A method and system for collaborative linkage control and management of UV transfer plate production equipment

Abstract

The application discloses a kind of UV transfer plate production equipment cooperative linkage control management method and system, it is related to UV transfer plate production control management technical field, its method includes the following steps: determining UV transfer plate product and multiple production equipment, corresponding each production equipment is set to acquisition layer, receiving layer and control layer;Set up virtual management center, deploy trained machine learning model in virtual management center.This application can ensure the accuracy of receiving point receiving state data, can realize the lightweight transmission of state data, reduce transmission load;It can also realize the repair of the first symbol marker symbol point in the monitoring space in the disturbed communication channel;So that the state data input into machine learning model is relatively accurate, can ensure the accuracy of machine learning model output control parameter, further ensure the accuracy of multiple production equipment in cooperative linkage control.

Description

Technical Field

[0001] This invention relates to the field of UV transfer plate production control and management technology, specifically to a collaborative control and management method and system for UV transfer plate production equipment. Background Technology

[0002] UV transfer boards are made by spraying special UV paint (UV curing coating, UV photosensitive ink, etc.) onto particleboard, ceramic tile, artificial stone, glass, acrylic and other boards with a protective surface layer through professional equipment and then drying them with a UV curing machine.

[0003] In the production process of UV transfer plates, the coordinated control and management of production equipment plays a crucial role in ensuring product quality, improving production efficiency, and guaranteeing the stability of the production process. The production of UV transfer plates involves multiple complex technological steps, some of which require collecting status data of the UV transfer plate products during processing (such as UV coating thickness, humidity, etc.) to precisely control the control parameters of the production equipment based on the status data of the UV transfer plate products.

[0004] During the production of UV transfer plates, the status data of some UV transfer plates is easily interfered with during transmission, resulting in inaccurate status data. If the control parameters of the production equipment are determined based on these inaccurate status data, the final control parameters will also be inaccurate, which in turn can easily affect the accuracy of the production equipment for UV transfer plates in coordinated control.

[0005] Based on this, the present invention proposes a collaborative linkage control and management method and system for UV transfer plate production equipment to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a collaborative control and management method and system for UV transfer plate production equipment to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a collaborative control and management method for UV transfer plate production equipment, comprising the following steps:

[0008] The UV transfer plate product and multiple production equipment are identified, and a collection layer, a receiving layer, and a control layer are set up for each production equipment; a virtual management center is set up, and a trained machine learning model is deployed in the virtual management center;

[0009] Each acquisition point in the acquisition layer is configured with a first mapping table and two monitoring spaces, and each receiving point in the receiving layer is configured with a second mapping table. A transmission channel is set between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels.

[0010] Status data is collected using collection points. The status data includes UV coating thickness, temperature, and humidity. The status data is converted and transmitted to the receiving point through a first mapping table, a second mapping table, two monitoring spaces, and a transmission channel.

[0011] The state data received by the receiving points in the receiving layer is input into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power, and conveying speed. The control points in the control layer execute the corresponding control parameters to achieve coordinated control and management of multiple production equipment.

[0012] Furthermore, the steps of determining the UV transfer plate product and multiple production devices, setting up a collection layer, a receiving layer, and a control layer for each production device, and setting up a virtual management center and deploying a trained machine learning model within the virtual management center include:

[0013] Determine the processing requirements for UV transfer printing plate products and the corresponding production equipment;

[0014] A virtual management center is deployed for multiple production equipment, and multiple acquisition points and multiple control points are deployed for each production equipment. The multiple acquisition points and multiple control points form the acquisition layer and control layer of the corresponding production equipment, respectively. Multiple receiving points are deployed in the virtual management center for each acquisition point. The multiple receiving points form the receiving layer of the corresponding acquisition layer. The acquisition points and receiving points are in a one-to-one correspondence and are connected through a transmission channel.

[0015] The trained machine learning model is deployed for multiple production devices, and the trained machine learning model communicates with the receiving layer and control layer of multiple production devices.

[0016] Furthermore, each acquisition point in the corresponding acquisition layer is configured with a first mapping table and two monitoring spaces, and each receiving point in the corresponding receiving layer is configured with a second mapping table. A transmission channel is established between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels. The steps include:

[0017] A first mapping table is determined based on the status data collected at each collection point, and a second mapping table is determined based on the collection point corresponding to the receiving point. The first and second mapping tables correspond one-to-one with the collection point and the receiving point, respectively. Both the first and second mapping tables include multiple status data and multiple first symbols. The multiple status data form a data sequence in the first and second mapping tables according to the arrangement order, and the multiple first symbols correspond one-to-one with the multiple status data.

