A method and system for calculating pump speed of extrusion coating machine

Abstract

The present invention relates to the technical field of data processing, and in particular to a method and system for calculating the pump speed of an extrusion coating machine. The method comprises the following steps: performing a stirring simulation according to coating parameter data to generate slurry viscosity change data; performing mutation point marking according to the slurry viscosity change data to generate mutation point data; performing coating simulation and viscosity screening using characteristic demand data and mutation point data to generate preliminary screening mutation point data; performing flow rate convergence iterative simulation according to the preliminary screening mutation point data to generate coating flow rate data; performing viscosity convergence iterative simulation on the preliminary screening mutation point data based on the coating flow rate data to generate coating viscosity data; performing viscosity deviation correction on the coating viscosity data to generate actual coating viscosity data; performing pump speed evaluation according to the actual coating viscosity data and the coating flow rate data to generate coating pump speed data; the present invention uses coating simulation to save actual test resources and determine the coating pump speed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for calculating the pump speed of an extrusion coating machine. Background Art

[0002] Being able to accurately calculate the pump speed during the coating process and ensure that the coating material is evenly coated on the substrate surface at just the right speed is crucial to ensuring a good coating process. Accurately calculated pump speeds can save coating materials, reduce production costs, and avoid quality problems caused by excessive or insufficient coating. The application of pump speed calculation methods and systems provides an automated and precise solution, improves the stability and controllability of the coating process, and is of great significance to the coating production process in various industries. However, the existing extrusion coater pump speed calculation methods and systems still need to be simulated in an actual production environment, and in order to determine the final pump speed, it often takes a lot of manpower and material resources. Summary of the invention

[0003] Based on this, it is necessary to provide a method for calculating the pump speed of an extrusion coater to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for calculating the pump speed of an extrusion coating machine is provided, the method comprising the following steps:

[0005] Step S1: Acquire coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification correction based on the viscosity prediction data to generate slurry viscosity change data;

[0006] Step S2: Acquire coating requirement data of the article to be coated; use imaging equipment to image the required area of ​​the article to be coated to generate microscopic feature data; perform feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data;

[0007] Step S3: Use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening to generate preliminary screening mutation point data; perform flow rate convergence iterative simulation based on the preliminary screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the preliminary screening mutation point data based on the coating flow rate data to generate coating viscosity data;

[0008] Step S4: Acquire actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data and coating flow rate data to generate coating pump speed data; perform coating operation based on coating pump speed data to generate actual coating result data.

[0009] The present invention generates viscosity prediction data by acquiring coating material data and performing stirring simulation. It provides a key basis for predicting viscosity changes in the future coating process. Viscosity verification and correction based on viscosity prediction data ensures the accuracy and reliability of simulation data, thereby generating reliable slurry viscosity change data. It enables more accurate control of viscosity changes during the coating process to ensure coating quality and consistency. The imaging device is used to image the demand area of ​​the object to be coated to generate microscopic feature data. It helps to understand the demand differences in different regions and also provides a basis for targeted coating. The generation of characteristic demand data makes the coating process more personalized and accurate, and can meet the specific requirements of different regions. The marking of mutation point data helps to reduce the workload of the coating simulation process, because the initial simulation is only simulated based on the mutation point data to determine an approximate range. The coating simulation using characteristic demand data and mutation point data can simulate the needs and changes in different regions during the coating process. The generation of initial screening mutation point data helps to determine the focus of coating parameter adjustment. The coating flow rate data generated by the flow rate convergence iterative simulation provides a basis for flow rate adjustment, and more accurate flow rate data is obtained through continuous iteration of simulation. The viscosity convergence iterative simulation based on the coating flow rate data further improves the coating viscosity data to ensure the coating process. By analyzing the actual production environment data, the coating viscosity data is corrected to generate coating viscosity data that is more in line with the actual scene. The evaluation of the coating pump speed data is based on the actual coating viscosity and flow rate data, which provides an accurate basis for the selection of pump speed parameters. Finally, the coating operation is performed based on the coating pump speed data to generate actual coating result data, ensuring the accuracy and efficiency of the production process. Therefore, the extrusion coating machine pump speed calculation method and system of the present invention determines the change of slurry viscosity through stirring simulation, and then gradually determines each coating parameter through coating iterative simulation, and finally combines the actual test to calculate the final coating pump speed. In this way, through the simulation method, most of the test materials and test processes are saved, and it is ensured that the coating pump speed conforms to the actual extrusion coating process.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: obtaining coating material data;

[0012] Step S12: performing correlation analysis between characteristics according to the coating material data to generate component viscosity correlation data;

[0013] Step S13: using a numerical simulation method to simulate the stirring process of the component viscosity correlation data to generate stirring process data;

[0014] Step S14: Establishing a multivariate change relationship based on the stirring process data to generate viscosity prediction data;

[0015] Step S15: performing random viscosity test verification according to the viscosity prediction data to generate test result data;

[0016] Step S16: Based on the test result data, the multivariate change evaluation data is corrected for deviations to generate slurry viscosity change data.

[0017] The present invention provides necessary basic information for the coating process by acquiring coating material data, so that the behavior and characteristics of the material in the coating process can be predicted more accurately. The correlation analysis between characteristics takes into account the interaction between different components, such as the influence of different material components on the coating viscosity. In order to obtain a more stable and controllable coating viscosity. The stirring process is simulated for the component viscosity correlation data using a numerical simulation method to generate stirring process data. This simulation takes into account the interaction and change of components during the stirring process, as well as the change of viscosity during the stirring process. It helps to understand the mixing of materials during the stirring process and provide quantitative predictions for viscosity changes. The establishment of multivariate change relationships helps to more accurately predict the viscosity of the coating material. By establishing multivariate change relationships based on the stirring process data, the comprehensive influence of different factors on viscosity can be understood. The multivariate relationship can include the relationship between multiple variables such as temperature, stirring speed, and sedimentation time, providing more comprehensive and accurate results for the prediction of viscosity, and improving the predictability and stability of the coating process. Experimental data is provided by random viscosity tests, and compared and analyzed with simulation results to verify the accuracy and reliability of the model. It helps to verify the applicability of viscosity prediction results. Based on the test results, the viscosity prediction data is corrected to generate the slurry viscosity change data. The corrected data can better reflect the actual viscosity change and provide a more reliable basis for the optimization of coating process parameters.

[0018] Preferably, step S2 comprises the following steps:

[0019] Step S21: obtaining coating requirement data of the object to be coated;

[0020] Step S22: using an imaging device to image the required area of ​​the object to be coated to generate an image of the surface to be coated;

[0021] Step S23: performing microscopic feature evaluation on the surface image to be coated to generate microscopic feature data; performing feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data;

[0022] Step S24: Visualize the slurry viscosity change data to generate a multivariate viscosity change graph;

[0023] Step S25: Mark the mutation points according to the multivariate viscosity change diagram to generate mutation point data.

[0024] The present invention obtains coating requirement data of the object to be coated, such as surface characteristics, shape, size, roughness and other information of the coating area. These data provide guidance for the coating process, help determine coating parameters and methods, and ensure the accuracy and consistency of coating. The imaging device is used to image the required area of ​​the object to be coated, and the surface characteristics of the object to be coated are intuitively displayed in the form of images. The imaged surface information helps to understand the characteristics and requirements of the surface of the object more accurately. The microscopic feature evaluation of the surface image to be coated is performed to generate microscopic feature data. These microscopic feature data may include detailed features such as texture, concave-convex, color, shape, etc. of the surface of the object. Based on these feature data, the coating requirements are feature-labeled to generate feature requirement data. The coating process is made more in line with the characteristics of the surface of the object, and the accuracy and efficiency of coating are improved. Visual processing presents the slurry viscosity change data as a multivariate viscosity change diagram. This graphical presentation method helps to intuitively show the change law of viscosity under different conditions. Through the graphical display, the trend of viscosity as different parameters and conditions change, such as the influence of factors such as temperature, time, stirring speed, etc. on viscosity, can be clearly observed. The mutation points in the viscosity change graph are marked and identified, representing the critical points where the viscosity changes sharply. Identifying the mutation points helps determine the key factors or stages that affect the viscosity change, such as whether there is a staged viscosity change when the temperature rises or whether there is a significant viscosity mutation when the stirring speed changes.

[0025] Preferably, step S3 comprises the following steps:

[0026] Step S31: using the characteristic demand data and the mutation point data to perform the initial coating simulation and generate multi-point simulation result data;

[0027] Step S32: selecting the optimal simulation results according to the multi-point simulation result data to generate the optimal initial simulation data;

[0028] Step S33: Screening corresponding mutation points based on the optimal initial simulation data to generate initial screening mutation point data;

[0029] Step S34: performing a flow rate change coating simulation based on the initial screening mutation point data to generate multiple flow rate simulation data; performing a convergence iterative simulation based on the multiple flow rate simulation data to generate coating flow rate data;

[0030] Step S35: Screening simulation data based on the coating flow rate data to generate simulation coating result data; using the valve control times calculation formula and evaluating the difference in thickness between the head and the tail according to the simulation coating result data to generate valve switch control data;

[0031] Step S36: Based on the coating flow rate data and the valve switch control data, the initial screening mutation point data is subjected to viscosity convergence iterative simulation to generate the best coating result data; based on the best coating result data, the slurry viscosity interval analysis is performed to generate coating viscosity data.

