouped to obtain seven different groups of historical production sub-data, each group of which corresponds to the same target coating thickness.

[0081] In step S115, the original coating distribution control model is trained using the historical production sub-data corresponding to each target coating thickness as training samples, thereby obtaining a coating distribution control model corresponding to the target coating thickness. For example, a convolutional neural network model structure is constructed to obtain the original coating distribution control model. The hot-dip galvanizing process data is substituted into the original coating distribution control model. The convolutional and pooling layers extract feature information related to the coating thickness, and regression prediction is performed through the fully connected layer to obtain the final coating distribution control model.

[0082] For example, the above mentioned 7 target coating thicknesses are 10g / m 2 , 15g / m 2 , 20g / m 2 , 22g / m 2 , 30g / m 2 , 40g / m 2 , 50g / m 2 The corresponding historical sub-data were used as training samples for model training, and 7 independently trained coating distribution control models were obtained. Each trained coating distribution control model corresponds to a different target coating thickness.

[0083] On the basis that different target coating thicknesses correspond to different coating distribution control models, step S11 can be further explained as follows:

[0084] When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system determines a pre-trained target coating distribution control model corresponding to the target order information according to the target coating thickness in the target order information;

[0085] The production line control system generates the steel coil setting value request information according to the target order information, and sends it to the target coating distribution control model that corresponds to the target order information and is pre-trained.

[0086] That is to say, after obtaining the target order information corresponding to the new order, it is possible to determine which coating distribution control model to use for the calculation of control parameters based on the target coating thickness in the target order information, and then send the corresponding steel coil setting value request information to the corresponding coating distribution control model for the calculation of control parameters. For example, the target coating thickness corresponding to a target order information is 22g / m 2 , then 22g / m 2 The corresponding target coating distribution control model processes the steel coil set value request information and outputs control parameters corresponding to the current target order information.

[0087] Regarding step S12, the coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters that match the target order information according to the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system.

[0088] The coating distribution control model outputs the target control parameters corresponding to the current target coating thickness according to the target order information in the steel coil set value request information, and sends them to the production line control system for use.

[0089] Target control parameters include, but are not limited to, the transport speed of the steel strip, the control parameters of the sinking roller, the temperature of the zinc bath, the ambient temperature, and control parameters related to the air knife. Control parameters related to the air knife may include the opening distance of the air knife lip, the linear distance between the air knife lip and the galvanized steel strip, the distance between the air knife lip and the surface of the zinc bath, and the air pressure of the air knife.

[0090] For example, the target control parameter may include at least one of the temperature of the zinc liquid in the zinc pot in the hot-dip galvanizing production line and an air knife control parameter.

[0091] Regarding step S13, the production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

[0092] Steps S11 and S12 are all executed before the hot-dip galvanizing line produces the target order information. If the hot-dip galvanizing line is a continuous production line, it can also be said that they are executed during the process of the hot-dip galvanizing line producing the product of the previous order.

[0093] The production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line. When the weld between the last strip steel of the previous order and the first strip steel of the current target order is monitored, that is, when the production line control system monitors the strip steel weld corresponding to the target order information, the production line control system adjusts the current actual control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

[0094] To summarize, in the embodiment of the present application, when the production line control system of the hot-dip galvanizing production line receives target order information, the production line control system generates steel coil setting value request information and sends it to a pre-trained coating distribution control model; the coating distribution control model receives and responds to the steel pipe setting value request information, and outputs target control parameters that match the target order information according to the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system; the production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line, and when the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters. It can be seen that the embodiment of the present application uses big data analysis and modeling technology, which can analyze and process the target order information in a short time, and then output the corresponding relevant control parameters of the hot-dip galvanizing production line, improve the control accuracy of the hot-dip galvanizing production line, avoid the poor production quality of the hot-dip galvanizing production line caused by human experience factors, improve the consistency and uniformity of the galvanizing thickness of the hot-dip galvanizing production line, and improve the production quality of the hot-dip galvanizing production line.

[0095] Furthermore, based on the above solution, the embodiment of the present application also provides the following optimization solution.

[0096] After obtaining the pre-trained coating distribution control model, during the production process of the hot-dip galvanizing production line, the method further includes steps S21 and S22.

