Intelligent control method and system for aluminum foil coating machine

Abstract

The invention discloses an intelligent control method and system for an aluminum foil coating machine, and relates to the technical field of aluminum foil coating machines, and the method comprises the steps: connecting an intelligent control platform, and obtaining control target equipment information which comprises a coating machine identification code and an equipment communication port; target equipment signals are collected based on the centralized control signals, the coating machine identification codes and the equipment communication ports, and receiving control signals of all target equipment are obtained; performing window framing processing by using the centralized control signal and the receiving control signal of each target device, and analyzing the deviation characteristics of the device; when the equipment deviation characteristic exists, equipment positioning is carried out based on an equipment communication port, a signal deviation adjusting instruction is sent, and the signal deviation adjusting instruction is used for carrying out deviation rectification preprocessing on the received control signal and then enters an execution control stage. The technical problem that in the prior art, when the aluminum foil coating machine is subjected to centralized control, the control accuracy is low is solved, and the technical effect of improving the centralized control accuracy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of aluminum foil coating machines, and in particular to an intelligent control method and system for an aluminum foil coating machine. Background Art

[0002] When multiple devices of the aluminum foil coating machine work simultaneously, higher requirements are placed on production control. At present, since only the working nodes of each device are controlled, the consistency factors between different devices in production are ignored, resulting in inadequate status analysis of different devices during centralized control, resulting in large errors in control. The existing technology has the technical problem of low control accuracy when the aluminum foil coating machine is centrally controlled. Summary of the invention

[0003] The present application provides an intelligent control method and system for an aluminum foil coating machine, which is used to solve the technical problem of low control accuracy when the aluminum foil coating machine is centrally controlled in the prior art.

[0004] In view of the above problems, the present application provides an intelligent control method and system for an aluminum foil coating machine.

[0005] In a first aspect of the present application, a smart control method for an aluminum foil coating machine is provided, wherein the method is applied to a smart control platform, and the method comprises: Connect to the smart control platform to obtain the target device information, including the coating machine identification code and device communication port; Acquire a centralized control signal, and based on the centralized control signal, the coating machine identification code, and the device communication port, collect target device signals to obtain receiving control signals of each target device; Utilizing the centralized control signal and the receiving control signal of each target device, performing window framing processing and analyzing device deviation characteristics; When there is a device deviation feature, the device is positioned based on the device communication port and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal before entering the execution control stage.

[0006] The second aspect of the present application provides an intelligent control system for an aluminum foil coating machine, the system comprising: The control target device information acquisition module is used to connect to the intelligent control platform and obtain the control target device information, including the coating machine identification code and the device communication port; A receiving control signal acquisition module is used to acquire a centralized control signal, collect target device signals based on the centralized control signal, the coating machine identification code, and the device communication port, and obtain a receiving control signal for each target device; A device deviation feature analysis module, used to perform window framing processing and analyze device deviation features by using the centralized control signal and the received control signal of each target device; The adjustment instruction sending module is used to locate the device based on the device communication port when there is a device deviation feature, and send a signal deviation adjustment instruction, wherein the signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal and then enter the execution control stage.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application obtains the information of the target device to be controlled by connecting to the intelligent control platform, including the coating machine identification code and the device communication port, and then obtains the centralized control signal. Based on the centralized control signal, the coating machine identification code and the device communication port, the target device signal is collected to obtain the receiving control signal of each target device, and then the centralized control signal and the receiving control signal of each target device are used to perform window framing processing, analyze the device deviation characteristics, and then when there is a device deviation characteristic, the device is located based on the device communication port, and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the receiving control signal and then enter the execution control stage. The technical effect of improving the control reliability and accuracy of each target device is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic flow chart of the intelligent control method for an aluminum foil coating machine provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an intelligent control system for an aluminum foil coating machine provided in an embodiment of the present application.

[0010] Explanation of reference numerals: control target device information acquisition module 11, control signal receiving acquisition module 12, device deviation characteristic analysis module 13, adjustment instruction sending module 14. DETAILED DESCRIPTION

[0011] The present application provides an intelligent control method and system for an aluminum foil coating machine, which is used to solve the technical problem of low control accuracy when the aluminum foil coating machine is centrally controlled in the prior art.