[0032] The present invention simulates a plurality of possible coating results by simulating the coating process, combining demand data and mutation point data. These simulation results cover situations under different coating parameters and conditions, which are helpful to understand the influence of different parameters on the coating results in the simulation stage, and reduce the range of slurry viscosity according to the results. According to the coating requirements and expected results, the simulation results are evaluated and screened, and high-quality, high-quality simulation data that meets the requirements are selected. This superior simulation data helps to focus on the simulation results that meet the requirements, reduces the subsequent screening work, and improves the accuracy and availability of the simulation results. The mutation key points that meet the expected residual effect in the simulation are screened out, thereby narrowing the suitable slurry viscosity. Identifying these mutation points helps to understand which parameters or conditions will cause important changes in the coating results during the simulation process, so as to carry out subsequent parameter adjustments and optimizations in a targeted manner. For the mutation points screened for the first time, the flow rate is changed for coating simulation, and simulation results under a variety of different flow rates are generated. It helps to understand the influence of different flow rates on the coating results and provide a basis for selecting the optimal flow rate. Next, a convergent iterative simulation is performed based on these multi-flow rate simulation data to generate more accurate and stable coating flow rate data, making the coating process more controllable and efficient. The initial simulation results are screened according to the coating flow rate data, and the simulated coating result data with high quality and meeting the requirements are selected. Based on the simulation results and the valve control number calculation formula, the difference in thickness at the beginning and end of the coating is evaluated to provide important data support for valve control and ensure the uniformity and consistency of the coating. Combining the flow rate data, valve control data and the mutation point data of the initial screening, the coating parameters are further optimized and iterated to generate the best coating result data. At the same time, the slurry viscosity range analysis based on the best coating result data helps to understand the range of changes in slurry viscosity during the coating process.

[0033] Preferably, step S34 includes the following steps:

[0034] Step S341: Perform flow rate change coating simulation according to the initial screening mutation point data to generate multi-flow rate simulation data;

[0035] Step S342: selecting the highest flow rate according to the multi-flow rate simulation data to generate high flow rate range data; clustering the high flow rate range data to generate aggregated flow rate distribution data;

[0036] Step S343: performing range convergence iterative simulation based on the aggregated flow velocity distribution data to generate convergence simulation result data;

[0037] Step S344: performing an optimal coating effect evaluation according to the convergence simulation result data to generate flow rate convergence effect data;

[0038] Step S345: Select the optimal flow rate based on the flow rate convergence effect data to generate coating flow rate data.

[0039] The present invention generates a series of coating results by simulating under different flow rate conditions. These simulation data cover the coating effects under different flow rate conditions, which are helpful to identify the flow rate range that is most suitable for the coating process, that is, the upper limit condition of the flow rate. For the coating process, determining the highest flow rate range can avoid the flow rate conditions that exceed the equipment or material capacity, and ensure the stability of the coating process and the uniformity of the material. Subsequently, the high flow rate range data is clustered to generate aggregate flow rate distribution data. This aggregate flow rate distribution data can classify and integrate different conditions within the high flow rate range, help understand the distribution of flow rate, and provide guidance for the optimization of coating parameters. By iteratively simulating the aggregate flow rate distribution data, find the optimal simulation result that converges within the flow rate range. Through the iterative simulation process, the coating flow rate range can be gradually adjusted so that the simulation results are more convergent and stable. Such convergent simulation result data can provide more accurate and stable coating effect predictions. The convergent simulation results are comprehensively evaluated and screened to select data with better coating effects. Through this evaluation process, the simulation data with the best coating flow rate range can be identified, providing strong support for the final flow rate selection. Based on the previous evaluation and screening results, the optimal coating flow rate conditions are determined. By analyzing the convergence effect data, the optimal range of coating flow rates is determined to ensure the best effect and stability during the coating process.

[0040] Preferably, the calculation formula for the valve control times in step S35 is as follows:

[0041]

[0042] Where N is the number of valve controls, L is the required coating length, H is the thickness difference between the head and the tail, V H is the thickness change rate at the head and tail, A is the simulated coating speed, B is the simulated slurry flow, C is the simulated roller speed, D is the required coating thickness, t1 is the coating start time, t2 is the coating end time, K is the valve control sensitivity, e is the base of the natural logarithm, t is the time variable value, It is the deviation correction value of valve control times.

[0043] The present invention provides a valve control times calculation formula, which is used to evaluate the difference between the head and tail thickness according to the simulated coating result data and generate valve switch control data. The formula fully considers the coating required length L, the difference between the head and tail thickness H, and the head and tail thickness change rate V. H, simulated coating speed A, simulated slurry flow B, simulated roller speed C, coating required thickness D, coating start time t1, coating end time t2, valve control sensitivity K, natural logarithm base e, time variable value t, valve control times deviation correction value And the interaction relationship between parameters constitutes the functional relationship:

[0044]

[0045] By considering the effect of coating required length L and thickness difference value H at the head and tail. If coating length increases, more control is needed to maintain coating consistency. At the same time, if the thickness difference at the head and tail increases, more adjustments are needed to ensure coating quality. However, these two factors may affect each other. For example, increasing coating length may result in more material supply, thus affecting the thickness difference at the head and tail. If V H As D increases, the coating system needs to adjust more quickly to maintain stability. But this also depends on other factors, such as the simulated coating speed A. A high coating speed means more frequent adjustments are needed. The interaction between the coating requirement thickness D and the coating flow rate A will also affect the number of valve controls. If D increases, more material and more frequent adjustments are required to meet the coating needs, especially when A increases. The slurry flow rate usually represents the amount of material used in the coating process. The square of B amplifies the impact of the simulated slurry flow rate on the result, where a higher roller speed may result in more uniform coating or a higher coating speed. The proportional relationship between the coating requirement thickness and the slurry flow rate and roller speed takes into account the effect of the coating thickness on the coating flow rate and coating uniformity. The integral term in the formula Represents the cumulative effect over time. It is often used to describe the historical dependence of coating control. In other words, it reflects the impact of adjustments made by the coating system in the past on the current control decision. For example, if past adjustments took a long time to reach a stable state, then the current control may require more adjustments to ensure stable coating. K is a control sensitivity parameter, which represents the degree of influence of the sensitivity of the valve switch adjustment on the system. Exponential decay e ―t It means that the influence of past control intervention on the current state gradually weakens over time. This formula provides a numerical standard for the evaluation of the difference between the head and tail thickness, and serves as one of the bases for generating valve switch control data, which helps to optimize the control and adjustment during the coating process. At the same time, the valve control sensitivity and deviation correction value in the formula can be corrected according to the actual simulation situation to adapt to the coating valve control calculation of different substrates, which improves the flexibility and applicability of the formula.

[0046] Preferably, step S4 comprises the following steps:

[0047] Step S41: acquiring actual production environment data; performing viscosity deviation correction on coating viscosity data based on the actual production environment data to generate actual coating viscosity data;

[0048] Step S42: using the coating pump speed calculation formula and performing pump speed evaluation according to the actual coating viscosity data and coating flow rate data to generate coating pump speed data;

[0049] Step S43: adjusting the coating pressure according to the microscopic characteristic data to generate coating pressure differentiation data;

[0050] Step S44: performing an actual environmental test according to the coating pump speed data and the coating pressure differentiation data to generate coating test result data;

[0051] Step S45: performing deviation analysis on the coating experiment result data based on the coating requirement data to generate test deviation data; performing coating parameter correction based on the test deviation data to generate coating parameter data;

[0052] Step S46: Perform coating operation according to the coating parameter data to generate actual coating result data.

[0053] The present invention corrects the coating viscosity data previously simulated or calculated by actual production environment data. By feedback of actual data, the coating viscosity is corrected, so that the simulation and calculation results are closer to the actual situation, and the accuracy and controllability of the coating process are improved. Based on the calculation formula of the coating pump speed, the pump speed required for coating is evaluated and calculated in combination with the actual viscosity data and flow rate data. This process can dynamically adjust the pump speed according to the actual data to ensure the stability and accuracy of the coating flow. The pressure in the coating process is adjusted by using microscopic feature data, and the pressure applied during coating is adjusted according to the surface characteristics of the object and the coating requirements. This step enables the coating pressure to be more in line with the actual coating requirements, and improves the accuracy and efficiency of the coating process. Through actual coating tests, the coating pump speed and pressure conditions previously determined are simulated in a real production environment. The data collected through the test can be fed back to the adjustment and optimization of the coating parameters, ensuring that the actual coating conditions match the parameters previously simulated, and improving the reliability and controllability of the experiment. By analyzing the differences and deviations between the experimental data and the coating requirement data, the problems and deviations in the coating process are identified. Through these deviation data, the coating parameters can be adjusted and corrected to ensure that the coating process is more in line with the requirements and improve the accuracy and consistency of the coating. The actual coating operation is carried out based on the adjusted and corrected coating parameters. The actual coating result data obtained is obtained after parameter adjustment and optimization, ensuring that the actual coating effect meets the expected requirements and improving the accuracy and stability of the coating process.

[0054] Preferably, the coating pump speed calculation formula in step S42 is as follows:

[0055]

[0056] In the formula, v p is the coating pump speed, v0 is the original coating pump speed, μ is the actual coating viscosity, d is the required coating width, a h is the actual air humidity, η is the slurry shear viscosity, ρ is the slurry density, D is the required coating thickness, V S is the substrate moving speed, V C is the coating flow rate, is the partial derivative of the slurry shear viscosity with respect to the required coating thickness, and ω is the deviation correction value of the coating pump speed.