[0018] Two monitoring spaces are set up for each collection point, and symbol lines are set up in the two monitoring spaces. Each symbol line includes multiple symbol points.

[0019] Furthermore, the step of setting symbol lines in two monitoring spaces, each symbol line comprising multiple symbol points, includes:

[0020] Multiple symbol points are set in two monitoring spaces corresponding to multiple first symbols. The multiple symbol points are connected to form symbol lines according to the arrangement order of multiple state data in the first mapping table. A repairer is set between two symbol lines and the repairer is connected to the two symbol lines.

[0021] Furthermore, the step of collecting status data using acquisition points, including UV coating thickness, temperature, and humidity, and converting and transmitting the status data to the receiving point through a first mapping table, a second mapping table, two monitoring spaces, and a transmission channel includes:

[0022] The status data of the UV transfer plate products on the corresponding production equipment are collected by using multiple collection points in the collection layer;

[0023] The collected state data is converted by the first mapping table to obtain the first symbol corresponding to the state data. The first symbol corresponding to the state data is marked on the symbol point corresponding to the first symbol in two monitoring spaces to enable the two symbol points. A connection is established between the two enabled symbol points. The two enabled symbol points are transmitted in two communication channels respectively.

[0024] The connection between the two symbol points is maintained during transmission until the two symbol points are transmitted to the receiving point and converted into state data through the second mapping table; if the connection between the two marked symbol points is lost during transmission, the actively disconnected symbol points are repaired.

[0025] Furthermore, the step of repairing the actively disconnected symbol point if the two marked symbol points are disconnected during transmission includes:

[0026] When the communication channel is interfered with, if the symbol point corresponding to the first symbol in the corresponding monitoring space changes, that is, the unmarked symbol point is closed and the corresponding changed symbol point is enabled, and the two connected symbol points are disconnected.

[0027] The repairer records the actively disconnected symbol point among two connected symbol points, and uses the passively disconnected symbol point to repair the actively disconnected symbol point until the two symbol points are reconnected.

[0028] Further, the steps of inputting the state data received by the receiving points in the receiving layer into the trained machine learning model, and the trained machine learning model outputting control parameters to the corresponding control layer, including the paint pump speed, UV lamp power, and conveying speed, and the control points in the control layer executing the corresponding control parameters to achieve coordinated control and management of multiple production devices, include:

[0029] The state data received by all receiving points in the receiving layer are used as input features to input the trained machine learning model, and the trained machine learning model outputs the control parameters corresponding to the state data.

[0030] When the corresponding control parameters are output to the control layer, the control layer sends the control parameters to the corresponding control points. The control points execute the received control parameters, and the coordinated control and management of multiple production equipment is achieved by executing the received control parameters through multiple control points.

[0031] This invention also provides a collaborative control and management system for UV transfer plate production equipment, comprising:

[0032] The first setup module is used to determine the UV transfer plate product and multiple production devices, and to set up a collection layer, a receiving layer and a control layer for each production device; a virtual management center is set up, and a trained machine learning model is deployed in the virtual management center;

[0033] The second setting module is used to set a first mapping table and two monitoring spaces for each acquisition point in the acquisition layer, and to set a second mapping table for each receiving point in the receiving layer. A transmission channel is set between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels.

[0034] The data acquisition and transmission module is used to collect status data using acquisition points. The status data includes UV coating thickness, temperature and humidity. The status data is converted and transmitted to the receiving point through a first mapping table, a second mapping table, two monitoring spaces and a transmission channel.

[0035] The collaborative linkage control module is used to input the status data received by the receiving points in the receiving layer into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power and conveying speed. The control points in the control layer execute the corresponding control parameters to realize the collaborative linkage control management of multiple production equipment.

[0036] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0037] 1. This invention marks the first symbol of the state data conversion on the corresponding symbol points in two monitoring spaces and enables the two symbol points, thereby ensuring the accuracy of the state data received by the receiving point, realizing lightweight transmission of state data, and reducing the transmission load.