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1 like Figure 1 As shown, the present application provides an intelligent control method for an aluminum foil coating machine, wherein the method is applied to an intelligent control platform, and the method includes: Step S100: Connect to the smart control platform to obtain the target device information, including the coating machine identification code and the device communication port; In a possible embodiment, the aluminum foil coating machine is a device used to coat or apply various substances on the surface of aluminum foil. The coating can increase the waterproof performance of the aluminum foil and protect the product. The intelligent control platform is used to intelligently control multiple aluminum foil coating machines, and the signal processing is performed according to the energy difference of the control signals of different devices, so as to achieve the goal of centralized control of batch equipment.

[0015] Optionally, by connecting to the smart control platform, the control target device information is obtained. The control target device information is used to describe the device status controlled by the smart control platform, including the coating machine identification code and the device communication port. The coating machine identification code is a specific coding system for identifying the coating machine device, which can be a unique combination of numbers, letters or symbols to quickly identify the device. The device communication port is an interface or connection point for the coating machine to communicate with the external system, which is used to transmit data, commands, control signals, etc.

[0016] Step S200: Acquire a centralized control signal, collect target device signals based on the centralized control signal, the coating machine identification code, and the device communication port, and obtain a receiving control signal of each target device; Furthermore, the centralized control signal is obtained, and step S200 in the embodiment of the present application further includes: Acquire coating components, perform property analysis on the coating components, and obtain property characteristics, wherein the property characteristics include adhesion characteristics, cross-linking reaction characteristics, and chemical reaction characteristics; Decomposing and matching the process parameters based on the attribute characteristics to determine the degree of influence of each attribute characteristic on the process parameters; According to the influence of each attribute characteristic and process parameter, configure the process technology control target variable and control influence relationship; Control optimization is performed according to the process technology control target variables and control influence relationships to obtain control information of each process as the centralized control signal.

[0017] In an embodiment of the present application, the centralized control signal is a signal sent by the intelligent control platform to control multiple devices or systems, and is used to perform various operations of the device, including target variables and variable parameters for controlling each process. After obtaining the centralized control signal, the device signals of different coating machines are collected based on the coating machine identification code and the device communication port to obtain the receiving control signal of each target device. Among them, the receiving control signal reflects the reception of the centralized control signal by each target device.

[0018] Optionally, the coating components to be coated on the aluminum foil are obtained. The coating components have a direct impact on the surface properties of the aluminum foil, and different coating components have different degrees of influence on the surface properties. Exemplarily, the coating components can be polymer materials (polyurethane, polyester, polyether, etc.), adhesives, additives, etc. The attribute characteristics are obtained by performing attribute analysis on the coating components. Among them, the attribute characteristics are used to describe the performance of the coating components, including adhesion characteristics, cross-linking reaction characteristics, and chemical reaction characteristics. Among them, the adhesion characteristics are the ability of the coating components to combine with the surface of the aluminum foil, which is used to measure the degree to which the coating can firmly adhere to the surface of the aluminum foil after coating, and are very important for ensuring the long-term and stability of the coating.

[0019] The cross-linking reaction characteristics are the degree of chemical reaction between molecules in the coating or between molecules in the coating and the surface of the aluminum foil, as well as the physical conditions during the coating process, including cross-linking density, cross-linking structure, cross-linking degree, cross-linking reaction speed, coating speed, coating thickness, and time and temperature of the drying and curing process. The chemical reaction characteristics are used to describe the chemical reaction of the coating during the curing or hardening process, including reaction type, reaction conditions, reaction rate, reaction products, etc. By performing attribute analysis to obtain the attribute characteristics, a technical effect of a multi-faceted description of the coating components and providing basic data for subsequent control is achieved.

[0020] In one possible embodiment, the process parameters are decomposed and allocated according to the attribute characteristics. Optionally, based on the attribute characteristics of the coating components, we can perform process parameter decomposition matching to determine the degree of association between each attribute characteristic and the process parameters used in the process of coating the aluminum foil surface. By quantifying the degree of influence of different process parameters on the coating attribute characteristics, the technical effect of improving the control accuracy of the aluminum foil coating machine is achieved.

[0021] Specifically, we first decompose the coating property characteristics into different property characteristics, such as cross-linking density, cross-linking structure, reaction rate, etc. Then, for each property characteristic, we analyze its correlation with each process parameter, and determine the degree of influence of each process parameter on the property characteristic through experimental design or model derivation. In this way, we can establish a correlation model between property characteristics and process parameters, providing a scientific basis and guidance for optimizing the intelligent control of aluminum foil coating machines.

[0022] In a possible embodiment, according to the influence degree of each attribute feature and process parameter, the control target variable and control influence relationship of each process technology are configured. The process technology control target variable is the variable that needs to be controlled when each process technology is operated, such as controlling the moving speed of the coating head in the coating stage, controlling the heating temperature in the drying stage, etc. The control influence relationship is the correlation relationship between the process parameter and each attribute feature, that is, when controlling the process parameter, the degree of each attribute feature needs to be considered.

