A glue-filling jig and a glue-filling method for a display module

Abstract

The application belongs to the technical field of glue filling, and provides a glue filling jig and a glue filling method of a display module. The glue filling method of the display module comprises the following steps: before the glue filling process is performed, a module structure of the display module is acquired, the density and height difference of internal components of the module structure are analyzed, a structure complexity value is output, and the complexity of the module structure is evaluated; historical data when the display module is glued is extracted, the data is clustered according to glue filling process parameters, glue solidification time data and structure complexity value data corresponding to each cluster are acquired, the glue solidification time and the structure complexity value are analyzed, and whether the two indexes are in a correlation relationship is judged through correlation strength and correlation direction consistency, if the two indexes are in the correlation relationship, then a correlation model is respectively constructed for each cluster; and a target correlation model is identified according to the correlation model of each cluster and input current glue filling process parameters.

Description

Technical Field

[0001] The invention belongs to the technical field of glue potting, and in particular to a glue potting jig and a glue potting method for a display module. Background Art

[0002] Gluing of display modules is an important packaging process. It involves injecting a specific colloid material into the interior or surrounding area of ​​the display module using specialized equipment or manual operation. Its core purpose is to enhance the protective performance of the display module. For example, the colloid can fill the tiny gaps between components within the module, preventing the intrusion of impurities such as dust and moisture, avoiding circuit short circuits and corrosion caused by environmental factors, and ensuring the stable operation of the display module in complex environments. At the same time, glue potting can also play a role in fixing components, reducing component loosening and displacement caused by external forces such as vibration and impact, thereby improving the overall mechanical strength and reliability of the display module, extending its service life, and ensuring consistent display effects.

[0003] Existing technologies for the glue potting of display modules face numerous challenges when dealing with complex internal structures. This is due to the inability to accurately assess the degree to which the density and height differences of components within the module hinder the flow of the colloid. When the complex structure hinders the flow of the colloid, there is a lack of a dynamic adjustment mechanism to adjust process parameters such as flow rate. These issues can lead to poor glue potting quality, such as glue shortages and bubbles, which can allow dust and moisture to enter the module, causing circuit short circuits, component corrosion, and other faults. This also reduces production efficiency, requiring repeated trial and error debugging on the production line, increasing production costs and extending the new product introduction cycle. This makes it difficult to adapt to the diverse and high-precision development needs of display modules.

[0004] To this end, the present invention provides a glue pouring fixture and a glue pouring method for a display module. Summary of the Invention

[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0006] The technical solution adopted by the present invention to solve the technical problem is: a method for glue filling of a display module, comprising the following steps:

[0007] Before the glue filling process, the module structure of the display module is obtained, the density and height difference of the internal components of the module structure are analyzed, the structural complexity value is output, and the complexity of the module structure is evaluated;

[0008] The historical data is extracted when the display module is filled with glue, the data is clustered according to the glue filling process parameters, the glue solidification time data and the structure complexity value data corresponding to each cluster are obtained, the glue solidification time and the structure complexity value are analyzed, and whether it is a correlation is judged through the correlation strength and the consistency of the correlation direction, if it is a correlation, a correlation model is constructed for each cluster;

[0009] According to the correlation model of each cluster, the current glue filling process parameters are input to identify the target correlation model, the structure complexity value of the current display module is input into the target correlation model, and the actual glue solidification time value is output, which is compared with the theoretical glue solidification time value to obtain the time deviation value, the positive and negative of the time deviation value is identified, and if the time deviation value is positive, the glue filling flow rate is adjusted based on the time deviation value.

[0010] As a further scheme of the application, the output structure value process is:

[0011] The number of connection points between parts in the display module and the total number of parts are counted, and the number of connection points and the total number of parts are compared to obtain the connection density.

[0012] The height of the highest point and the height of the lowest point of all parts in the display module are measured, the difference between the height of the highest point and the height of the lowest point is calculated, and the height deviation degree is obtained by comparing the height of the lowest point.

[0013] The connection density and the height deviation degree are fused to output the structure complexity value.

[0014] As a further scheme of the application, the historical data is clustered according to the glue filling process parameters by using hierarchical clustering algorithm, which is used to analyze the relationship between the glue solidification time and the structure complexity value under the premise of similar glue filling process parameters.

[0015] As a further scheme of the application, the process of judging whether it is a correlation is:

[0016] The correlation degree of each cluster is obtained, the cluster whose absolute value of correlation degree is greater than the correlation threshold value is extracted, and the number thereof is counted as the number of strongly correlated clusters; and the number of strongly correlated clusters is compared with the total number of clusters to obtain the proportion of the number of strongly correlated clusters.