[0038] 2. This invention connects two symbol points of the first symbol marker within two monitoring spaces. The two monitoring spaces transmit data through two communication channels. When the communication channels are interfered with, the passively disconnected symbol point can repair the actively disconnected symbol point and re-establish the connection between the two symbol points. This enables the repair of the first symbol marker symbol points within the monitoring space in the interfered communication channel. This ensures that the state data input to the machine learning model is more accurate, guarantees the accuracy of the control parameters output by the machine learning model, and further ensures the accuracy of the coordinated control of multiple production devices. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0040] Figure 1 This is a flowchart of the method of the present invention.

[0041] Figure 2 This is a schematic diagram of the structure of the virtual management center in the method of the present invention;

[0042] Figure 3 This is a schematic diagram of the transmission channel structure in the method of the present invention;

[0043] Figure 4 This is a system block diagram of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example 1, please refer to Figures 1 to 3 As shown in this embodiment, a collaborative control and management method for UV transfer plate production equipment includes the following steps:

[0046] S1. Determine the UV transfer plate product and multiple production equipment, and set up a collection layer, a receiving layer and a control layer for each production equipment; set up a virtual management center and deploy the trained machine learning model in the virtual management center;

[0047] S2. A first mapping table and two monitoring spaces are set for each acquisition point in the corresponding acquisition layer, and a second mapping table is set for each receiving point in the corresponding receiving layer. A transmission channel is set between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels.

[0048] S3. Collect status data using the collection point. The status data includes UV coating thickness, temperature, and humidity. Convert the status data using the first mapping table, the second mapping table, the two monitoring spaces, and the transmission channel, and then transmit it to the receiving point.

[0049] S4. Input the state data received by the receiving point in the receiving layer into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power and conveying speed. The control point in the control layer executes the corresponding control parameters to realize the coordinated control and management of multiple production equipment.

[0050] In this embodiment, the first symbol, converted from state data, is marked on corresponding symbol points in two monitoring spaces, and the two symbol points are activated. This ensures the accuracy of the state data received by the receiving point, enables lightweight transmission of state data, and reduces transmission load. Through the connection between the two symbol points marked by the first symbol in the two monitoring spaces, the two monitoring spaces transmit data through two communication channels. When the communication channel is interfered with, the passively disconnected symbol point can repair the actively disconnected symbol point, re-establishing the connection between the two symbol points. This allows for the repair of the first symbol-marked symbol points in the monitoring space within the interfered communication channel, making the state data input to the machine learning model more accurate. This ensures the accuracy of the control parameters output by the machine learning model, further ensuring the accuracy of coordinated control of multiple production devices. This solves the problem that during the production process of UV transfer plates, the state data of some UV transfer plates is easily interfered with during transmission, leading to inaccurate transmitted state data and affecting the accuracy of coordinated control of the production equipment.

[0051] In one embodiment, the steps of determining the UV transfer plate product and multiple production devices, setting up a collection layer, a receiving layer, and a control layer for each production device, and setting up a virtual management center and deploying a trained machine learning model within the virtual management center include:

[0052] S11. Determine the processing requirements of UV transfer printing plate products and the corresponding production equipment;

[0053] S12. A virtual management center is deployed for multiple production equipment, and multiple acquisition points and multiple control points are deployed for each production equipment. The multiple acquisition points and multiple control points form the acquisition layer and control layer of the corresponding production equipment, respectively. Multiple receiving points are deployed in the virtual management center for each acquisition point. The multiple receiving points form the receiving layer of the corresponding acquisition layer. The acquisition points and receiving points are in one-to-one correspondence and connected through a transmission channel.

[0054] S13. Deploy pre-trained machine learning models for multiple production devices, and establish communication connections between the pre-trained machine learning models and the receiving and control layers of the multiple production devices.

[0055] It should be noted that, as described in S11 to S13 above, the processing requirements for UV transfer printing plate products are clearly defined, such as the resolution of the transfer pattern and the thickness of the UV coating. Based on these requirements, multiple production devices involved in processing the UV transfer printing plate products are identified. These devices include: coating equipment (for uniformly coating UV paint), UV curing equipment (for curing the paint using ultraviolet light), transfer equipment (for transferring the pattern from the mold to the plate surface), and conveyor belts. A virtual management center is deployed on a local server or cloud platform where these multiple production devices reside. This virtual management center integrates the multiple production devices through the Internet of Things (IoT) and data management tools to coordinate all production devices in a unified manner, facilitating the collection and transmission of status data and the distribution of control parameters.