[0023] In one embodiment, control optimization is performed according to the process control target variables and control influence relationships, thereby determining control information of each process, and using the control information of each process as the centralized control signal. Optionally, each process includes coating, drying, curing, cooling, etc.

[0024] Furthermore, according to the influence degree of each attribute feature and process parameter, the process technology control target variable and the control influence relationship are configured. Step S200 of the embodiment of the present application also includes: Extracting an original control data set based on the attribute characteristics and process parameters; Clustering the original control data set according to attribute characteristics to obtain attribute characteristic sample clusters; Determine the relevant process according to the process mapping relationship between the attribute feature and the attribute feature sample cluster, perform influence relationship analysis of process control parameters according to the attribute feature sample cluster, and obtain control target variables, where the control target variables are process control parameters that have influence on the attribute feature; The control influence relationship is determined according to the influence degree of the attribute feature and the process parameter, and the control influence proportion of the attribute feature in the attribute feature sample cluster.

[0025] In an embodiment of the present application, the data repository of the intelligent control platform is searched with attribute features and process parameters as indexes to obtain the original control data set. The original control data set includes the initial control parameters of each process. The data in the original control data set is clustered with the attribute features as indexes, and the original control data belonging to the same attribute features are classified into one category to obtain the attribute feature sample cluster.

[0026] Then, according to the process mapping relationship between the attribute feature and the attribute feature sample cluster, the process related to the attribute feature is determined, and then, according to the attribute feature sample cluster, the parameter with greater influence in the process control parameter is determined as the control target variable. The control target variable is the process control parameter that has influence on the attribute feature.

[0027] Optionally, a weighted calculation is performed on the degree of influence between the attribute feature and the process parameter, and the proportion of the attribute feature in the control influence of the attribute feature sample cluster to obtain the control influence relationship.

[0028] Furthermore, control optimization is performed according to the process technology control target variables and control influence relationships to obtain control information of each process. Step S200 of the embodiment of the present application further includes: Obtaining coating target performance, performing attribute characteristic target decomposition according to the coating target performance and coating composition, and determining attribute characteristic target values; According to the process technology control target variables and control influence relationships, a reaction effect evaluation function of the attribute characteristics is constructed, and the difference between the reaction effect evaluation value and the attribute characteristic target value is minimized as the optimization goal, and an optimization space is established; Iterative optimization of the control target variable is performed through the optimization space, and when the optimization target or iteration threshold is reached, the control information of each process is obtained.

[0029] Furthermore, step S200 of the embodiment of the present application further includes: Obtain the process nodes that affect the cross-linking reaction characteristics and chemical reaction characteristics, distribute the proportions through the evaluation channels, and obtain the process node weights; Perform cross-linking reaction and chemical reaction target value analysis according to the coating target performance and coating composition to determine the reaction target; Add the reaction target as a constraint condition into the optimization space to obtain control information affecting the process nodes; Construct a timing chain according to the sequential relationship of the nodes that affect the process; The cross-linking reaction characteristics and chemical reaction characteristics of the coating material are used as the state quantity of the time series node, the process control parameters are used as the action quantity of the time series node, and the control influence relationship between the process control parameters and the cross-linking reaction characteristics and chemical reaction characteristics is used as the incentive quantity of the time series node to construct a Markov chain model. The Markov chain model is used to perform probability evaluation on the control information of each process, and when the reaction target probability is met, the control information of each process is fed back.

[0030] In a possible embodiment, the coating target performance is collected, wherein the coating target performance is the functional requirement that the coating on the surface of the aluminum foil needs to meet, including coating thickness, coating uniformity, corrosion resistance, wear resistance, heat resistance, etc. According to the coating target performance and coating composition, the target value of each attribute feature is determined with the attribute feature as an index to obtain the attribute feature target value.

[0031] Optionally, a reaction effect evaluation function of the attribute characteristics is constructed according to the process technology control target variable and the control influence relationship. The reaction effect evaluation function is used to determine the reaction effect of the attribute characteristics according to the change of the process technology control target variable. Then, the difference between the reaction effect evaluation value and the attribute characteristic target value is minimized as the optimization target, and an optimization space is constructed. In the optimization space, iterative optimization of the control target variable is performed. When the optimization target or the iteration threshold (the number of iterations set by a person skilled in the art) is met, the iterative optimization is stopped and the control information of each process is output. The control information of each process is the control parameter value of each process.