[0017] The positive and negative of the corresponding correlation degree in the strongly correlated cluster are identified, and the number of clusters with positive correlation degree and the number of clusters with negative correlation degree are counted respectively; the maximum value is extracted as the number of dominant correlation direction clusters, and the number of dominant correlation direction clusters is compared with the number of strongly correlated clusters to obtain the proportion of the number of dominant correlation direction clusters.

[0018] The proportion of the number of strongly correlated clusters and the proportion of the number of dominant correlation direction clusters are added to output the correlation coefficient.

[0019] If the correlation coefficient is greater than or equal to the correlation coefficient limit, it means that there is a correlation between the colloid curing time and the structural complexity value.

[0020] As a further solution of the present invention: the relevance is obtained in the following manner:

[0021] For each cluster, the corresponding colloid solidification time data and structural complexity value data are extracted, and the Pearson correlation coefficient of the colloid solidification time data and the structural complexity value data is calculated to characterize the correlation, thereby obtaining the corresponding correlation of each cluster.

[0022] As a further solution of the present invention: the process of constructing a correlation model for clustering clusters is:

[0023] Extract the data of each cluster from all the dominant correlation direction clusters as the model construction dataset; divide the dataset into training set and validation set;

[0024] The glue filling process parameters and structural complexity are used as input features, and the glue curing time is used as the output target;

[0025] Among them, the glue filling process parameters are used as input features to distinguish the clusters to which they belong and select the corresponding correlation model;

[0026] The least squares method is used to fit the data sets in each cluster to obtain the corresponding correlation models, and the test set is used to verify the performance of the model; the verified correlation model is integrated into the glue filling control system.

[0027] As a further solution of the present invention: the process of obtaining the time deviation value is:

[0028] Obtain the current glue filling process parameters and identify the corresponding related model as the target related model;

[0029] Substitute the structural complexity value of the current display module into the target-related model as a known value, output the corresponding actual colloid curing time value; and obtain the theoretical colloid curing value;

[0030] The time deviation value is obtained by performing a difference calculation between the actual colloid solidification value and the theoretical colloid solidification value.

[0031] As a further solution of the present invention: the process of identifying the positivity of the time deviation value is:

[0032] Identify the positive and negative of the time deviation value. If the time deviation value is negative or equal to zero, it means that the actual colloid solidification value is less than or equal to the theoretical colloid solidification value;

[0033] If the time deviation value is positive, it means that the actual colloid solidification value is greater than the theoretical colloid solidification value, and the colloid flow rate adjustment process needs to be performed.

[0034] As a further solution of the present invention: the process of adjusting the colloid flow rate is:

[0035] Get the total glue injection amount and the current glue injection speed value, calculate the ratio of the total glue injection amount to the current glue injection speed value, and get the current glue injection completion time;

[0036] Calculate the difference between the current glue filling completion time and the time deviation value to obtain the target glue filling completion time;

[0037] The target glue dispensing speed is obtained by calculating the ratio of the total glue dispensing amount to the target glue dispensing completion time.

[0038] A glue pouring jig, the glue pouring jig specifically comprising: a male mold and a female mold;

[0039] The master mold includes multiple sets of positioning columns and guide columns fixedly mounted on the reference surface, and the bottom surface of the master mold base plate is milled with a groove matching the equipment reference surface and locked by bolts;

[0040] The male mold bottom plate is provided with positioning holes corresponding to the female mold positioning columns, and guide sleeves are installed on both sides of the male mold to slide with the female mold guide columns.

[0041] The beneficial effects of the present invention are as follows:

[0042] The present invention calculates the structural complexity value obtained by calculating the connection density and height deviation, which can assess the degree of obstruction to the flow of colloid within the module. The correlation model constructed in combination with historical data can accurately predict the actual curing time, reducing the deviation between the theoretical value and actual demand. When the complex structure causes the curing time to be extended, the mechanism of adjusting the glue filling flow rate can effectively reduce problems such as glue shortage and bubbles, so that the glue can evenly fill the gaps between components, enhance the dust and moisture resistance and mechanical strength of the display module, and improve its stability and reliability in complex environments.

[0043] The present invention performs cluster analysis on historical data based on the glue filling process parameters. The constructed clustering model can accurately match the corresponding model according to the real-time process parameters. When there is a deviation between the actual curing time and the theoretical value, the glue filling flow rate can be adjusted, reducing manual trial and error debugging and shortening the process debugging time. At the same time, the method has good adaptability to module structures of different complexities, can quickly respond to diversified module designs, improve the compatibility of the production line with different products, reduce production costs, and shorten the new product introduction cycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention will be further described below with reference to the accompanying drawings.