[0097] Step S21, obtaining actual order information and actual control parameters corresponding to various target coating thicknesses during the production process of the hot-dip galvanizing production line;

[0098] Step S22: Whenever the data volume of the actual order information and the actual control parameters corresponding to any target coating thickness meets the preset requirements, the coating distribution control model corresponding to the target coating thickness that meets the preset requirements is updated and trained using the actual order information and the actual control parameters that meet the preset requirements to obtain the updated coating distribution control model corresponding to the target coating thickness.

[0099] Regarding step S21, during the hot-dip galvanizing production line, it is necessary to record order information and control parameters and other data during the production process. Based on the aforementioned different target coating thicknesses corresponding to different coating distribution control models in the embodiment of the present application, the embodiment of the present application also records order information and control parameters and other data during the production process according to different target coating thicknesses.

[0100] Regarding step S22, the target coating thickness corresponding to the current strip is determined based on the actual order information, and then the data volume of the actual control parameters stored in the actual production process for each target coating thickness is monitored. When the data volume meets the preset requirements, for example, when the data volume exceeds 1,000 pieces and the 1,000 pieces of data correspond to more than 10 strips, it is considered that the data volume meets the preset requirements, and the coating distribution control model corresponding to the target coating thickness is updated and trained according to the currently collected data volume.

[0101] In other words, steps S21 and S22 are methods for updating the coating distribution control model during production, which can be referred to as an online mode. Steps S111 and S115 are methods for initially training the coating distribution control model using historical production data, which can be referred to as an offline mode. Both methods are methods for training the coating distribution control model.

[0102] It can be seen that the embodiment of the present application uses production process big data to train a cold-based hot-dip galvanized sheet coating lateral thickness distribution prediction and analysis model, so as to predict the coating lateral thickness distribution according to the control parameter setting value and environmental variables; determine the control parameter setting value according to the target coating distribution prediction; build a hot-dip galvanizing process and coating distribution prediction process, connect to the galvanizing process control system, realize the budgeting and self-learning of control parameters, improve the control accuracy of the hot-dip galvanizing production line, avoid the poor production quality of the hot-dip galvanizing production line caused by human experience factors, improve the consistency and uniformity of the galvanizing thickness of the hot-dip galvanizing production line, and improve the production quality of the hot-dip galvanizing production line.

[0103] According to the aforementioned solution, target order information can be input into a pre-trained coating distribution control model to obtain corresponding target control parameters. These target control parameters can then be used to control the hot-dip galvanizing production line during production, thereby improving the production quality and stability of the hot-dip galvanizing production line. Alternatively, the following solution can be included: after obtaining the pre-trained coating distribution control model, the method further includes steps S31-S33.

[0104] Step S31, obtaining historical control parameters and historical order information corresponding to the target coating thickness to be studied in the hot-dip galvanizing production line;

[0105] Step S32, inputting the historical control parameters corresponding to the target coating thickness to be studied into the coating distribution control model corresponding to the target coating thickness to be studied, to obtain predicted order information corresponding to the target coating thickness to be studied;

[0106] Step S33: analyzing the influence of the historical control parameters corresponding to the target coating thickness to be studied on the hot-dip galvanizing coating thickness distribution according to the difference between the historical order information and the predicted order information.

[0107] Steps S31 to S33 are mainly used to assist engineers in studying the relevant control rules of the hot-dip galvanizing production line during the production process. When new products need to be produced, steps S31 to S33 can be used to simulate the process to provide a reference for the production control of the new products. That is, the trial stage of the new products can be simulated, shortening the production control R&D cycle of the new products, while also ensuring good production quality of the new products during the R&D process.

[0108] In step S31, a target old product that is closest to the new product is selected from various old products previously produced in the hot-dip galvanizing line. The target coating thickness corresponding to the target old product is used as the target coating thickness to be studied. Then, historical control parameters and historical order information corresponding to the target coating thickness to be studied in the hot-dip galvanizing line are obtained.

[0109] Regarding step S32, the predicted order information is derived by the coating distribution control model based on historical control parameters. The historical order information refers to the actual order information corresponding to the hot-dip galvanizing production line during actual production.