[0057] The present invention provides a coating pump speed calculation formula, which is used to evaluate the pump speed according to the actual coating viscosity data and the coating flow rate data, and generate coating pump speed data. The formula fully considers the original coating pump speed v0, the actual coating viscosity μ, the coating required width d, the actual air humidity a h , slurry shear viscosity η, slurry density ρ, coating thickness D, substrate moving speed V S , coating flow rate V C , the partial derivative of the slurry shear viscosity with respect to the required coating thickness The deviation correction value ω of the coating pump speed and the interaction relationship between variables constitute a functional relationship:

[0058]

[0059] Through the interaction between the required coating width and the actual air humidity, the coating pump speed can be adjusted according to different environmental conditions and requirements to obtain better coating quality and efficiency. When the original coating pump speed increases, if the actual coating viscosity also increases, the product of the numerator will increase, driving the increase in the coating pump speed. This interaction ensures a higher pump speed at high viscosity to maintain coating quality. A larger required coating width may cause the actual coating viscosity to have a more significant effect in the formula, which means that a higher coating pump speed is required to ensure that the entire width is properly coated. The actual air humidity affects the coating pump speed through a logarithmic function. High humidity may have a negative effect on the coating effect. For example, the higher the humidity, the easier it is for the coating to work, which indirectly affects the coating pump speed. By comprehensively considering the relationship between the flow characteristics of the slurry, the size of the coating requirement and the coating speed. Through this interaction, the coating pump speed can be adjusted according to the properties of the slurry and the coating conditions to ensure the consistency of the coating thickness and coating quality. The coating pump speed is adjusted according to the rate of change of the required coating thickness and the substrate speed. The partial derivative of the slurry shear viscosity with respect to the required coating thickness represents the change of the slurry during the coating process. By considering this change and the relationship between the substrate speed and the coating flow rate, the coating pump speed can be adjusted to better control the shear force and viscosity changes, thereby achieving a more stable and uniform coating. This formula combines factors such as the actual coating viscosity and the coating flow rate, and does not rely solely on the evaluation of a single factor. It helps to more accurately predict the required coating pump speed and avoid errors caused by ignoring certain factors. At the same time, the deviation correction value of the actual air humidity and the coating pump speed in the formula can be corrected according to the actual coating process to adapt to different coating environments.

[0060] Preferably, step S43 includes the following steps:

[0061] Step S431: Acquire diversified micro data; perform correlation feature analysis based on the diversified micro data to generate correlated micro feature data;

[0062] Step S432: performing multi-pressure coating simulation according to the associated micro-feature data to generate multi-pressure simulation data;

[0063] Step S433: performing coating pressure commonality evaluation based on the multi-pressure simulation data to generate characteristic pressure correlation data;

[0064] Step S434: performing convergence simulation based on the characteristic pressure correlation data to generate characteristic pressure change data; performing visualization processing on the characteristic pressure change data to generate a characteristic pressure curve;

[0065] Step S435: performing pressure matching on the characteristic pressure curve based on the microscopic characteristic data to generate coating pressure matching data;

[0066] Step S436: Setting the coating pressure according to the coating pressure matching data to generate coating pressure differentiation data.

[0067] The present invention collects diversified microscopic data, which may include various data such as surface features of objects and material properties, and analyzes and extracts related features. These related microscopic feature data can help identify the correlation and commonality between different microscopic features, providing a deeper understanding and basis for the further coating process. Multi-pressure simulation data can help understand the influence of different pressures on the coating process, as well as the optimal selection of pressure under different microscopic features, and provide more parameter selection and optimization schemes for the coating process. Through the analysis and evaluation of multi-pressure simulation data, the common features under different pressure conditions can be identified, and the correlation and optimization direction of the coating pressure can be found. These characteristic pressure correlation data can provide more guidance for the selection of coating pressure, so that the pressure parameters are more in line with the coating requirements of different microscopic features, and improve the adaptability and flexibility of the coating process. Use characteristic pressure correlation data for simulation to generate characteristic change data under pressure conditions. This convergence simulation helps to understand the influence of different pressures on microscopic features, and provides characteristic data under pressure changes, which provides an important basis for the optimization of the coating process. The characteristic pressure change data is presented as a curve chart by a visualization method. This visualization helps to intuitively show the influence trend of pressure on microscopic features, providing an intuitive basis for further analysis. The characteristic pressure curve is analyzed and matched using microscopic feature data to obtain more appropriate coating pressure data. Such a matching process helps to determine the optimal pressure conditions to be used in the coating process based on specific microscopic features. Using the matched coating pressure data, coating pressure conditions suitable for different microscopic features are set. Such data generation makes the pressure setting in the coating process more accurate and can better meet the needs of different surface features of objects.

[0068] The present invention also provides an extrusion coating machine pump speed calculation system, which is used to execute the extrusion coating machine pump speed calculation method as described above, comprising:

[0069] The slurry stirring simulation module is used to obtain coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification and correction based on viscosity prediction data to generate slurry viscosity change data;

[0070] The coating demand analysis module is used to obtain the coating demand data of the object to be coated; use the imaging device to image the demand area of ​​the object to be coated to generate microscopic feature data; perform feature annotation on the coating demand data based on the microscopic feature data to generate feature demand data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data;

[0071] The coating parameter analysis module is used to use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening, and generate the initial screening mutation point data; perform flow rate convergence iterative simulation based on the initial screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the initial screening mutation point data based on the coating flow rate data to generate coating viscosity data;

[0072] The actual coating operation module is used to obtain actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data to generate coating pump speed data; adjust coating pressure through micro-feature data to generate coating pressure differentiation data; perform coating operations based on coating pump speed data and coating pressure differentiation data to generate actual coating result data.

[0073] The beneficial effect of the present application is that the present invention can determine the predicted viscosity of the coating material at different time points, temperatures, or stirring speeds by simulating the stirring process. Such viscosity prediction data is based on the simulation of material properties and stirring conditions, and can predict the change trend of the viscosity of the coating material in advance. The purpose of viscosity verification and correction based on the viscosity prediction data is to calibrate the accuracy of the prediction data. In actual situations, the viscosity prediction may be affected by experimental errors or simulation conditions. Through the verification and correction process, the prediction data can be corrected and adjusted through experimental data to generate more accurate and reliable slurry viscosity change data. These data provide more accurate material viscosity information for the coating process to ensure accurate control of viscosity during the coating process. The microscopic features of the object are obtained by imaging equipment in order to understand the characteristics of the object surface in more detail. These features may include surface texture, pore properties or other microscopic details. After generating the microscopic feature data, feature annotation is performed in combination with the coating requirement data to generate feature requirement data. Such data makes the coating process more personalized, and the coating scheme is tailored according to the specific microscopic features of the object. The mutation point marking according to the slurry viscosity change data is to identify the key points that may exist in the coating process. Breakpoint markers can help identify locations where material viscosity or other properties change dramatically under specific coating conditions. Breakpoint markers help adjust coating parameters more accurately to adapt to changes in material properties, thereby improving coating efficiency and quality. Coating simulation and viscosity screening help narrow the range of slurry viscosities that meet coating effects, thereby reducing subsequent simulation processes. Through iterative simulation, the coating flow rate can be gradually adjusted to make it tend to the optimal coating flow rate under specific conditions. Help optimize the coating process to ensure uniformity and consistency of materials during coating. Through viscosity convergence iterative simulation, simulate different combinations of viscosities and flow rates to obtain the optimal coating viscosity, thereby ensuring the adaptability and quality of materials during the coating process. Correct the previously simulated coating viscosity based on actual conditions to more accurately reflect the viscosity changes under real production conditions. Help improve the stability and controllability of the coating process. Determine the optimal pump speed setting based on the actual viscosity and flow rate conditions for more accurate coating control. Therefore, the extrusion coating machine pump speed calculation method and system of the present invention determines the change of slurry viscosity through stirring simulation, and then gradually determines each coating parameter through coating iteration simulation, and finally calculates the final coating pump speed in combination with actual test. In this way, most of the test materials and test processes are saved through the simulation method, and it is ensured that the coating pump speed conforms to the actual extrusion coating process. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic flow chart of the steps of a method for calculating the pump speed of an extrusion coating machine;

[0075] Figure 2 for Figure 1Detailed implementation steps of step S2 in the flowchart;

[0076] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0077] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0078] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0079] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0080] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0081] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0082] To achieve this, please refer to Figures 1 to 4 , a method for calculating the pump speed of an extrusion coating machine, the method comprising the following steps:

[0083] Step S1: Acquire coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification correction based on the viscosity prediction data to generate slurry viscosity change data;

[0084] Step S2: Acquire coating requirement data of the article to be coated; use imaging equipment to image the required area of ​​the article to be coated to generate microscopic feature data; perform feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data;

[0085] Step S3: Use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening to generate preliminary screening mutation point data; perform flow rate convergence iterative simulation based on the preliminary screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the preliminary screening mutation point data based on the coating flow rate data to generate coating viscosity data;

[0086] Step S4: Acquire actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data and coating flow rate data to generate coating pump speed data; perform coating operation based on coating pump speed data to generate actual coating result data.

[0087] The present invention generates viscosity prediction data by acquiring coating material data and performing stirring simulation. It provides a key basis for predicting viscosity changes in the future coating process. Viscosity verification and correction based on viscosity prediction data ensures the accuracy and reliability of simulation data, thereby generating reliable slurry viscosity change data. It enables more accurate control of viscosity changes during the coating process to ensure coating quality and consistency. The imaging device is used to image the demand area of ​​the object to be coated to generate microscopic feature data. It helps to understand the demand differences in different regions and also provides a basis for targeted coating. The generation of characteristic demand data makes the coating process more personalized and accurate, and can meet the specific requirements of different regions. The marking of mutation point data helps to reduce the workload of the coating simulation process, because the initial simulation is only simulated based on the mutation point data to determine an approximate range. The coating simulation using characteristic demand data and mutation point data can simulate the needs and changes in different regions during the coating process. The generation of initial screening mutation point data helps to determine the focus of coating parameter adjustment. The coating flow rate data generated by the flow rate convergence iterative simulation provides a basis for flow rate adjustment, and more accurate flow rate data is obtained through continuous iteration of simulation. The viscosity convergence iterative simulation based on the coating flow rate data further improves the coating viscosity data to ensure the coating process. By analyzing the actual production environment data, the coating viscosity data is corrected to generate coating viscosity data that is more in line with the actual scene. The evaluation of the coating pump speed data is based on the actual coating viscosity and flow rate data, which provides an accurate basis for the selection of pump speed parameters. Finally, the coating operation is performed based on the coating pump speed data to generate actual coating result data, ensuring the accuracy and efficiency of the production process. Therefore, the extrusion coating machine pump speed calculation method and system of the present invention determines the change of slurry viscosity through stirring simulation, and then gradually determines each coating parameter through coating iterative simulation, and finally combines the actual test to calculate the final coating pump speed. In this way, through the simulation method, most of the test materials and test processes are saved, and it is ensured that the coating pump speed conforms to the actual extrusion coating process.