[0056] In the acquisition layer, multiple acquisition points are sensors deployed on the production equipment to collect the status parameters of the UV transfer plate products. Each acquisition point's corresponding first mapping table and two monitoring spaces are stored in the sensor's configured storage space. Whenever an acquisition point collects corresponding status data, two new monitoring spaces are automatically generated. The status parameters of the UV transfer plate products include UV coating thickness, temperature, and humidity. Multiple acquisition points are connected via wired or wireless networks to form the acquisition layer, ensuring comprehensive collection of the UV transfer plate product status data from the production equipment. In the control layer, multiple control points correspond to actuators or controllers deployed on the production equipment. Examples of control points include: the paint pump speed controller for the coating equipment, the UV lamp power controller for the UV curing equipment, and the conveyor... The system includes a conveyor speed controller, etc.; multiple control points form a control layer for each production equipment to facilitate precise control of the equipment; in the receiving layer, a receiving point is deployed in the virtual management center for each acquisition point. Each receiving point is a virtual communication node used to receive status data in the virtual management center. Multiple receiving points form a receiving layer, which receives status data transmitted from the acquisition layer. A one-to-one correspondence between acquisition points and receiving points ensures a clear transmission path for status data; for example, one temperature acquisition point corresponds to one temperature receiving point, and one humidity acquisition point corresponds to one humidity receiving point. Machine learning models are deployed for multiple production equipment. The receiving layer inputs status data into the machine learning model, and the machine learning model outputs control parameters, which are then distributed to the corresponding control points of the production equipment through the control layer for execution.

[0057] In one embodiment, each acquisition point in the corresponding acquisition layer is configured with a first mapping table and two monitoring spaces, and each receiving point in the corresponding receiving layer is configured with a second mapping table. The step of establishing a transmission channel between the corresponding acquisition point and the receiving point, the transmission channel including two communication channels, includes:

[0058] S21. Determine the corresponding first mapping table based on the status data collected at each collection point, and determine the corresponding second mapping table based on the collection point corresponding to the receiving point; wherein, the first mapping table and the second mapping table correspond one-to-one with the collection point and the receiving point, respectively; both the first mapping table and the second mapping table include multiple status data and multiple first symbols, the multiple status data form a data sequence in the arrangement order of the first mapping table and the second mapping table, and the multiple first symbols correspond one-to-one with the multiple status data;

[0059] S22. Two monitoring spaces are set up for each collection point, and symbol lines are set up in the two monitoring spaces. Each symbol line includes multiple symbol points.

[0060] In one embodiment, the step of setting symbol lines in two monitoring spaces, each symbol line comprising multiple symbol points, includes:

[0061] S221. Multiple symbol points are set in two monitoring spaces corresponding to multiple first symbols respectively. The multiple symbol points are connected to form symbol lines according to the arrangement order of multiple state data in the first mapping table. A repairer is set between two symbol lines and the repairer is connected to the two symbol lines. The symbol point is a communication node that can mark the first symbol on the first mapping table.

[0062] It should be noted that, as described in S21 to S221 above, a first mapping table is set for each acquisition point. The first mapping table is used for the conversion between state data and first symbols. Multiple state data and multiple first symbols are arranged in an ascending order within the first mapping table (e.g., 1mm-a, 2mm-b, 3mm-c, where 1mm, 2mm, and 3mm are state data, and a, b, and c are first symbols). For example, when the UV coating thickness is 1mm, the first mapping table converts it to 'a'. The state data and first symbols are set in opposite order in the first and second mapping tables. A second mapping table is set for each receiving point. The second mapping table is used to convert the first symbols into corresponding state data. Multiple first symbols and multiple state data are arranged in an ascending order (e.g., a-1mm, b-2mm, c-3mm). For example, the second mapping table converts 'a' into a UV coating thickness of 1mm. mm; For each acquisition point, two identical monitoring spaces are set up. The monitoring space is a virtual machine, which is used to mark the first symbol on the symbol line and the symbol point corresponding to the first symbol. Multiple symbol points correspond one-to-one with the first symbol in the first mapping table set on the first symbol line, and the number of multiple symbol points is equal to the number of the first symbol in the first mapping table. The symbol point is the physical image of the first symbol in the monitoring space (i.e., the first symbol is c, and the monitoring space also has symbol point c). For example, the first mapping table converts the state data collected by the acquisition point, such as 3mm, into c. The first symbol c is marked on the symbol point c corresponding to the symbol line in the two monitoring spaces. When the receiving point receives the symbol point c, the second mapping table converts the first symbol c into 3mm. Thus, through the setting of the first mapping table, the second mapping table, and the monitoring space, lightweight transmission of state data can be achieved, reducing the transmission load.