[0032] Optionally, the parameter range of the control target variable can be selected as a parameter adjustment interval set in the optimization space, and the parameters of the control target variable are randomly adjusted in the parameter adjustment interval set, and the adjusted control target variable is input into the reaction effect evaluation function to obtain a reaction effect evaluation value, and then the difference between the reaction effect evaluation value and the attribute characteristic target value is calculated. The parameters of the control target variable are randomly adjusted for the second time in the parameter adjustment interval set, and the control target variable after the second adjustment is input into the reaction effect evaluation function to obtain a second reaction effect evaluation value, and then the second difference between the second reaction effect evaluation value and the attribute characteristic target value is calculated. Compare the difference with the second difference, retain the parameters of the control target variable corresponding to the smaller value, and perform the next iterative optimization until the optimization target or iteration threshold is reached, and the parameters of the control target variable corresponding to the minimum difference value are used as the control information of each process.

[0033] In a possible embodiment, by obtaining the influencing process nodes of the cross-linking reaction characteristics and the chemical reaction characteristics, and using the hierarchical analysis method to construct an evaluation channel, the influence degree of different influencing process nodes is analyzed, and the influence distribution ratio of each influencing process node is determined to obtain the process node weight. Among them, the larger the process node weight, the more important the corresponding influencing process node is for the cross-linking reaction characteristics and the chemical reaction characteristics.

[0034] Optionally, the influence distribution ratio of each process node is determined as the target layer of the evaluation channel, and the relative importance of the process nodes influencing the cross-linking reaction characteristics and chemical reaction characteristics is compared in accordance with the process sequence, and the relative importance of the process nodes influencing each other is evaluated by expert analysis, and the judgment matrix is ​​filled in, and then the weight value of each process node influencing is calculated by using the specific calculation method of the hierarchical analysis method. The weight value of each process node influencing the consistency is verified with the judgment matrix. When the verification is passed, the weight value of each process node influencing the consistency is used as the process node weight.

[0035] Optionally, the coating target performance is taken as the target, and the coating composition is taken as the basis for the reaction, and the target value of the cross-linking reaction and the chemical reaction is determined to determine the reaction target. Among them, the reaction target is to meet the coating target performance, and the target value of the cross-linking reaction and the chemical reaction that can be achieved when the aluminum foil coating machine is working based on the coating composition is taken as the reaction target. The reaction target is added to the optimization space as a constraint condition to obtain the control information that affects the process node. In other words, on the basis of satisfying the optimization target, the control information of each process obtained by the optimization needs to satisfy the constraint conditions at the same time.

[0036] In one possible embodiment, a timing chain is constructed according to the sequential timing relationship of the process nodes, and each process node is used as a node on the timing chain. Furthermore, the cross-linking reaction characteristics and chemical reaction characteristics of the coating material are used as the state quantity of the timing node, the process control parameters are used as the action quantity of the timing node, and the control influence relationship between the process control parameters and the cross-linking reaction characteristics and the chemical reaction characteristics is used as the excitation quantity of the timing node to construct a Markov chain model. Among them, the Markov chain model predicts the state changes of the cross-linking reaction characteristics and chemical reaction characteristics of the coating material when each process of the aluminum foil coating machine is working, and the probability of change of each state depends only on the current state and has nothing to do with the previous state. Furthermore, the Markov chain model is used to perform probability evaluation on the control information of each process, and when the reaction target probability is met, the control information of each process is fed back. Among them, the reaction target probability is the possibility of the cross-linking reaction characteristics and chemical reaction characteristics of the coating material reaching the target value set by the technicians in this field.

[0037] When the cross-linking reaction and chemical reaction are in progress, because the cross-linking chemical reaction has a superimposed effect, at this time, the speed and time of the coating roller will have overlapping effects, and the drying temperature and time will also have overlapping effects, and the curing temperature will also have an impact. Therefore, the Markov chain model can be used to comprehensively consider the progress of the two reactions, conduct a comprehensive analysis of the control information of each process, and improve the accuracy of control.

[0038] Step S300: Utilizing the centralized control signal and the receiving control signal of each target device, performing window framing processing and analyzing device deviation characteristics; Further, the centralized control signal and the received control signal of each target device are used to perform window framing processing and analyze device deviation characteristics. Step S300 of the embodiment of the present application further includes: Setting a standard time analysis window, using the standard time analysis window to perform frame processing on the centralized control signal and the received control signal of each target device, and constructing a window signal set of each control signal; Based on the window signal set of each control signal, calculating the short-time energy entropy in each window signal; Calculating the short-time energy ratio according to the short-time energy entropy in the window signal to obtain the signal short-time energy entropy ratio; The device deviation characteristic is determined according to the signal short-time energy entropy ratio.