[0110] Regarding step S33, the historical order information is compared with the predicted order information to obtain the difference between the two, and then the degree of influence of the historical control parameters corresponding to the target coating thickness to be studied on the hot-dip galvanized coating thickness distribution is determined, so that engineers can fine-tune the control parameters of the new product according to the degree of influence, thereby assisting engineers in completing the control strategy of the new product.

[0111] In order to further illustrate the solution provided in the embodiments of the present application, a specific example is now provided.

[0112] like Figure 3 As shown, the product raw material information, order information, and hot-dip galvanizing process production data are analyzed and cleaned, specifically including extracting normal production process data, deleting the front and rear strip transition process data and outliers, and normalizing the data, such as aligning the data, to improve the quality and consistency of sample data.

[0113] Based on the key parameter of target coating thickness, the sample data is classified and processed. A convolutional neural network model structure is constructed, and the hot-dip galvanizing process data is substituted into it. Through its convolutional and pooling layers, feature information related to coating thickness is extracted. Regression prediction is then performed through the fully connected layer to obtain a trained coating distribution control model.

[0114] like Figure 4 As shown, after receiving the new order information, the original product information and target coating information are extracted, the model group to which the product with the target coating thickness corresponding to the current order belongs is determined, and the corresponding coating distribution control model is loaded according to the target coating thickness corresponding to the current order.

[0115] During the operation of the hot-dip galvanizing production line, it is also possible to load the trained model and gradually introduce new data to update the model to achieve incremental self-learning of the model, such as Figure 5 shown. Figure 5 The "greater than 100" in the data refers to data greater than 100 meters. This means that the head of the strip is removed, and only the data from the middle area after the head is retained. A grouping loop is started. If the data volume reaches 1000 and exceeds 10 rolls, the hot-dip galvanized coating distribution prediction model for this group is trained. If the data volume is less than 1000 or less than 10 rolls, the next loop is entered.

[0116] like Figure 6 As shown in the figure, the contribution of the characteristic quantities in each model under different process parameters and the change in coating distribution after adjusting the control parameters are analyzed. Through this detailed analysis, the control status of the historical production process can be effectively evaluated, the control points of each product can be accurately found, the control parameters can be optimized, and the precise control of coating distribution can be achieved. Figure 7 and Figure 8 The figure shows the contribution of hot dip galvanizing process parameters and the distribution prediction of coating. Figure 7 It can be seen that the distance between the measuring point on the lower surface and the edge has the greatest impact.

[0117] like Figure 9As shown in the figure, in the actual production process, the communication between the production line control system of the hot-dip galvanizing production line and the coating distribution control model is mainly realized by using the message queue as the middleware, coupling the production line control system process with the hot-dip galvanizing process parameter coating distribution prediction process. This minimizes the transformation of the production line control system and ensures the independent operation of the production line control system and the coating distribution control model. At the same time, it can also realize data communication between the production line control system and the coating distribution control model. Figure 9 The MTR in it refers to Material Test Report, and its full English name is Material Test Report. ZMO refers to Zinc Metering Optimization, and its full English name is Zinc Metering Optimization.

[0118] In summary, the embodiments of the present application improve the intelligent control level of hot-dip galvanizing process control. Through the embodiments of the present application, engineers can deeply explore the laws behind the data, perform precise modeling work, and specifically construct a coating thickness prediction model that is highly matched with the actual situation of the production line and the process characteristics. These models can not only accurately predict the thickness of the coating, but also reveal the specific effects of different process parameters on the coating thickness. The coating distribution prediction process involved in the embodiments of the present application uses these prediction models to achieve a detailed analysis of the weight of each process parameter to understand how they affect the coating thickness; the hot-dip galvanizing process parameter prediction process retrieves the target coating distribution curve and accurately predicts the hot-dip galvanizing process parameters. This precise prediction not only improves production efficiency, but also ensures the quality stability of galvanized products while reducing the frequency and cost of tests.