[0063] In one embodiment, the step of collecting status data using collection points, the status data including UV coating thickness, temperature, and humidity, and converting the status data through a first mapping table, a second mapping table, two monitoring spaces, and a transmission channel, and then transmitting the status data to the receiving point includes:

[0064] S31. Collect the status data of the UV transfer plate products on the corresponding production equipment using multiple collection points in the collection layer.

[0065] S32. The collected state data is converted through the first mapping table to obtain the first symbol corresponding to the state data. The first symbol corresponding to the state data is marked on the symbol points corresponding to the first symbol in two monitoring spaces to enable the two symbol points. A connection is established between the two enabled symbol points. The two enabled symbol points are transmitted in two communication channels respectively.

[0066] S33. Maintain the connection between the two symbol points during transmission until the two symbol points are transmitted to the receiving point and converted into status data through the second mapping table; wherein, if the two marked symbol points are disconnected during transmission, the actively disconnected symbol points are repaired.

[0067] In one embodiment, the step of repairing the actively disconnected symbol point if two marked symbol points are disconnected during transmission includes:

[0068] S331. When the communication channel is interfered with, if the symbol point corresponding to the first symbol in the corresponding monitoring space changes, that is, the unmarked symbol point is closed and the corresponding changed symbol point is enabled, and the two connected symbol points are disconnected.

[0069] S332. The repairer records the actively disconnected symbol point among the two connected symbol points, and uses the passively disconnected symbol point to repair the actively disconnected symbol point until the two symbol points are reconnected.

[0070] It should be noted that, as described in S31 to S332 above, for example: the first mapping table is 1mm-a, 2mm-b, 3mm-c, 4mm-d, and the second mapping table is a-1mm, b-2mm, c-3mm, d-4mm. The symbol points corresponding to the first symbols on the symbol lines in the monitoring space are a, b, c, and d, respectively. The arrangement order of multiple symbol points is the same as that of multiple first symbols in the first and second mapping tables. Symbol point a corresponds one-to-one with the first symbol a in the first and second mapping tables. When the first symbol c corresponds to symbol point c on the symbol line in the monitoring space (i.e., they are the same, and they only correspond when the symbol point is the same as the first symbol), the first symbol c is marked on symbol point c.

[0071] The pre-defined rules for connecting two symbol points in two monitoring spaces are as follows: when the two symbol points marked by the first symbol are the same, the marked symbol points in the two monitoring spaces are activated and connected simultaneously; when the two marked symbol points are different, the two symbol points are disconnected.

[0072] When two connected symbol points become disconnected, a repairer is triggered. The repairer is a logic module that records the connection status (disconnected or connected) of two marked symbol points in two monitoring spaces, as well as the disconnection time. The repairer records the actively disconnected symbol point and uses the first symbol carried by the passively disconnected symbol point to repair the actively disconnected symbol point, thus re-establishing the connection between the two symbol points in the two monitoring spaces. For example, when two symbol points c marked by the first symbol c in two monitoring spaces (i.e., monitoring space A and monitoring space B, where monitoring space A and monitoring space B are the same) are disturbed, the symbol point marked by the first symbol c (in monitoring space A) changes (or moves) from c to d. At this time, the symbol point d marked by the first symbol c (in monitoring space A) and the symbol point c (in monitoring space B) are now connected. If the symbols c (within monitoring space B) and d (within monitoring space A) do not correspond (are not the same), then the symbol point c is disconnected from the symbol point d. Based on the passively disconnected symbol point c (within monitoring space B), the repairer moves the first symbol c from symbol point d to symbol point c (within monitoring space A), and symbol point c (within monitoring space A) is reactivated. According to the rules for connecting two symbol points in two monitoring spaces, the two symbol points c in two monitoring spaces are reconnected. This achieves the repair of symbol points that are actively disconnected in two monitoring spaces. When the first symbol is marked on the corresponding symbol point, the mark indicates that the first symbol is carried on the corresponding (identical) symbol point (the first symbol c is carried by the corresponding symbol point c), that is, the corresponding symbol point is activated. The mark plays the role of carrying the first symbol and activating the symbol point. Furthermore, by connecting the two symbol points marked by the first symbol in the two monitoring spaces, the two monitoring spaces transmit data through two communication channels respectively. When the communication channel is interfered with, the passively disconnected symbol point can be repaired by the repairer to repair the actively disconnected symbol point, and the connection between the two symbol points can be re-established, thereby realizing the repair of the symbol points in the monitoring space in the interfered communication channel. This ensures that the state data input to the machine learning model is more accurate, which in turn ensures the accuracy of the control parameters output by the machine learning model, and further ensures the accuracy of the coordinated control of multiple production equipment.