[0039] Further, according to the short-time energy entropy in the window signal, a short-time energy ratio is calculated to obtain the signal short-time energy entropy ratio. Step S300 of the embodiment of the present application further includes: Aligning the centralized control signal and the receiving control signal of each target device according to a window order; According to the window alignment relationship, the first short-time energy entropy ratio of the window signal of each target device to the centralized control signal is calculated respectively; Calculating the second short-time energy entropy ratio of two consecutive windows according to the window timing relationship of the window signal set of each control signal; The first short-time energy entropy ratio and the second short-time energy entropy ratio are fused to obtain the signal short-time energy entropy ratio of each device.

[0040] In an embodiment of the present application, the centralized control signal and the receiving control signal of each target device are used to perform window framing processing on the amount of information allocated to the receiving control signal of each target device in the same time period to determine the device deviation characteristics of each target device when performing intelligent control.

[0041] In a possible embodiment, a standard time analysis window is set, wherein the standard time analysis window is a time period for frame processing. The centralized control signal and the received control signal of each target device are respectively divided into windows using the standard time analysis window to obtain a window signal set of each control signal. The window signal set of each control signal is a continuous signal data set of each control signal within multiple standard time analysis windows.

[0042] By analyzing the amount of information of each control signal in the same standard time analysis window according to the window signal set of each control signal, the short-time energy entropy in each window signal is obtained. Exemplarily, it can be calculated by the short-time energy entropy calculation formula. The short-time energy entropy calculation formula is: ,in, is the energy probability distribution of the signal in the i-th standard time analysis window, and M is the total number of standard time analysis windows. The information amount of each window signal is quantified using the short-time energy entropy calculation formula.

[0043] Then, the receiving control signals of each target device are aligned in the window order at the starting time points of the multiple standard time analysis windows divided by the centralized control signal. Then, according to the window alignment relationship, the first short-time energy entropy ratio of the window signal of each target device in the first window to the centralized control signal is calculated respectively. Then, according to the window timing relationship of the window signal set of each control signal, the second short-time energy entropy ratio of two consecutive windows is calculated. The weighted mean calculation of the first short-time energy entropy ratio and the second short-time energy entropy ratio is performed to obtain the signal short-time energy entropy ratio of each device.

[0044] The variance is calculated based on the short-time energy entropy ratio of the signal to obtain a first fluctuation variance. The first fluctuation variance reflects the degree of fluctuation of the amount of information of each control signal in the window signal. The larger the first fluctuation variance, the lower the consistency of the amount of information of each control signal. The first fluctuation variance is used as a device deviation feature.

[0045] Step S400: When there is a device deviation feature, the device is positioned based on the device communication port, and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal and then enter the execution control stage.

[0046] Furthermore, step S400 in the embodiment of the present application further includes: A monitoring module is provided, the monitoring module is connected to the intelligent control platform for communication, synchronous monitoring information is provided, and each control target device is controlled and monitored through the monitoring module. The monitoring module includes monitoring target features preset according to the centralized control signal, and the monitoring target features are abnormal process features obtained according to historical abnormal samples; Acquire real-time monitoring information, and perform traversal matching with the real-time monitoring information according to the monitoring target characteristics; When there is a matching relationship between the monitoring information and the monitoring target feature, feature marking is performed on the monitoring information; Abnormal equipment positioning and abnormal probability calculation are performed according to the feature annotations. When the abnormal equipment positioning and abnormal probability exceed the preset range, an early warning message is sent.

[0047] In a possible embodiment, when there is a device deviation feature, the device is located through the device communication port according to the size of the signal short-time energy entropy ratio of each device, the device position corresponding to the different signal short-time energy entropy ratios is determined, and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal before entering the execution control stage.

[0048] Optionally, the noise in the received control signal is processed by using a filter to achieve the goal of noise reduction, and then the noise reduction result is analyzed to determine whether it is necessary to perform noise reduction again, so as to achieve the technical effect of reducing the noise component in the signal and improving the signal-to-noise ratio of the signal. This effectively reduces the error in the calculation of the energy entropy ratio.