[0088] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for calculating the pump speed of an extrusion coating machine according to the present invention. In this example, the method for calculating the pump speed of an extrusion coating machine comprises the following steps:

[0089] Step S1: Acquire coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification correction based on the viscosity prediction data to generate slurry viscosity change data;

[0090] In an embodiment of the present invention, parameter data of the coating material, including viscosity, composition, etc., are collected and sorted. The obtained coating material parameter data is used to perform stirring simulation, and a suitable simulation method (e.g., computational fluid dynamics simulation) is used to predict the viscosity change under different parameters. The viscosity prediction data generated based on the stirring simulation is verified and corrected. For example, the simulation data is compared with the actual measurement data to verify the accuracy of the model and make necessary corrections. Based on the viscosity verification and corrected data, the viscosity change data of the slurry is generated. These data are generated based on the verified model results and can describe the change in slurry viscosity under different conditions (e.g., different temperatures, pressures, compositions, etc.).

[0091] Step S2: Acquire coating requirement data of the article to be coated; use imaging equipment to image the required area of ​​the article to be coated to generate microscopic feature data; perform feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data;

[0092] In an embodiment of the present invention, relevant demand data of the object to be coated, such as size, shape, coating position, etc., are collected and sorted. An imaging device (such as a camera, a scanner, etc.) is used to image the object to be coated, and detailed image data of the coating area is obtained. Based on the imaging data of the coating area, image processing and analysis are performed to extract microscopic feature data, such as surface roughness, shape characteristics, etc. In combination with the microscopic feature data and the coating requirement data, the image is annotated and feature matched to generate feature requirement data, which can describe the characteristics and coating requirements of different areas. The slurry viscosity change data is marked with mutation points to indicate the mutation points of the material viscosity change that occur under different conditions.

[0093] Step S3: Use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening to generate preliminary screening mutation point data; perform flow rate convergence iterative simulation based on the preliminary screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the preliminary screening mutation point data based on the coating flow rate data to generate coating viscosity data;

[0094] In an embodiment of the present invention, coating simulation is performed by utilizing characteristic demand data and mutation point data. This simulation simulates the coating process based on the characteristic demand of the coated article and the mutation point of the material viscosity. In the coating simulation, a preliminary screening is performed to obtain the viscosity change points with better coating effects, and the corresponding mutation point data are marked, thereby converging the viscosity range and reducing the subsequent coating simulation process. Based on the initial screening mutation point data, the flow rate is simulated and iterated to converge to the appropriate coating flow rate data. The simulation at this stage can be performed through computational models and numerical methods in fields such as fluid dynamics. On the basis of the convergence of the flow rate, the coating viscosity is simulated and iterated based on the coating flow rate data. This involves a viscosity change model and fluid simulation to obtain coating viscosity data that adapts to the flow rate.

[0095] Step S4: Acquire actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data and coating flow rate data to generate coating pump speed data; perform coating operation based on coating pump speed data to generate actual coating result data.

[0096] In an embodiment of the present invention, actual data during the coating process is obtained, including information on environmental factors, material properties, etc. The previously calculated coating viscosity data is corrected based on the actual production environment data. This correction, for example, fine-tunes the stirring process of the slurry based on the temperature, humidity or other process factors in the actual environment to obtain a slurry viscosity suitable for the actual environment. The pump speed is evaluated based on the corrected coating viscosity data and coating flow rate data to determine the coating pump speed data that best suits the actual production environment. These pump speed data are used to perform actual coating operations to generate actual coating result data.

[0097] Preferably, step S1 comprises the following steps:

[0098] Step S11: obtaining coating material data;

[0099] Step S12: performing correlation analysis between characteristics according to the coating material data to generate component viscosity correlation data;

[0100] Step S13: using a numerical simulation method to simulate the stirring process of the component viscosity correlation data to generate stirring process data;

[0101] Step S14: Establishing a multivariate change relationship based on the stirring process data to generate viscosity prediction data;

[0102] Step S15: performing random viscosity test verification according to the viscosity prediction data to generate test result data;

[0103] Step S16: Based on the test result data, the multivariate change evaluation data is corrected for deviations to generate slurry viscosity change data.

[0104] The present invention provides necessary basic information for the coating process by acquiring coating material data, so that the behavior and characteristics of the material in the coating process can be predicted more accurately. The correlation analysis between characteristics takes into account the interaction between different components, such as the influence of different material components on the coating viscosity. In order to obtain a more stable and controllable coating viscosity. The stirring process is simulated for the component viscosity correlation data using a numerical simulation method to generate stirring process data. This simulation takes into account the interaction and change of components during the stirring process, as well as the change of viscosity during the stirring process. It helps to understand the mixing of materials during the stirring process and provide quantitative predictions for viscosity changes. The establishment of multivariate change relationships helps to more accurately predict the viscosity of the coating material. By establishing multivariate change relationships based on the stirring process data, the comprehensive influence of different factors on viscosity can be understood. The multivariate relationship can include the relationship between multiple variables such as temperature, stirring speed, and sedimentation time, providing more comprehensive and accurate results for the prediction of viscosity, and improving the predictability and stability of the coating process. Experimental data is provided by random viscosity tests, and compared and analyzed with simulation results to verify the accuracy and reliability of the model. It helps to verify the applicability of viscosity prediction results. Based on the test results, the viscosity prediction data is corrected to generate the slurry viscosity change data. The corrected data can better reflect the actual viscosity change and provide a more reliable basis for the optimization of coating process parameters.

[0105] In an embodiment of the present invention, relevant data of the coating material are collected, including but not limited to data such as component content, viscosity, density, temperature, pH value, etc. Correlation analysis (such as Pearson correlation coefficient) is used to measure the linear correlation between the characteristics. In addition, non-parametric methods such as Spearman correlation coefficient can be considered, especially when the data does not satisfy the normal distribution. For the complex relationship between the characteristics, regression analysis is used to explore the functional relationship between the variables. This may involve simple linear regression, multivariate linear regression or other types of regression models to understand the possible relationship between the components and viscosity. Analyze the statistical results, understand the relationship between the characteristics, and explain the validity and reliability of the model. Extract the key correlation, especially the correlation with the viscosity of the components, and evaluate its impact on the coating process to generate component viscosity correlation data. Based on the component viscosity correlation data, numerical simulation methods (such as computational fluid dynamics simulation, finite element analysis, etc.) are used to simulate the behavior of the coating material during the stirring process. This can include simulations under different stirring speeds, times, temperatures, etc., as well as simulations of the effects of different component ratios on viscosity. Use mathematical or statistical models to consider the relationship between multiple variables, especially factors related to viscosity. Predict the effects of different factors on viscosity through mathematical modeling and data fitting. Use regression analysis, neural networks, random forests, etc. to establish relationship analysis to generate viscosity prediction data that can predict viscosity based on stirring process data. Set the extraction ratio, randomly extract data from the viscosity prediction data according to the extraction ratio, and conduct stirring tests according to the corresponding stirring conditions and component ratios to verify the accuracy of the viscosity prediction data. Use statistical analysis methods (such as analysis of variance, t-test, etc.) to evaluate the difference between the predicted value and the actual measured value. Analyze the difference between the test results and the predicted value. If there is a deviation, further analysis of the cause is required, such as model assumptions, experimental errors, or insufficient data collection. According to the results of the deviation analysis, the viscosity prediction model is corrected or optimized to obtain more accurate prediction results. It may be necessary to retrain the model and introduce more or more accurate data.

[0106] Preferably, step S2 comprises the following steps:

[0107] Step S21: obtaining coating requirement data of the object to be coated;

[0108] Step S22: using an imaging device to image the required area of ​​the object to be coated to generate an image of the surface to be coated;

[0109] Step S23: performing microscopic feature evaluation on the surface image to be coated to generate microscopic feature data; performing feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data;

[0110] Step S24: Visualize the slurry viscosity change data to generate a multivariate viscosity change graph;

[0111] Step S25: Mark the mutation points according to the multivariate viscosity change diagram to generate mutation point data.

[0112] The present invention obtains coating requirement data of the object to be coated, such as surface characteristics, shape, size, roughness and other information of the coating area. These data provide guidance for the coating process, help determine coating parameters and methods, and ensure the accuracy and consistency of coating. The imaging device is used to image the required area of ​​the object to be coated, and the surface characteristics of the object to be coated are intuitively displayed in the form of images. The imaged surface information helps to understand the characteristics and requirements of the surface of the object more accurately. The microscopic feature evaluation of the surface image to be coated is performed to generate microscopic feature data. These microscopic feature data may include detailed features such as texture, concave-convex, color, shape, etc. of the surface of the object. Based on these feature data, the coating requirements are feature-labeled to generate feature requirement data. The coating process is made more in line with the characteristics of the surface of the object, and the accuracy and efficiency of coating are improved. Visual processing presents the slurry viscosity change data as a multivariate viscosity change diagram. This graphical presentation method helps to intuitively show the change law of viscosity under different conditions. Through the graphical display, the trend of viscosity as different parameters and conditions change, such as the influence of factors such as temperature, time, stirring speed, etc. on viscosity, can be clearly observed. The mutation points in the viscosity change graph are marked and identified, representing the critical points where the viscosity changes sharply. Identifying the mutation points helps determine the key factors or stages that affect the viscosity change, such as whether there is a staged viscosity change when the temperature rises or whether there is a significant viscosity mutation when the stirring speed changes.

[0113] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0114] Step S21: obtaining coating requirement data of the object to be coated;

[0115] In the embodiment of the present invention, by clarifying the coating requirements and technical specifications of the object to be coated, including the coating thickness, the size of the coating area, the type of coating material required, etc., basic information of the object, such as size, material, and manufacturing process requirements, is collected to serve as the basis for subsequent coating demand data.