[0073] Specifically, the repairer is located outside the two monitoring spaces and is placed on the corresponding acquisition point (sensor). It plays the role of monitoring the connection status (disconnected or connected) and disconnection time of the two marked symbol points in the two monitoring spaces. When repairing the actively disconnected symbol points using the first symbol carried by the passively disconnected symbol points: the symbol points that change (or move) first in the two monitoring spaces are taken as the actively disconnected symbol points, and the symbol points that do not change (or move) are taken as the passively disconnected symbol points. The symbol points are communication nodes that can mark the first symbol on the first mapping table. The monitoring space is a virtual machine. By marking the first symbol on the corresponding symbol points in the two monitoring spaces, when the marked symbol points in the two monitoring spaces are the same, the two marked and identical symbol points in the two monitoring spaces are enabled, and the two enabled symbol points can establish a connection.

[0074] In one embodiment, the steps of inputting the state data received by the receiving points in the receiving layer into a trained machine learning model, and the trained machine learning model outputting control parameters to the corresponding control layer, wherein the control parameters include paint pump speed, UV lamp power, and conveying speed, and the control points in the control layer executing the corresponding control parameters to achieve coordinated control and management of multiple production devices, include:

[0075] S41. Input the state data received by all receiving points in the receiving layer into the trained machine learning model as input features, and the trained machine learning model outputs the control parameters corresponding to the state data.

[0076] S42. When the corresponding control parameters are output to the control layer, the control layer sends the control parameters to the corresponding control points. The control points execute the received control parameters. By executing the received control parameters through multiple control points, the coordinated control and management of multiple production equipment can be achieved.

[0077] It should be noted that, as described in S41 to S42 above, the training process of the machine learning model is as follows: the historical state data and the corresponding historical control parameters at the same time are taken as a set of samples, and multiple sets of samples are collected to form a dataset. The historical state data and historical control parameters in the same set of samples are taken as the input features and target output (i.e., control parameters) of the machine learning model, respectively. The dataset is divided into a training set and a test set in a 7:3 ratio. The random forest multi-output regression algorithm is used to build the machine learning model. The machine learning model is trained using the training set and tested using the test set until the machine learning model reaches the preset iteration conditions, and the trained machine learning model is obtained. A machine learning model was built using the random forest multi-output regression algorithm. Historical state data (UV coating thickness, temperature, and humidity) at the same time and corresponding historical control parameters (coating pump speed, UV lamp power, and delivery speed) were used as a set of samples, which became multi-input multi-output collaborative training data pairs. The dataset was divided into training and test sets in a 7:3 ratio. The model was trained with the goal of minimizing the prediction error of the control parameters. The model was trained by optimizing the hyperparameters (such as the number of decision trees and tree depth) of the machine learning model through the collaborative logic corresponding to the control parameters of the state data. This ensured that the machine learning model could learn the nonlinear linkage relationship between the state data and the control parameters. The training was continued until the collaborative prediction accuracy of the machine learning model on the test set met the preset conditions (such as the average absolute error of the control parameter combination ≤ 5%), resulting in a well-trained machine learning model adapted to collaborative control. Furthermore, by inputting the status data collected by the acquisition points (real-time acquired status data) into the trained machine learning model, the control parameters output by the machine learning model (control parameters corresponding to the real-time acquired status data) are obtained. The output control parameters are then sent to the corresponding control layer, and the control layer sends the control parameters to the corresponding control points. The control points execute the received control parameters, and the control parameters executed by multiple control points can realize the coordinated linkage control and management of multiple production equipment.For example, the status data is as follows: UV coating thickness: 12μm (preset standard value 15-18μm, below the lower limit, considered abnormal), temperature: 25℃ (preset standard value 23-27℃, normal), humidity: 45%RH (preset standard value 40%~50%RH, normal). The three corresponding receiving points of the receiving layer receive data through the transmission channel, integrating it into the status data [12μm, 25℃, 45%RH]. This data is then synchronously input into the trained machine learning model. The machine learning model outputs adapted control parameters: coating pump speed of the coating equipment: 60r / min (original default value 50r / min, increased to increase coating output), UV lamp power of the UV curing equipment: 8kW (original default value 8kW, no adjustment needed to avoid additional impact), conveyor belt speed: 3m / min (original default value 4m / min, reduced to extend coating time and ensure full coating coverage of the UV board). The control layer then sends these control parameters to... The corresponding control points are as follows: the coating pump speed controller (control point 1) of the coating equipment is set to 60 r / min, increasing the coating output by 20% to directly supplement the amount of coating required for the coating thickness; the conveyor belt speed controller (control point 2) is set to 3 m / min, extending the conveying time by 25%, allowing the coating equipment more time to evenly apply the newly added coating to the board surface; the UV lamp power controller (control point 3) of the UV curing equipment is maintained at 8 kW. Since there are no abnormalities in temperature and humidity, no power adjustment is required to avoid over-curing and causing coating cracking. Therefore, by increasing the coating pump speed and decreasing the conveying speed, the thickness of the UV coating collected later can reach 16 μm (meeting the preset standard value), which can ensure uniform coating curing effect without bubbles or cracking, solve the problem of insufficient UV coating thickness, ensure the dynamic balance of the production process, and facilitate the coordinated control of multiple production equipment based on status parameters to improve the overall processing effect of UV transfer board products.