[0119] Based on the same inventive concept, the present application provides the following embodiments: Figure 10 A hot dip galvanizing control device is shown, the device comprising:

[0120] The order processing module 101 is configured to generate steel coil setting value request information and send it to a pre-trained coating distribution control model when a production line control system of a hot-dip galvanizing production line receives target order information; the steel coil setting value request information includes the target order information;

[0121] a control parameter determination module 102 for receiving and responding to the steel pipe set value request information by the coating distribution control model, outputting target control parameters matching the target order information according to the target order information in the steel coil set value request information, and sending the target control parameters to the production line control system;

[0122] The galvanizing control module 103 is used for the production line control system to monitor the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

[0123] Furthermore, the order processing module 101 is used to:

[0124] When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system determines a pre-trained target coating distribution control model corresponding to the target order information according to the target coating thickness in the target order information;

[0125] The production line control system generates the steel coil setting value request information according to the target order information, and sends it to the target coating distribution control model that corresponds to the target order information and is pre-trained.

[0126] Furthermore, the model training module is used to:

[0127] Before a production line control system of a hot-dip galvanizing production line receives target order information, obtaining original historical production data of the hot-dip galvanizing production line, wherein the original historical production data includes historical order information and historical control parameters;

[0128] Performing data cleaning on the original historical production data to obtain initial historical production data;

[0129] Performing data alignment on corresponding positions of the hot-dip galvanizing production line according to the initial historical production data to obtain target historical production data;

[0130] Classifying the target historical production data according to different target coating thicknesses corresponding to the historical order information to obtain historical production sub-data corresponding to each different target coating thickness;

[0131] Based on the historical production sub-data corresponding to each different target coating thickness, the original coating distribution control model corresponding to each different target coating thickness is trained to obtain the coating distribution control model corresponding to each different target coating thickness.

[0132] Furthermore, the model training module is used to:

[0133] Abnormal data and front and rear strip transition process data in the original historical production data are deleted, and incomplete data in the original historical production data are supplemented to obtain the initial historical production data.

[0134] Furthermore, the model updating module is used to:

[0135] After obtaining the pre-trained coating distribution control model, during the production process of the hot-dip galvanizing production line, actual order information and actual control parameters corresponding to various target coating thicknesses of the hot-dip galvanizing production line are obtained;

[0136] Whenever the data volume of the actual order information and the actual control parameters corresponding to any target coating thickness meets the preset requirements, the actual order information and the actual control parameters that meet the preset requirements are used to update and train the coating distribution control model corresponding to the target coating thickness that meets the preset requirements, and obtain the updated coating distribution control model corresponding to the target coating thickness.

[0137] Furthermore, the research analysis module is used to:

[0138] After obtaining the pre-trained coating distribution control model, obtaining historical control parameters and historical order information corresponding to the target coating thickness to be studied in the hot-dip galvanizing production line;

[0139] Inputting the historical control parameters corresponding to the target coating thickness to be studied into the coating distribution control model corresponding to the target coating thickness to be studied, to obtain predicted order information corresponding to the target coating thickness to be studied;

[0140] According to the difference between the historical order information and the predicted order information, the degree of influence of the historical control parameters corresponding to the target coating thickness to be studied on the hot-dip galvanized coating thickness distribution is analyzed.

[0141] Furthermore, the target control parameter includes at least one of the temperature of the zinc liquid in the zinc pot in the hot-dip galvanizing production line and an air knife control parameter.

[0142] Based on the same inventive concept, the present application provides the following embodiments: Figure 11 An electronic device as shown includes:

[0143] Processor 111;

[0144] a memory 112 for storing instructions executable by the processor 111;

[0145] The processor 111 is configured to execute to implement a hot-dip galvanizing control method as provided above.

[0146] Based on the same inventive concept, an embodiment of the present application provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor 111 of the electronic device, the electronic device can execute a hot-dip galvanizing control method as provided above.

[0147] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiment of this application, based on the information processing method described in the embodiment of this application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be described in detail here. As long as those skilled in the art implement the electronic device used by the information processing method in the embodiment of this application, it falls within the scope of protection to be provided by this application.