[0116] Step S22: using an imaging device to image the required area of ​​the object to be coated to generate an image of the surface to be coated;

[0117] In the embodiment of the present invention, by selecting a suitable imaging device, such as an optical camera, a scanner or other visual imaging device according to the properties of the object, the object is imaged to ensure that the coating required area is covered and a high-quality surface image is obtained.

[0118] Step S23: performing microscopic feature evaluation on the surface image to be coated to generate microscopic feature data; performing feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data;

[0119] In the embodiment of the present invention, the image is processed by using image processing software or algorithm to extract microscopic feature information, such as texture, surface morphology, particle size, etc. Various features are extracted from the image using image processing technology and feature extraction algorithm, and converted into numerical data form. According to the extracted microscopic feature data, the coating requirement data is annotated. The microscopic features are matched with specific coating requirements to generate a feature requirement data set.

[0120] Step S24: Visualize the slurry viscosity change data to generate a multivariate viscosity change graph;

[0121] In the embodiment of the present invention, the data quality and accuracy are ensured by collating the slurry viscosity change data. Select appropriate data visualization tools or programming languages, such as Matplotlib, Seaborn, Plotly (Python library), ggplot2 in R language, etc. Design charts according to data characteristics, select appropriate chart types (line charts, scatter plots, heat maps, etc.), and correspond time / steps to viscosity changes. Use the selected visualization tool to convert the slurry viscosity change data into an intuitive multivariate viscosity change graph.

[0122] Step S25: Mark the mutation points according to the multivariate viscosity change diagram to generate mutation point data.

[0123] In the embodiment of the present invention, the abnormal points or mutation points in the multivariate viscosity change diagram are identified by using statistical methods or algorithms (such as local abnormal factor detection, moving window detection). The identified mutation points are marked in the diagram using marks or symbols, or their position information is recorded. The position, time or other relevant information of the mutation point is organized into a data set for further analysis or for subsequent steps.

[0124] Preferably, step S3 comprises the following steps:

[0125] Step S31: using the characteristic demand data and the mutation point data to perform the initial coating simulation and generate multi-point simulation result data;

[0126] Step S32: selecting the optimal simulation results according to the multi-point simulation result data to generate the optimal initial simulation data;

[0127] Step S33: Screening corresponding mutation points based on the optimal initial simulation data to generate initial screening mutation point data;

[0128] Step S34: performing a flow rate change coating simulation based on the initial screening mutation point data to generate multiple flow rate simulation data; performing a convergence iterative simulation based on the multiple flow rate simulation data to generate coating flow rate data;

[0129] Step S35: Screening simulation data based on the coating flow rate data to generate simulation coating result data; using the valve control times calculation formula and evaluating the difference in thickness between the head and the tail according to the simulation coating result data to generate valve switch control data;

[0130] Step S36: Based on the coating flow rate data and the valve switch control data, the initial screening mutation point data is subjected to viscosity convergence iterative simulation to generate the best coating result data; based on the best coating result data, the slurry viscosity interval analysis is performed to generate coating viscosity data.

[0131] The present invention simulates a plurality of possible coating results by simulating the coating process, combining demand data and mutation point data. These simulation results cover situations under different coating parameters and conditions, which are helpful to understand the influence of different parameters on the coating results in the simulation stage, and reduce the range of slurry viscosity according to the results. According to the coating requirements and expected results, the simulation results are evaluated and screened, and high-quality simulation data that meets the requirements are selected. This superior simulation data helps to focus on the simulation results that meet the requirements, reduces the subsequent screening work, and improves the accuracy and availability of the simulation results. The mutation key points that meet the expected residual effect in the simulation are screened out, thereby narrowing the suitable slurry viscosity. Identifying these mutation points helps to understand which parameters or conditions will cause important changes in the coating results during the simulation process, so as to carry out subsequent parameter adjustments and optimizations in a targeted manner. For the mutation points screened for the first time, the flow rate is changed for coating simulation, and simulation results under a variety of different flow rates are generated. It helps to understand the influence of different flow rates on the coating results and provide a basis for selecting the optimal flow rate. Next, a convergent iterative simulation is performed based on these multi-flow rate simulation data to generate more accurate and stable coating flow rate data, making the coating process more controllable and efficient. The initial simulation results are screened according to the coating flow rate data, and the simulated coating result data with high quality and meeting the requirements are selected. Based on the simulation results and the valve control number calculation formula, the difference in coating thickness at the beginning and end is evaluated to provide important data support for valve control and ensure the uniformity and consistency of coating. Combining the flow rate data, valve control data and the mutation point data of the initial screening, the coating parameters are further optimized and iterated to generate the best coating result data. At the same time, the slurry viscosity range analysis based on the best coating result data helps to understand the range of changes in slurry viscosity during the coating process.

[0132] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0133] Step S31: using the characteristic demand data and the mutation point data to perform the initial coating simulation and generate multi-point simulation result data;

[0134] In an embodiment of the present invention, by setting environmental parameters for simulated coating, such as temperature, humidity, pressure, etc., ensure that the simulated environment is close to the actual coating. Select a suitable simulation algorithm, such as finite element simulation, machine learning model (such as neural network, decision tree, etc.) or a model based on physical equations. Input the characteristic demand data of the article to be coated and the coating viscosity corresponding to the mutation point data into the simulation system. Perform multi-point coating simulation, simulate the coating results of different points based on the input data, and generate multi-point simulation result data, which includes the coating simulation results corresponding to each mutation point.

[0135] Step S32: selecting the optimal simulation results according to the multi-point simulation result data to generate the optimal initial simulation data;

[0136] In the embodiment of the present invention, by analyzing and screening the multi-point simulation result data, high-quality simulation results can be identified through index evaluation or specific algorithms, and the index can be set through characteristic requirement data. Good simulation result data, i.e., high-quality initial simulation data, are selected according to the screening criteria.

[0137] Step S33: Screening corresponding mutation points based on the optimal initial simulation data to generate initial screening mutation point data;

[0138] In the embodiment of the present invention, the optimal initial simulation data is matched or screened with the mutation point data, and the mutation point data related to the simulation result is screened out according to the matching result to generate the initial screening mutation point data.

[0139] Step S34: performing a flow rate change coating simulation based on the initial screening mutation point data to generate multiple flow rate simulation data; performing a convergence iterative simulation based on the multiple flow rate simulation data to generate coating flow rate data;

[0140] In the embodiment of the present invention, different coating flow rates are set according to the initial screening mutation point data and simulated. This may require adjusting the flow rate parameters and performing coating simulation for each flow rate. The multi-flow rate simulation data is analyzed and the best flow rate data is selected. This may involve evaluating the coating uniformity, head-to-tail thickness difference and other indicators in the simulation results in order to select the flow rate data that best meets the requirements.

[0141] Step S35: Screening simulation data based on the coating flow rate data to generate simulation coating result data; using the valve control times calculation formula and evaluating the difference in thickness between the head and the tail according to the simulation coating result data to generate valve switch control data;

[0142] In an embodiment of the present invention, by screening based on the coating flow rate data, the simulated coating result data that best meets the actual requirements is selected. Screening can be performed by setting screening criteria, such as coating uniformity, thickness difference, etc. Using the coating simulation results, a preset valve control number calculation formula is used to evaluate the difference in thickness between the head and tail during the coating process. The formula fully considers variables such as the coating required length, the head and tail thickness difference value, and the head and tail thickness change rate to finely evaluate the coating uniformity, thereby deriving the corresponding valve control number and generating valve switch control data. Or by performing a detailed analysis of the simulated coating result data. Including the thickness change of the coating head and tail parts, the change of coating speed and pressure, the distribution of coating materials in the head and tail parts, etc. Based on the simulation results, the thickness difference index of the head and tail parts is determined. It can be by calculating the average value or variance of the coating thickness of the head and tail parts, or defining the index according to the thickness difference of a specific area. Compare the simulated coating results with the expected coating requirements to establish a control strategy. This strategy can adjust the valve switching frequency based on the thickness difference index of the head and tail parts. For example, if it is found that the thickness difference between the head and tail parts is large, it is necessary to increase the number of valve adjustments to achieve more uniform coating. Use simulation methods to simulate the coating effect under different valve control times. This can be done by calculating the simulated coating results and comparing them with the ideal coating requirements to verify whether the thickness difference between the head and tail parts is effectively controlled. Finally, the verified valve switch control strategy is applied to the actual coating process. Monitor the coating thickness of the head and tail parts and record the number of valve control times, and then evaluate them based on the actual effect. Fine-tune and optimize the valve control strategy based on actual conditions.

[0143] Step S36: Based on the coating flow rate data and the valve switch control data, the initial screening mutation point data is subjected to viscosity convergence iterative simulation to generate the best coating result data; based on the best coating result data, the slurry viscosity interval analysis is performed to generate coating viscosity data.

[0144] In the embodiment of the present invention, the viscosity convergence iterative simulation is performed on the initial screening mutation point data based on the coating flow rate data and the valve switch control data. This includes iterative simulation to obtain the best coating result according to the viscosity change under different conditions. The slurry viscosity interval analysis is performed on the best coating result, which involves evaluating and analyzing the viscosity change under different conditions during the coating process to obtain the coating viscosity data.

[0145] Preferably, step S34 includes the following steps:

[0146] Step S341: Perform flow rate change coating simulation according to the initial screening mutation point data to generate multi-flow rate simulation data;

[0147] Step S342: selecting the highest flow rate according to the multi-flow rate simulation data to generate high flow rate range data; clustering the high flow rate range data to generate aggregated flow rate distribution data;

[0148] Step S343: performing range convergence iterative simulation based on the aggregated flow velocity distribution data to generate convergence simulation result data;

[0149] Step S344: performing an optimal coating effect evaluation according to the convergence simulation result data to generate flow rate convergence effect data;

[0150] Step S345: Select the optimal flow rate based on the flow rate convergence effect data to generate coating flow rate data.