[0049] In a possible embodiment, the monitoring module is used to control and monitor each control target device, communicate with the intelligent control platform, and synchronize the monitored information to the intelligent control platform. The monitoring module includes monitoring target features preset according to the centralized control signal, and the monitoring target features are abnormal process features obtained according to historical abnormal samples. Among them, the monitoring target features include oscillation or fluctuation, mutation or jump, saturation or truncation, abnormal spectrum features, etc. By analyzing the historical abnormal samples, the abnormal process features when the centralized control signal is abnormal are determined.

[0050] Then, the monitoring module is used to control and monitor each control target device to obtain real-time monitoring information. The real-time monitoring information is used to describe the real-time operation status of each control target device. Then, the real-time monitoring information is traversed and matched with the monitoring target features. Optionally, the similarity between the real-time monitoring information and the monitoring target features is calculated by using the cosine similarity calculation formula. When the similarity meets the threshold, the real-time monitoring information is marked with features using the corresponding monitoring target features.

[0051] Then, the abnormal equipment is located by feature annotation, and the number of feature annotations corresponding to the abnormal equipment is compared with the total number of corresponding real-time monitoring information, and the ratio is used as the abnormal probability. When the number of abnormal equipment located and the abnormal probability are either out of the preset range, an early warning message is sent.

[0052] In summary, the embodiments of the present application have at least the following technical effects: This application obtains the information of the target device to be controlled, including the coating machine identification code and the device communication port, by connecting to the intelligent control platform, so as to provide a basis for the subsequent simultaneous control of multiple devices. Then, the centralized control signal is obtained, and the target device signal is collected based on the centralized control signal, the coating machine identification code and the device communication port, and the receiving control signal of each target device is obtained, so as to achieve the goal of collecting the control signal reception status of different target devices. Then, the centralized control signal and the receiving control signal of each target device are used to perform window framing processing, analyze the device deviation characteristics, and achieve the goal of analyzing the reception deviation degree of different target devices. Then, when there is a device deviation characteristic, the device is located based on the device communication port, and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the receiving control signal and then enter the execution control stage. The technical effect of improving the control reliability and accuracy of each target device is achieved.

[0053] Embodiment 2 Based on the same inventive concept as the intelligent control method of the aluminum foil coating machine in the aforementioned embodiment, Figure 2 As shown, the present application provides an intelligent control system for an aluminum foil coating machine, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: The control target device information acquisition module 11 is used to connect to the intelligent control platform and obtain the control target device information, including the coating machine identification code and the device communication port; The receiving control signal obtaining module 12 is used to obtain the centralized control signal, collect the target device signal based on the centralized control signal, the coating machine identification code, and the device communication port, and obtain the receiving control signal of each target device; The device deviation feature analysis module 13 is used to perform window framing processing and analyze device deviation features by using the centralized control signal and the received control signal of each target device; The adjustment instruction sending module 14 is used to locate the device based on the device communication port when there is a device deviation feature, and send a signal deviation adjustment instruction, wherein the signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal before entering the execution control stage.

[0054] Furthermore, the device deviation feature analysis module 13 is used to perform the following steps: Setting a standard time analysis window, using the standard time analysis window to perform frame processing on the centralized control signal and the received control signal of each target device, and constructing a window signal set of each control signal; Based on the window signal set of each control signal, calculating the short-time energy entropy in each window signal; Calculating the short-time energy ratio according to the short-time energy entropy in the window signal to obtain the signal short-time energy entropy ratio; The device deviation characteristic is determined according to the signal short-time energy entropy ratio.

[0055] Furthermore, the device deviation feature analysis module 13 is used to perform the following steps: Aligning the centralized control signal and the receiving control signal of each target device according to a window order; According to the window alignment relationship, the first short-time energy entropy ratio of the window signal of each target device to the centralized control signal is calculated respectively; Calculating the second short-time energy entropy ratio of two consecutive windows according to the window timing relationship of the window signal set of each control signal; The first short-time energy entropy ratio and the second short-time energy entropy ratio are fused to obtain the signal short-time energy entropy ratio of each device.

[0056] Furthermore, the received control signal obtaining module 12 is used to perform the following steps: Acquire coating components, perform property analysis on the coating components, and obtain property characteristics, wherein the property characteristics include adhesion characteristics, cross-linking reaction characteristics, and chemical reaction characteristics; Decomposing and matching the process parameters based on the attribute characteristics to determine the degree of influence of each attribute characteristic on the process parameters; According to the influence of each attribute characteristic and process parameter, configure the process technology control target variable and control influence relationship; Control optimization is performed according to the process technology control target variables and control influence relationships to obtain control information of each process as the centralized control signal.