[0078] Example 2, please refer to Figure 4 As shown in this embodiment, a collaborative control and management system for UV transfer plate production equipment includes:

[0079] The first setup module is used to determine the UV transfer plate product and multiple production devices, and to set up a collection layer, a receiving layer and a control layer for each production device; a virtual management center is set up, and a trained machine learning model is deployed in the virtual management center;

[0080] The second setting module is used to set a first mapping table and two monitoring spaces for each acquisition point in the acquisition layer, and to set a second mapping table for each receiving point in the receiving layer. A transmission channel is set between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels.

[0081] The data acquisition and transmission module is used to collect status data using acquisition points. The status data includes UV coating thickness, temperature and humidity. The status data is converted and transmitted to the receiving point through a first mapping table, a second mapping table, two monitoring spaces and a transmission channel.

[0082] The collaborative linkage control module is used to input the status data received by the receiving points in the receiving layer into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power and conveying speed. The control points in the control layer execute the corresponding control parameters to realize the collaborative linkage control management of multiple production equipment.

[0083] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A collaborative control and management method for UV transfer plate production equipment, characterized in that, Includes the following steps: The UV transfer plate product and multiple production equipment are identified, and a collection layer, a receiving layer, and a control layer are set up for each production equipment; a virtual management center is set up, and a trained machine learning model is deployed in the virtual management center; Each acquisition point in the acquisition layer is configured with a first mapping table and two monitoring spaces, and each receiving point in the receiving layer is configured with a second mapping table. A transmission channel is established between the acquisition point and the receiving point, and the transmission channel includes two communication channels. Each of the first and second mapping tables includes multiple status data and multiple first symbols. The multiple status data form a data sequence in the first and second mapping tables according to the arrangement order, and the multiple first symbols correspond one-to-one with the multiple status data. Each acquisition point is configured with two monitoring spaces, and symbol lines are set in the two monitoring spaces, with each symbol line including multiple symbol points. Status data is collected using collection points. The status data includes UV coating thickness, temperature, and humidity. The status data is converted and transmitted to the receiving point through a first mapping table, a second mapping table, two monitoring spaces, and a transmission channel. The steps of collecting status data using acquisition points, including UV coating thickness, temperature, and humidity, and converting and transmitting the status data to the receiving point through a first mapping table, a second mapping table, two monitoring spaces, and a transmission channel include: collecting status data of the UV transfer plate product on the corresponding production equipment using multiple acquisition points in the acquisition layer; converting the collected status data into a first symbol corresponding to the status data through the first mapping table; marking the first symbol corresponding to the status data on the symbol points corresponding to the first symbol in the two monitoring spaces to activate the two symbol points, establishing a connection between the two activated symbol points, and transmitting the two activated symbol points in two communication channels respectively; maintaining the connection between the two symbol points during transmission until the two symbol points are transmitted to the receiving point and converted into status data through the second mapping table; wherein, if the connection between the two marked symbol points is lost during transmission, the actively disconnected symbol points are repaired. The state data received by the receiving points in the receiving layer is input into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power, and conveying speed. The control points in the control layer execute the corresponding control parameters to achieve coordinated control and management of multiple production equipment.