[0151] The present invention generates a series of coating results by simulating under different flow rate conditions. These simulation data cover the coating effects under different flow rate conditions, which are helpful to identify the flow rate range that is most suitable for the coating process, that is, the upper limit condition of the flow rate. For the coating process, determining the highest flow rate range can avoid the flow rate conditions that exceed the equipment or material capacity, and ensure the stability of the coating process and the uniformity of the material. Subsequently, the high flow rate range data is clustered to generate aggregate flow rate distribution data. This aggregate flow rate distribution data can classify and integrate different conditions within the high flow rate range, help understand the distribution of flow rate, and provide guidance for the optimization of coating parameters. By iteratively simulating the aggregate flow rate distribution data, find the optimal simulation result that converges within the flow rate range. Through the iterative simulation process, the coating flow rate range can be gradually adjusted so that the simulation results are more convergent and stable. Such convergent simulation result data can provide more accurate and stable coating effect predictions. The convergent simulation results are comprehensively evaluated and screened to select data with better coating effects. Through this evaluation process, the simulation data with the best coating flow rate range can be identified, providing strong support for the final flow rate selection. Based on the previous evaluation and screening results, the optimal coating flow rate conditions are determined. By analyzing the convergence effect data, the optimal range of coating flow rates is determined to ensure the best effect and stability during the coating process.

[0152] In an embodiment of the present invention, different coating flow rates are set by pre-screening mutation point data, and simulation is performed. It may be necessary to adjust flow rate parameters, such as speed size and range of variation. The data point with the highest flow rate is identified from the multi-flow rate simulation data, and high flow rate range data is created. Cluster analysis is performed on the high flow rate range data, such as clustering algorithm (such as K-means clustering) to identify and generate aggregate flow rate distribution data. Using the aggregate flow rate distribution data, range convergence iterative simulation is performed. This includes iterative simulation to ensure the convergence of the coating flow rate and the final coating effect. Determine indicators for measuring high-quality coating effects, such as coating uniformity, thickness consistency, edge quality, etc. Using the result data of the convergence simulation, evaluation is performed by quantitative and qualitative methods, which can be performed by using image processing, data analysis tools or simulation software. According to the evaluation results, data on the flow rate convergence effect is generated, that is, the scores or levels of various evaluation indicators. Based on the flow rate convergence effect data, an algorithm or rule is used to determine the optimal flow rate. Optimization algorithms (such as genetic algorithms or gradient descent methods) or empirical methods can be used to adjust the flow rate parameters. According to the determined optimal flow rate parameters, the best coating flow rate data is generated for use in actual coating.

[0153] Preferably, the calculation formula for the valve control times in step S35 is as follows:

[0154]

[0155] Where N is the number of valve controls, L is the required coating length, H is the thickness difference between the head and the tail, V H is the thickness change rate at the head and tail, A is the simulated coating speed, B is the simulated slurry flow, C is the simulated roller speed, D is the required coating thickness, t1 is the coating start time, t2 is the coating end time, K is the valve control sensitivity, e is the base of the natural logarithm, t is the time variable value, It is the deviation correction value of valve control times.

[0156] The present invention provides a valve control times calculation formula, which is used to evaluate the difference between the head and tail thickness according to the simulated coating result data and generate valve switch control data. The formula fully considers the coating required length L, the difference between the head and tail thickness H, and the head and tail thickness change rate V. H , simulated coating speed A, simulated slurry flow B, simulated roller speed C, coating required thickness D, coating start time t1, coating end time t2, valve control sensitivity K, natural logarithm base e, time variable value t, valve control times deviation correction value And the interaction relationship between parameters constitutes the functional relationship:

[0157]

[0158] By considering the effect of coating required length L and thickness difference value H at the head and tail. If coating length increases, more control is needed to maintain coating consistency. At the same time, if the thickness difference at the head and tail increases, more adjustments are needed to ensure coating quality. However, these two factors may affect each other. For example, increasing coating length may result in more material supply, thus affecting the thickness difference at the head and tail. If V H As D increases, the coating system needs to adjust more quickly to maintain stability. But this also depends on other factors, such as the simulated coating speed A. A high coating speed means more frequent adjustments are needed. The interaction between the coating requirement thickness D and the coating flow rate A will also affect the number of valve controls. If D increases, more material and more frequent adjustments are required to meet the coating needs, especially when A increases. The slurry flow rate usually represents the amount of material used in the coating process. The square of B amplifies the impact of the simulated slurry flow rate on the result, where a higher roller speed may result in more uniform coating or a higher coating speed. The proportional relationship between the coating requirement thickness and the slurry flow rate and roller speed takes into account the effect of the coating thickness on the coating flow rate and coating uniformity. The integral term in the formula Represents the cumulative effect over time. It is often used to describe the historical dependence of coating control. In other words, it reflects the impact of adjustments made by the coating system in the past on the current control decision. For example, if past adjustments took a long time to reach a stable state, then the current control may require more adjustments to ensure stable coating. K is a control sensitivity parameter, which represents the degree of influence of the sensitivity of the valve switch adjustment on the system. Exponential decay e ―t It means that the influence of past control intervention on the current state gradually weakens over time. This formula provides a numerical standard for the evaluation of the difference between the head and tail thickness, and serves as one of the bases for generating valve switch control data, which helps to optimize the control and adjustment during the coating process. At the same time, the valve control sensitivity and deviation correction value in the formula can be corrected according to the actual simulation situation to adapt to the coating valve control calculation of different substrates, which improves the flexibility and applicability of the formula.

[0159] Preferably, step S4 comprises the following steps:

[0160] Step S41: acquiring actual production environment data; performing viscosity deviation correction on coating viscosity data based on the actual production environment data to generate actual coating viscosity data;

[0161] Step S42: using the coating pump speed calculation formula and performing pump speed evaluation according to the actual coating viscosity data and coating flow rate data to generate coating pump speed data;

[0162] Step S43: adjusting the coating pressure according to the microscopic characteristic data to generate coating pressure differentiation data;

[0163] Step S44: performing an actual environmental test according to the coating pump speed data and the coating pressure differentiation data to generate coating test result data;

[0164] Step S45: performing deviation analysis on the coating experiment result data based on the coating requirement data to generate test deviation data; performing coating parameter correction based on the test deviation data to generate coating parameter data;

[0165] Step S46: Perform coating operation according to the coating parameter data to generate actual coating result data.

[0166] The present invention corrects the coating viscosity data previously simulated or calculated by actual production environment data. By feedback of actual data, the coating viscosity is corrected, so that the simulation and calculation results are closer to the actual situation, and the accuracy and controllability of the coating process are improved. Based on the calculation formula of the coating pump speed, the pump speed required for coating is evaluated and calculated in combination with the actual viscosity data and flow rate data. This process can dynamically adjust the pump speed according to the actual data to ensure the stability and accuracy of the coating flow. The pressure in the coating process is adjusted by using microscopic feature data, and the pressure applied during coating is adjusted according to the surface characteristics of the object and the coating requirements. This step enables the coating pressure to be more in line with the actual coating requirements, and improves the accuracy and efficiency of the coating process. Through actual coating tests, the coating pump speed and pressure conditions previously determined are simulated in a real production environment. The data collected through the test can be fed back to the adjustment and optimization of the coating parameters, ensuring that the actual coating conditions match the parameters previously simulated, and improving the reliability and controllability of the experiment. By analyzing the differences and deviations between the experimental data and the coating requirement data, the problems and deviations in the coating process are identified. Through these deviation data, the coating parameters can be adjusted and corrected to ensure that the coating process is more in line with the requirements and improve the accuracy and consistency of the coating. The actual coating operation is carried out based on the adjusted and corrected coating parameters. The actual coating result data obtained is obtained after parameter adjustment and optimization, ensuring that the actual coating effect meets the expected requirements and improving the accuracy and stability of the coating process.

[0167] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0168] Step S41: acquiring actual production environment data; performing viscosity deviation correction on coating viscosity data based on the actual production environment data to generate actual coating viscosity data;

[0169] In the embodiment of the present invention, the viscosity data in the actual production environment during the coating process is obtained, which may be obtained through sensors, measuring instruments or records. The data is analyzed using statistical analysis or models to identify and correct the viscosity deviation. For example, methods such as outlier detection, averaging, and correction curve fitting are included. Based on the analysis results, the corrected actual coating viscosity data is generated.

[0170] Step S42: using the coating pump speed calculation formula and performing pump speed evaluation according to the actual coating viscosity data and coating flow rate data to generate coating pump speed data;

[0171] In an embodiment of the present invention, a preset coating pump speed calculation formula is used, which fully considers variables such as the original coating pump speed, the actual coating viscosity, and the coating required width to adapt to different coating environments and accurately evaluate the corresponding coating pump speed. In addition to the preset formula, a model can also be established by using machine learning or statistical methods to associate the coating pump speed with factors such as the actual coating viscosity and the coating flow rate. This may include methods such as multivariate linear regression, support vector machine (SVM), and neural network. Or based on physical principles such as liquid fluid mechanics and heat transfer, a mathematical model describing the coating process is established. The model can take into account the physical relationship between different variables, such as viscosity, flow rate, pipe diameter, etc. Thereby generating coating pump speed data.

[0172] Step S43: adjusting the coating pressure according to the microscopic characteristic data to generate coating pressure differentiation data;

[0173] In the embodiment of the present invention, microscopic feature data, such as surface structure, particle size, etc., are obtained by using imaging or sensor data. The microscopic feature data is analyzed and processed to generate coating pressure differentiation data. This can be used to adjust the coating conditions by using different coating pressures, flow rates or other parameters to meet specific needs.

[0174] Step S44: performing an actual environmental test according to the coating pump speed data and the coating pressure differentiation data to generate coating test result data;

[0175] In an embodiment of the present invention, an experiment is designed based on coating pump speed data and pressure differentiation data. Test conditions, equipment settings, and operation steps are determined. Coating tests are performed in an actual production environment, and coating operations are performed according to predetermined conditions. Test data, including coating parameters, pump speed, pressure, etc., are recorded. Test result data may be collected through sensors, monitoring equipment, imaging tools, or manual recording.