[0148] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0152] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0153] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A hot dip galvanizing control method, characterized in that: The method comprises: When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system generates a steel coil setting value request message and sends it to a pre-trained coating distribution control model; the steel coil setting value request message includes the target order information; The coating distribution control model receives and responds to the steel pipe setting value request information, outputs target control parameters matching the target order information according to the target order information in the steel coil setting value request information, and sends the target control parameters to the production line control system; The production line control system monitors the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

2. The method according to claim 1, wherein When the production line control system of the hot-dip galvanizing production line receives the target order information, the production line control system generates a steel coil set value request information and sends it to the pre-trained coating distribution control model, including: When a production line control system of a hot-dip galvanizing production line receives target order information, the production line control system determines a pre-trained target coating distribution control model corresponding to the target order information according to the target coating thickness in the target order information; The production line control system generates the steel coil setting value request information according to the target order information, and sends it to the target coating distribution control model that corresponds to the target order information and is pre-trained.

3. The method according to claim 1, wherein Before the production line control system of the hot-dip galvanizing production line receives the target order information, the method further includes: Obtaining original historical production data of the hot-dip galvanizing production line, wherein the original historical production data includes historical order information and historical control parameters; Performing data cleaning on the original historical production data to obtain initial historical production data; Performing data alignment on corresponding positions of the hot-dip galvanizing production line according to the initial historical production data to obtain target historical production data; Classifying the target historical production data according to different target coating thicknesses corresponding to the historical order information to obtain historical production sub-data corresponding to each different target coating thickness; Based on the historical production sub-data corresponding to each different target coating thickness, the original coating distribution control model corresponding to each different target coating thickness is trained to obtain the coating distribution control model corresponding to each different target coating thickness.

4. The method according to claim 3, wherein The data cleaning of the original historical production data to obtain the initial historical production data includes: Abnormal data and front and rear strip transition process data in the original historical production data are deleted, and incomplete data in the original historical production data are supplemented to obtain the initial historical production data.

5. The method according to claim 1, wherein After obtaining the pre-trained coating distribution control model, during the production process of the hot-dip galvanizing production line, the method further includes: Obtaining actual order information and actual control parameters corresponding to various target coating thicknesses during the production process of the hot-dip galvanizing production line; Whenever the data volume of the actual order information and the actual control parameters corresponding to any target coating thickness meets the preset requirements, the actual order information and the actual control parameters that meet the preset requirements are used to update and train the coating distribution control model corresponding to the target coating thickness that meets the preset requirements, and obtain the updated coating distribution control model corresponding to the target coating thickness.

6. The method according to claim 1, wherein After obtaining the pre-trained coating distribution control model, the method further includes: Obtaining historical control parameters and historical order information corresponding to the target coating thickness to be studied in the hot-dip galvanizing production line; Inputting the historical control parameters corresponding to the target coating thickness to be studied into the coating distribution control model corresponding to the target coating thickness to be studied, to obtain predicted order information corresponding to the target coating thickness to be studied; According to the difference between the historical order information and the predicted order information, the degree of influence of the historical control parameters corresponding to the target coating thickness to be studied on the hot-dip galvanized coating thickness distribution is analyzed.

7. The method according to claim 1, wherein The target control parameter includes at least one of the temperature of the zinc liquid in the zinc pot in the hot-dip galvanizing production line and an air knife control parameter.

8. A hot dip galvanizing control device, characterized in that: The device comprises: An order processing module is configured to generate steel coil setting value request information and send it to a pre-trained coating distribution control model when a production line control system of a hot-dip galvanizing production line receives target order information; the steel coil setting value request information includes the target order information; a control parameter determination module, configured for the coating distribution control model to receive and respond to the steel pipe set value request information, output target control parameters matching the target order information according to the target order information in the steel coil set value request information, and send the target control parameters to the production line control system; The galvanizing control module is used for the production line control system to monitor the welds of the continuous strip steel on the hot-dip galvanizing production line. When the production line control system monitors the strip steel welds corresponding to the target order information, the production line control system adjusts the control parameters of the hot-dip galvanizing production line to the target control parameters, so that the hot-dip galvanizing production line processes the strip steel corresponding to the target order information according to the target control parameters.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute to implement a hot-dip galvanizing control method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to implement a hot-dip galvanizing control method according to any one of claims 1 to 7.

Images