2. The method for collaborative control and management of UV transfer plate production equipment according to claim 1, characterized in that, The UV transfer plate product is determined to be associated with multiple production devices, and a collection layer, a receiving layer, and a control layer are respectively set for each production device. The steps for setting up a virtual management center and deploying a trained machine learning model within it include: Determine the processing requirements for UV transfer printing plate products and the corresponding production equipment; A virtual management center is deployed for multiple production equipment, and multiple acquisition points and multiple control points are deployed for each production equipment. The multiple acquisition points and multiple control points form the acquisition layer and control layer of the corresponding production equipment, respectively. Multiple receiving points are deployed in the virtual management center for each acquisition point. The multiple receiving points form the receiving layer of the corresponding acquisition layer. The acquisition points and receiving points are in a one-to-one correspondence and are connected through a transmission channel. The trained machine learning model is deployed for multiple production devices, and the trained machine learning model communicates with the receiving layer and control layer of multiple production devices.

3. The method for collaborative control and management of UV transfer plate production equipment according to claim 1, characterized in that, Each acquisition point in the corresponding acquisition layer is configured with a first mapping table and two monitoring spaces, and each receiving point in the corresponding receiving layer is configured with a second mapping table. A transmission channel is established between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels. The steps include: A first mapping table is determined based on the status data collected at each collection point, and a second mapping table is determined based on the collection point corresponding to the receiving point; wherein the first mapping table and the second mapping table correspond one-to-one with the collection point and the receiving point, respectively.

4. The method for collaborative control and management of UV transfer plate production equipment according to claim 1, characterized in that, The step of setting symbol lines in two monitoring spaces, wherein each symbol line includes multiple symbol points, includes: Multiple symbol points are set in two monitoring spaces corresponding to multiple first symbols. The multiple symbol points are connected to form symbol lines according to the arrangement order of multiple state data in the first mapping table. A repairer is set between two symbol lines and the repairer is connected to the two symbol lines.

5. The method for collaborative control and management of UV transfer plate production equipment according to claim 4, characterized in that, The step of repairing the actively disconnected symbol points if the two marked symbol points are disconnected during transmission includes: When the communication channel is interfered with, if the symbol point corresponding to the first symbol in the corresponding monitoring space changes, that is, the unmarked symbol point is closed and the corresponding changed symbol point is enabled, and the two connected symbol points are disconnected. The repairer records the actively disconnected symbol point among two connected symbol points, and uses the passively disconnected symbol point to repair the actively disconnected symbol point until the two symbol points are reconnected.

6. The method for collaborative control and management of UV transfer plate production equipment according to claim 1, characterized in that, The steps of inputting the state data received by the receiving points in the receiving layer into the trained machine learning model, and the trained machine learning model outputting control parameters to the corresponding control layer, including the paint pump speed, UV lamp power, and conveying speed, and the control points in the control layer executing the corresponding control parameters to achieve coordinated control and management of multiple production devices, include: The state data received by all receiving points in the receiving layer are used as input features to input the trained machine learning model, and the trained machine learning model outputs the control parameters corresponding to the state data. When the corresponding control parameters are output to the control layer, the control layer sends the control parameters to the corresponding control points. The control points execute the received control parameters, and the coordinated control and management of multiple production equipment is achieved by executing the received control parameters through multiple control points.

7. A collaborative control and management system for UV transfer plate production equipment, used to implement the collaborative control and management method for UV transfer plate production equipment as described in any one of claims 1-6, characterized in that, include: The first setting module is used to determine the UV transfer plate product and multiple production equipment, and sets up a collection layer, a receiving layer and a control layer for each production equipment respectively. Set up a virtual management center and deploy the trained machine learning model within the virtual management center; The second setting module is used to set a first mapping table and two monitoring spaces for each acquisition point in the acquisition layer, and to set a second mapping table for each receiving point in the receiving layer. A transmission channel is set between the corresponding acquisition point and the receiving point, and the transmission channel includes two communication channels. The data acquisition and transmission module is used to collect status data using acquisition points. The status data includes UV coating thickness, temperature and humidity. The status data is converted and transmitted to the receiving point through a first mapping table, a second mapping table, two monitoring spaces and a transmission channel. The collaborative linkage control module is used to input the status data received by the receiving points in the receiving layer into the trained machine learning model. The trained machine learning model outputs control parameters to the corresponding control layer. The control parameters include paint pump speed, UV lamp power and conveying speed. The control points in the control layer execute the corresponding control parameters to realize the collaborative linkage control management of multiple production equipment.

Images