[0176] Step S45: performing deviation analysis on the coating experiment result data based on the coating requirement data to generate test deviation data; performing coating parameter correction based on the test deviation data to generate coating parameter data;

[0177] In an embodiment of the present invention, by arranging the coating requirement data and the test result data, such as coating thickness, speed, coating area, etc., the two are compared to find the deviation. Through data comparison and analysis, the differences and deviations between the test results and the requirement data are identified. Including comparisons in terms of coating uniformity, thickness difference, coverage, etc. Check the trend of the coating result data to determine whether there are continuous deviations or inconsistencies. Based on the deviation analysis results, determine the coating parameters that need to be adjusted. This requires analyzing the impact of the parameters on the coating results. Based on the findings of the deviation analysis, the coating parameters are optimized. For example, increase or decrease the pump speed, adjust the coating pressure, adjust the coating flow, etc., to generate coating parameter data.

[0178] Step S46: Perform coating operation according to the coating parameter data to generate actual coating result data.

[0179] In the embodiment of the present invention, the coating equipment is set according to the modified coating parameter data, including pump speed, pressure, coating flow rate, etc. The actual coating operation is performed, and the coating is performed according to the adjusted parameters. The key data during the actual operation is recorded.

[0180] Preferably, the coating pump speed calculation formula in step S42 is as follows:

[0181]

[0182] In the formula, v p is the coating pump speed, v0 is the original coating pump speed, μ is the actual coating viscosity, d is the required coating width, a h is the actual air humidity, η is the slurry shear viscosity, ρ is the slurry density, D is the required coating thickness, V S is the substrate moving speed, V C is the coating flow rate, is the partial derivative of the slurry shear viscosity with respect to the required coating thickness, and ω is the deviation correction value of the coating pump speed.

[0183] The present invention provides a coating pump speed calculation formula, which is used to evaluate the pump speed according to the actual coating viscosity data and the coating flow rate data, and generate coating pump speed data. The formula fully considers the original coating pump speed v0, the actual coating viscosity μ, the coating required width d, the actual air humidity a h , slurry shear viscosity η, slurry density ρ, coating thickness D, substrate moving speed V S , coating flow rate V C , the partial derivative of the slurry shear viscosity with respect to the required coating thickness The deviation correction value ω of the coating pump speed and the interaction relationship between variables constitute a functional relationship:

[0184]

[0185] Through the interaction between the required coating width and the actual air humidity, the coating pump speed can be adjusted according to different environmental conditions and requirements to obtain better coating quality and efficiency. When the original coating pump speed increases, if the actual coating viscosity also increases, the product of the numerator will increase, driving the increase in the coating pump speed. This interaction ensures a higher pump speed at high viscosity to maintain coating quality. A larger required coating width may cause the actual coating viscosity to have a more significant effect in the formula, which means that a higher coating pump speed is required to ensure that the entire width is properly coated. The actual air humidity affects the coating pump speed through a logarithmic function. High humidity may have a negative effect on the coating effect. For example, the higher the humidity, the easier it is for the coating to work, which indirectly affects the coating pump speed. By comprehensively considering the relationship between the flow characteristics of the slurry, the size of the coating requirement and the coating speed. Through this interaction, the coating pump speed can be adjusted according to the properties of the slurry and the coating conditions to ensure the consistency of the coating thickness and coating quality. The coating pump speed is adjusted according to the rate of change of the required coating thickness and the substrate speed. The partial derivative of the slurry shear viscosity with respect to the required coating thickness represents the change of the slurry during the coating process. By considering this change and the relationship between the substrate speed and the coating flow rate, the coating pump speed can be adjusted to better control the shear force and viscosity changes, thereby achieving a more stable and uniform coating. This formula combines factors such as the actual coating viscosity and the coating flow rate, and does not rely solely on the evaluation of a single factor. It helps to more accurately predict the required coating pump speed and avoid errors caused by ignoring certain factors. At the same time, the deviation correction value of the actual air humidity and the coating pump speed in the formula can be corrected according to the actual coating process to adapt to different coating environments.

[0186] Preferably, step S43 includes the following steps:

[0187] Step S431: Acquire diversified micro data; perform correlation feature analysis based on the diversified micro data to generate correlated micro feature data;

[0188] Step S432: performing multi-pressure coating simulation according to the associated micro-feature data to generate multi-pressure simulation data;

[0189] Step S433: performing coating pressure commonality evaluation based on the multi-pressure simulation data to generate characteristic pressure correlation data;

[0190] Step S434: performing convergence simulation based on the characteristic pressure correlation data to generate characteristic pressure change data; performing visualization processing on the characteristic pressure change data to generate a characteristic pressure curve;

[0191] Step S435: performing pressure matching on the characteristic pressure curve based on the microscopic characteristic data to generate coating pressure matching data;

[0192] Step S436: Setting the coating pressure according to the coating pressure matching data to generate coating pressure differentiation data.

[0193] The present invention collects diversified microscopic data, which may include various data such as surface features of objects and material properties, and analyzes and extracts related features. These related microscopic feature data can help identify the correlation and commonality between different microscopic features, providing a deeper understanding and basis for the further coating process. Multi-pressure simulation data can help understand the influence of different pressures on the coating process, as well as the optimal selection of pressure under different microscopic features, and provide more parameter selection and optimization schemes for the coating process. Through the analysis and evaluation of multi-pressure simulation data, the common features under different pressure conditions can be identified, and the correlation and optimization direction of the coating pressure can be found. These characteristic pressure correlation data can provide more guidance for the selection of coating pressure, so that the pressure parameters are more in line with the coating requirements of different microscopic features, and improve the adaptability and flexibility of the coating process. Use characteristic pressure correlation data for simulation to generate characteristic change data under pressure conditions. This convergence simulation helps to understand the influence of different pressures on microscopic features, and provides characteristic data under pressure changes, which provides an important basis for the optimization of the coating process. The characteristic pressure change data is presented as a curve chart by a visualization method. This visualization helps to intuitively show the influence trend of pressure on microscopic features, providing an intuitive basis for further analysis. The characteristic pressure curve is analyzed and matched using microscopic feature data to obtain more appropriate coating pressure data. Such a matching process helps to determine the optimal pressure conditions to be used in the coating process based on specific microscopic features. Using the matched coating pressure data, coating pressure conditions suitable for different microscopic features are set. Such data generation makes the pressure setting in the coating process more accurate and can better meet the needs of different surface features of objects.

[0194] In an embodiment of the present invention, by collecting diversified microscopic data during the coating process, such as the surface morphology, particle size, distribution and other information of different coated objects, it can be obtained through an imaging device, a scanner or a sensor. The data is cleaned, processed and standardized to ensure data quality and consistency. For the microscopic data, key features such as particle size, shape, color distribution, etc. are extracted to form a feature set. Statistical methods, machine learning or correlation analysis tools are used to analyze the association and correlation between different features, and form a data set of associated microscopic features. Coating simulation experiment schemes under various pressure conditions are designed according to the associated microscopic feature data. The coating process is simulated under different pressure conditions by means of numerical simulation software, coating equipment models or physical simulation experiments, and relevant data are recorded. The data generated by the simulation experiment are collected, including coating results, coating thickness, uniformity, etc. under different pressure conditions. The simulation data is analyzed to find out the common features and correlations under different coating pressure conditions. The degree of association between different coating pressures and microscopic features is evaluated, for example, the relationship between pressure and coating uniformity and particle distribution is analyzed. The analysis results are sorted out to generate characteristic pressure correlation data to describe the information related to the microscopic features under different coating pressure conditions. Using the convergent simulation method, simulation experiments are carried out based on the characteristic pressure correlation data to generate data on characteristic pressure changes. Using data visualization tools (such as Matplotlib in Python, ggplot2 in R language, etc.), the characteristic pressure change data is converted into a curve graph to intuitively display the changing trend under different pressure conditions. Using the key information in the microscopic characteristic data, it is compared and matched with the characteristic pressure curve to determine the pressure conditions most relevant to the microscopic features. Based on the matching results, the coating pressure matching data is generated, including the value or range of the coating pressure, and the corresponding microscopic features or performance. Based on the coating pressure matching data, the optimal coating pressure conditions are determined and the coating pressure parameters are set. The set coating pressure parameters are converted into specific coating pressure differentiation data, including the coating set value under different pressure conditions, the actual applied pressure range or stage, etc.

[0195] The present invention also provides an extrusion coating machine pump speed calculation system, which is used to execute the extrusion coating machine pump speed calculation method as described above, comprising:

[0196] The slurry stirring simulation module is used to obtain coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification and correction based on viscosity prediction data to generate slurry viscosity change data;

[0197] The coating demand analysis module is used to obtain the coating demand data of the object to be coated; use the imaging device to image the demand area of ​​the object to be coated to generate microscopic feature data; perform feature annotation on the coating demand data based on the microscopic feature data to generate feature demand data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data;

[0198] The coating parameter analysis module is used to use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening, and generate the initial screening mutation point data; perform flow rate convergence iterative simulation based on the initial screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the initial screening mutation point data based on the coating flow rate data to generate coating viscosity data;

[0199] The actual coating operation module is used to obtain actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data to generate coating pump speed data; adjust coating pressure through micro-feature data to generate coating pressure differentiation data; perform coating operations based on coating pump speed data and coating pressure differentiation data to generate actual coating result data.