[0057] Furthermore, the received control signal obtaining module 12 is used to perform the following steps: Extracting an original control data set based on the attribute characteristics and process parameters; Clustering the original control data set according to attribute characteristics to obtain attribute characteristic sample clusters; Determine the relevant process according to the process mapping relationship between the attribute feature and the attribute feature sample cluster, perform influence relationship analysis of process control parameters according to the attribute feature sample cluster, and obtain control target variables, where the control target variables are process control parameters that have influence on the attribute feature; The control influence relationship is determined according to the influence degree of the attribute feature and the process parameter, and the control influence proportion of the attribute feature in the attribute feature sample cluster.

[0058] Furthermore, the received control signal obtaining module 12 is used to perform the following steps: Obtaining coating target performance, performing attribute characteristic target decomposition according to the coating target performance and coating composition, and determining attribute characteristic target values; According to the process technology control target variables and control influence relationships, a reaction effect evaluation function of the attribute characteristics is constructed, and the difference between the reaction effect evaluation value and the attribute characteristic target value is minimized as the optimization goal, and an optimization space is established; Iterative optimization of the control target variable is performed through the optimization space, and when the optimization target or iteration threshold is reached, the control information of each process is obtained.

[0059] Furthermore, the received control signal obtaining module 12 is used to perform the following steps: Obtain the process nodes that affect the cross-linking reaction characteristics and chemical reaction characteristics, distribute the proportions through the evaluation channels, and obtain the process node weights; Perform cross-linking reaction and chemical reaction target value analysis according to the coating target performance and coating composition to determine the reaction target; Add the reaction target as a constraint condition into the optimization space to obtain control information affecting the process nodes; Construct a timing chain according to the sequential relationship of the nodes that affect the process; The cross-linking reaction characteristics and chemical reaction characteristics of the coating material are used as the state quantity of the time series node, the process control parameters are used as the action quantity of the time series node, and the control influence relationship between the process control parameters and the cross-linking reaction characteristics and chemical reaction characteristics is used as the incentive quantity of the time series node to construct a Markov chain model. The Markov chain model is used to perform probability evaluation on the control information of each process, and when the reaction target probability is met, the control information of each process is fed back.

[0060] Furthermore, the adjustment instruction sending module 14 is used to perform the following steps: A monitoring module is provided, the monitoring module is connected to the intelligent control platform for communication, synchronous monitoring information is provided, and each control target device is controlled and monitored through the monitoring module. The monitoring module includes monitoring target features preset according to the centralized control signal, and the monitoring target features are abnormal process features obtained according to historical abnormal samples; Acquire real-time monitoring information, and perform traversal matching with the real-time monitoring information according to the monitoring target characteristics; When there is a matching relationship between the monitoring information and the monitoring target feature, feature marking is performed on the monitoring information; Abnormal equipment positioning and abnormal probability calculation are performed according to the feature annotations. When the abnormal equipment positioning and abnormal probability exceed the preset range, an early warning message is sent.

[0061] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0062] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0063] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The intelligent control method of aluminum foil coating machine is characterized by: The method is applied to a smart control platform, and the method comprises: Connect to the smart control platform to obtain the target device information, including the coating machine identification code and device communication port; Acquire a centralized control signal, and based on the centralized control signal, the coating machine identification code, and the device communication port, collect target device signals to obtain receiving control signals of each target device; Utilizing the centralized control signal and the receiving control signal of each target device, performing window framing processing and analyzing device deviation characteristics; When there is a device deviation feature, the device is positioned based on the device communication port and a signal deviation adjustment instruction is sent. The signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal before entering the execution control stage.

2. The method according to claim 1, characterized in that Utilizing the centralized control signal and the receiving control signal of each target device, performing window framing processing and analyzing device deviation characteristics include: Setting a standard time analysis window, using the standard time analysis window to perform frame processing on the centralized control signal and the received control signal of each target device, and constructing a window signal set of each control signal; Based on the window signal set of each control signal, calculating the short-time energy entropy in each window signal; Calculating the short-time energy ratio according to the short-time energy entropy in the window signal to obtain the signal short-time energy entropy ratio; The device deviation characteristic is determined according to the signal short-time energy entropy ratio.

3. The method according to claim 2, characterized in that According to the short-time energy entropy in the window signal, a short-time energy ratio is calculated to obtain the signal short-time energy entropy ratio, including: Aligning the centralized control signal and the receiving control signal of each target device according to a window order; According to the window alignment relationship, the first short-time energy entropy ratio of the window signal of each target device to the centralized control signal is calculated respectively; Calculating the second short-time energy entropy ratio of two consecutive windows according to the window timing relationship of the window signal set of each control signal; The first short-time energy entropy ratio and the second short-time energy entropy ratio are fused to obtain the signal short-time energy entropy ratio of each device.