[0200] The beneficial effect of the present application is that the present invention can determine the predicted viscosity of the coating material at different time points, temperatures, or stirring speeds by simulating the stirring process. Such viscosity prediction data is based on the simulation of material properties and stirring conditions, and can predict the change trend of the viscosity of the coating material in advance. The purpose of viscosity verification and correction based on the viscosity prediction data is to calibrate the accuracy of the prediction data. In actual situations, the viscosity prediction may be affected by experimental errors or simulation conditions. Through the verification and correction process, the prediction data can be corrected and adjusted through experimental data to generate more accurate and reliable slurry viscosity change data. These data provide more accurate material viscosity information for the coating process to ensure accurate control of viscosity during the coating process. The microscopic features of the object are obtained by imaging equipment in order to understand the characteristics of the object surface in more detail. These features may include surface texture, pore properties or other microscopic details. After generating the microscopic feature data, feature annotation is performed in combination with the coating requirement data to generate feature requirement data. Such data makes the coating process more personalized, and the coating scheme is tailored according to the specific microscopic features of the object. The mutation point marking according to the slurry viscosity change data is to identify the key points that may exist in the coating process. Breakpoint markers can help identify locations where material viscosity or other properties change dramatically under specific coating conditions. Breakpoint markers help adjust coating parameters more accurately to adapt to changes in material properties, thereby improving coating efficiency and quality. Coating simulation and viscosity screening help narrow the range of slurry viscosities that meet coating effects, thereby reducing subsequent simulation processes. Through iterative simulation, the coating flow rate can be gradually adjusted to make it tend to the optimal coating flow rate under specific conditions. Help optimize the coating process to ensure uniformity and consistency of materials during coating. Through viscosity convergence iterative simulation, simulate different combinations of viscosities and flow rates to obtain the optimal coating viscosity, thereby ensuring the adaptability and quality of materials during the coating process. Correct the previously simulated coating viscosity based on actual conditions to more accurately reflect the viscosity changes under real production conditions. Help improve the stability and controllability of the coating process. Determine the optimal pump speed setting based on the actual viscosity and flow rate conditions for more accurate coating control. Therefore, the extrusion coating machine pump speed calculation method and system of the present invention determines the change of slurry viscosity through stirring simulation, and then gradually determines each coating parameter through coating iteration simulation, and finally calculates the final coating pump speed in combination with actual test. In this way, most of the test materials and test processes are saved through the simulation method, and it is ensured that the coating pump speed conforms to the actual extrusion coating process.

[0201] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0202] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for calculating the pump speed of an extrusion coating machine, characterized in that: The following steps are involved: Step S1: Acquire coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; Perform viscosity verification and correction based on viscosity prediction data to generate slurry viscosity change data; Step S2: Acquire coating requirement data of the article to be coated; use imaging equipment to image the required area of ​​the article to be coated to generate microscopic feature data; perform feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data; Step S3: Use the characteristic demand data and the mutation point data to perform coating simulation and viscosity screening to generate preliminary screening mutation point data; perform flow rate convergence iterative simulation based on the preliminary screening mutation point data to generate coating flow rate data; perform viscosity convergence iterative simulation on the preliminary screening mutation point data based on the coating flow rate data to generate coating viscosity data; Step S4: Acquire actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data and coating flow rate data to generate coating pump speed data; perform coating operation based on coating pump speed data to generate actual coating result data.

2. The method for calculating the pump speed of an extrusion coater according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: obtaining coating material data; Step S12: performing correlation analysis between characteristics according to the coating material data to generate component viscosity correlation data; Step S13: using a numerical simulation method to simulate the stirring process of the component viscosity correlation data to generate stirring process data; Step S14: Establishing a multivariate change relationship based on the stirring process data to generate viscosity prediction data; Step S15: performing random viscosity test verification according to the viscosity prediction data to generate test result data; Step S16: Based on the test result data, the multivariate change evaluation data is corrected for deviations to generate slurry viscosity change data.

3. The method for calculating the pump speed of an extrusion coater according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: obtaining coating requirement data of the object to be coated; Step S22: using an imaging device to image the required area of ​​the object to be coated to generate an image of the surface to be coated; Step S23: performing microscopic feature evaluation on the surface image to be coated to generate microscopic feature data; performing feature annotation on the coating requirement data based on the microscopic feature data to generate feature requirement data; Step S24: Visualize the slurry viscosity change data to generate a multivariate viscosity change graph; Step S25: Mark the mutation points according to the multivariate viscosity change diagram to generate mutation point data.

4. The method for calculating the pump speed of an extrusion coater according to claim 3, characterized in that: Step S3 includes the following steps: Step S31: using the characteristic demand data and the mutation point data to perform the initial coating simulation and generate multi-point simulation result data; Step S32: selecting the optimal simulation results according to the multi-point simulation result data to generate the optimal initial simulation data; Step S33: Screening corresponding mutation points based on the optimal initial simulation data to generate initial screening mutation point data; Step S34: performing a flow rate change coating simulation based on the initial screening mutation point data to generate multiple flow rate simulation data; performing a convergence iterative simulation based on the multiple flow rate simulation data to generate coating flow rate data; Step S35: Screening simulation data based on the coating flow rate data to generate simulation coating result data; using the valve control times calculation formula and evaluating the difference in thickness between the head and the tail according to the simulation coating result data to generate valve switch control data; Step S36: Based on the coating flow rate data and the valve switch control data, the initial screening mutation point data is subjected to viscosity convergence iterative simulation to generate the best coating result data; based on the best coating result data, the slurry viscosity interval analysis is performed to generate coating viscosity data.

5. The method for calculating the pump speed of an extrusion coater according to claim 4, characterized in that: Step S34 includes the following steps: Step S341: Perform flow rate change coating simulation according to the initial screening mutation point data to generate multi-flow rate simulation data; Step S342: selecting the highest flow rate according to the multi-flow rate simulation data to generate high flow rate range data; clustering the high flow rate range data to generate aggregated flow rate distribution data; Step S343: performing range convergence iterative simulation based on the aggregated flow velocity distribution data to generate convergence simulation result data; Step S344: performing an optimal coating effect evaluation according to the convergence simulation result data to generate flow rate convergence effect data; Step S345: Select the optimal flow rate based on the flow rate convergence effect data to generate coating flow rate data.

6. The method for calculating the pump speed of an extrusion coater according to claim 4, characterized in that: The calculation formula for the valve control times in step S35 is as follows: Where N is the number of valve controls, L is the required coating length, H is the thickness difference between the head and the tail, V H is the thickness change rate at the head and tail, A is the simulated coating speed, B is the simulated slurry flow, C is the simulated roller speed, D is the required coating thickness, t1 is the coating start time, t2 is the coating end time, K is the valve control sensitivity, e is the base of the natural logarithm, t is the time variable value, It is the deviation correction value of valve control times.

7. The method for calculating the pump speed of an extrusion coater according to claim 6, characterized in that: Step S4 includes the following steps: Step S41: acquiring actual production environment data; performing viscosity deviation correction on coating viscosity data based on the actual production environment data to generate actual coating viscosity data; Step S42: using the coating pump speed calculation formula and performing pump speed evaluation according to the actual coating viscosity data and coating flow rate data to generate coating pump speed data; Step S43: adjusting the coating pressure according to the microscopic characteristic data to generate coating pressure differentiation data; Step S44: performing an actual environmental test according to the coating pump speed data and the coating pressure differentiation data to generate coating test result data; Step S45: performing deviation analysis on the coating experiment result data based on the coating requirement data to generate test deviation data; performing coating parameter correction based on the test deviation data to generate coating parameter data; Step S46: Perform coating operation according to the coating parameter data to generate actual coating result data.

8. The method for calculating the pump speed of an extrusion coater according to claim 7, characterized in that: The coating pump speed calculation formula in step S42 is as follows: In the formula, v p is the coating pump speed, v0 is the original coating pump speed, μ is the actual coating viscosity, d is the required coating width, a h is the actual air humidity, η is the slurry shear viscosity, ρ is the slurry density, D is the required coating thickness, V S is the substrate moving speed, V C is the coating flow rate, is the partial derivative of the slurry shear viscosity with respect to the required coating thickness, and ω is the deviation correction value of the coating pump speed.

9. The method for calculating the pump speed of an extrusion coating machine according to claim 7, characterized in that: Step S43 includes the following steps: Step S431: Acquire diversified micro data; perform correlation feature analysis based on the diversified micro data to generate correlated micro feature data; Step S432: performing multi-pressure coating simulation according to the associated micro-feature data to generate multi-pressure simulation data; Step S433: performing coating pressure commonality evaluation based on the multi-pressure simulation data to generate characteristic pressure correlation data; Step S434: performing convergence simulation based on the characteristic pressure correlation data to generate characteristic pressure change data; performing visualization processing on the characteristic pressure change data to generate a characteristic pressure curve; Step S435: performing pressure matching on the characteristic pressure curve based on the microscopic characteristic data to generate coating pressure matching data; Step S436: Setting the coating pressure according to the coating pressure matching data to generate coating pressure differentiation data.

10. An extrusion coating machine pump speed calculation system, characterized in that: Used to execute the method for calculating the pump speed of an extrusion coating machine according to claim 1, the pump speed calculation system for the extrusion coating machine comprises: The slurry stirring simulation module is used to obtain coating material data; perform stirring simulation according to coating parameter data to generate viscosity prediction data; perform viscosity verification and correction based on viscosity prediction data to generate slurry viscosity change data; The coating demand analysis module is used to obtain the coating demand data of the object to be coated; use the imaging device to image the demand area of ​​the object to be coated to generate microscopic feature data; perform feature annotation on the coating demand data based on the microscopic feature data to generate feature demand data; perform mutation point marking according to the slurry viscosity change data to generate mutation point data; The coating parameter analysis module is used to use the characteristic demand data and mutation point data to perform coating simulation and viscosity screening, and generate preliminary screening mutation point data; perform flow rate convergence iterative simulation based on the preliminary screening mutation point data to generate coating flow rate data; Based on the coating flow rate data, the viscosity convergence iterative simulation is performed on the initial screening mutation point data to generate coating viscosity data; The actual coating operation module is used to obtain actual production environment data; perform viscosity deviation correction on coating viscosity data based on actual production environment data to generate actual coating viscosity data; perform pump speed evaluation based on actual coating viscosity data to generate coating pump speed data; adjust coating pressure through micro-feature data to generate coating pressure differentiation data; perform coating operations based on coating pump speed data and coating pressure differentiation data to generate actual coating result data.

Images