4. The method according to claim 1, characterized in that The obtaining of the centralized control signal comprises: Acquire coating components, perform property analysis on the coating components, and obtain property characteristics, wherein the property characteristics include adhesion characteristics, cross-linking reaction characteristics, and chemical reaction characteristics; Decomposing and matching the process parameters based on the attribute characteristics to determine the degree of influence of each attribute characteristic on the process parameters; According to the influence of each attribute characteristic and process parameter, configure the process technology control target variable and control influence relationship; Control optimization is performed according to the process technology control target variables and control influence relationships to obtain control information of each process as the centralized control signal.

5. The method according to claim 4, characterized in that According to the influence of each attribute characteristic and process parameter, configure the process technology control target variables and control influence relationship, including: Extracting an original control data set based on the attribute characteristics and process parameters; Clustering the original control data set according to attribute characteristics to obtain attribute characteristic sample clusters; Determine the relevant process according to the process mapping relationship between the attribute feature and the attribute feature sample cluster, perform influence relationship analysis of process control parameters according to the attribute feature sample cluster, and obtain control target variables, where the control target variables are process control parameters that have influence on the attribute feature; The control influence relationship is determined according to the influence degree of the attribute feature and the process parameter, and the control influence proportion of the attribute feature in the attribute feature sample cluster.

6. The method according to claim 5, characterized in that According to the process control target variables and control influence relationships, control optimization is performed to obtain control information of each process, including: Obtaining coating target performance, performing attribute characteristic target decomposition according to the coating target performance and coating composition, and determining attribute characteristic target values; According to the process technology control target variables and control influence relationships, a reaction effect evaluation function of the attribute characteristics is constructed, and the difference between the reaction effect evaluation value and the attribute characteristic target value is minimized as the optimization goal, and an optimization space is established; Iterative optimization of the control target variable is performed through the optimization space, and when the optimization target or iteration threshold is reached, the control information of each process is obtained.

7. The method according to claim 6, characterized in that The method further comprises: Obtain the process nodes that affect the cross-linking reaction characteristics and chemical reaction characteristics, distribute the proportions through the evaluation channels, and obtain the process node weights; Perform cross-linking reaction and chemical reaction target value analysis according to the coating target performance and coating composition to determine the reaction target; Add the reaction target as a constraint condition into the optimization space to obtain control information affecting the process nodes; Construct a timing chain according to the sequential relationship of the nodes that affect the process; The cross-linking reaction characteristics and chemical reaction characteristics of the coating material are used as the state quantity of the time series node, the process control parameters are used as the action quantity of the time series node, and the control influence relationship between the process control parameters and the cross-linking reaction characteristics and chemical reaction characteristics is used as the incentive quantity of the time series node to construct a Markov chain model. The Markov chain model is used to perform probability evaluation on the control information of each process, and when the reaction target probability is met, the control information of each process is fed back.

8. The method according to claim 7, characterized in that The method further comprises: A monitoring module is provided, the monitoring module is connected to the intelligent control platform for communication, synchronous monitoring information is provided, and each control target device is controlled and monitored through the monitoring module. The monitoring module includes monitoring target features preset according to the centralized control signal, and the monitoring target features are abnormal process features obtained according to historical abnormal samples; Acquire real-time monitoring information, and perform traversal matching with the real-time monitoring information according to the monitoring target characteristics; When there is a matching relationship between the monitoring information and the monitoring target feature, feature marking is performed on the monitoring information; Abnormal equipment positioning and abnormal probability calculation are performed according to the feature annotations. When the abnormal equipment positioning and abnormal probability exceed the preset range, an early warning message is sent.

9. The intelligent control system of the aluminum foil coating machine is characterized by: The system comprises: The control target device information acquisition module is used to connect to the intelligent control platform and obtain the control target device information, including the coating machine identification code and the device communication port; A receiving control signal acquisition module is used to acquire a centralized control signal, collect target device signals based on the centralized control signal, the coating machine identification code, and the device communication port, and obtain a receiving control signal for each target device; A device deviation feature analysis module, used to perform window framing processing and analyze device deviation features by using the centralized control signal and the received control signal of each target device; The adjustment instruction sending module is used to locate the device based on the device communication port when there is a device deviation feature, and send a signal deviation adjustment instruction, wherein the signal deviation adjustment instruction is used to perform deviation correction preprocessing on the received control signal and then enter the execution control stage.

Images