[0045] Figure 1 This is a flow chart of the steps of a method for glue filling of a display module of the present invention;

[0046] Figure 2 This is a diagram of the glue filling system architecture of a display module of the present invention;

[0047] Figure 3 This is a master mold diagram of a glue-filling mold of the present invention;

[0048] Figure 4 This is a male mold diagram of a glue-filling jig of the present invention. DETAILED DESCRIPTION

[0049] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0050] Example 1:

[0051] See also Figure 1 As shown, a method for filling glue for a display module according to an embodiment of the present invention includes the following steps:

[0052] Step 1: Before the glue filling process, obtain the module structure of the display module, analyze the density and height difference of the internal components of the module structure, and evaluate the complexity of the module structure;

[0053] Those skilled in the art will appreciate that different display module structures have different requirements for the density and height difference of internal components, which all affect the flow of the colloid. Since the complexity of the module structure is analyzed to determine whether the internal structure of the module affects the curing time of the colloid, this step uses the layout and height difference of the components as evaluation indicators of the module structure complexity.

[0054] Before the glue filling process of the display module is carried out, a layout diagram of the internal components of the display module is drawn using drawing software according to the design drawings, and the positions and relative relationships of each component are marked;

[0055] As an optional implementation of this embodiment, the density of components is represented based on the connection relationship between the components;

[0056] Count the number of connection points between components and the total number of components in the display module, and calculate the ratio of the number of connection points to the total number of components as the connection density;

[0057] Measure the height of the highest point and the lowest point of all components in the display module, calculate the difference between the highest point and the lowest point, and then calculate the ratio with the height of the lowest point to obtain the height deviation;

[0058] By weighted fusion of connection density and height deviation, the output is the structural complexity value;

[0059] Among them, it is necessary to explain the acquisition of the structural complexity value. The connection density reflects the closeness between the components. The more connection points and the denser the distribution of components, the greater the obstruction encountered by the colloid during the flow process, the increased flow resistance and the difficulty of filling. The height deviation reflects the height difference of the components inside the module. The greater the height difference, the different effects of gravity and surface tension on the colloid when it flows in different height areas, which may lead to uneven distribution of the colloid and increase the difficulty of filling. The structural complexity value indicates the comprehensive obstruction of the internal structure of the module to the flow and filling of the colloid. The larger the value, the more complex the internal structure of the module, the greater the resistance encountered by the colloid during the filling process, and the higher the filling difficulty. The smaller the value, the relatively simpler the internal structure of the module, and the relatively easy flow and filling of the colloid.

[0060] The weights of connection density and height deviation are determined by those skilled in the art through experimental verification. Multiple display module samples with different structures are designed, and their connection density and height deviation are recorded. Glue filling experiments are then conducted to observe the colloid filling effect, such as glue shortages and bubbles. Based on the experimental results, the structural complexity of each sample is subjectively scored by those skilled in the art (e.g., 1-5, with 1 indicating simplicity and 5 indicating complexity). Statistical methods such as linear regression are used to analyze the relationship between connection density and height deviation and the structural complexity score, determine the coefficients of influence of the two on structural complexity, and normalize these coefficients to serve as weights.

[0061] This step has at least the following effects: it can quantify the degree of obstruction of the module to the flow of the colloid through the component density and height difference indicators, providing data support for the subsequent calculation of the actual colloid curing time, so that the curing time is combined with the actual structural characteristics;

[0062] At the same time, the analysis results can serve as a basis for adjusting the glue potting process parameters, predicting the filling resistance that may be caused by complex structures in advance, reducing problems such as bubbles and glue shortages caused by structural obstructions, improving the glue potting quality and the protection reliability of the display module, and providing a basis for the adaptability of the glue potting process for modules with different structures, avoiding process deviations caused by structural differences.

[0063] Step 2: Extract historical data from the glue potting process of the display module, cluster the data according to the glue potting process parameters, obtain the glue curing time data and structural complexity value data corresponding to each cluster, analyze whether the glue curing time and structural complexity value are correlated, and if so, construct correlation models for each cluster;

[0064] In some embodiments, the historical data extracted for glue pouring of the display module includes at least glue pouring process parameters, glue curing time, and structural complexity value; the glue pouring parameters include but are not limited to glue pouring speed and pressure;

[0065] Specifically, a hierarchical clustering algorithm is used to cluster historical data according to the glue pouring process parameters. After clustering, the glue pouring process parameters corresponding to each cluster are similar. This facilitates the analysis of the relationship between the colloid curing time and the structural complexity value under the premise of similar glue pouring process parameters, thereby making the correlation between the two more accurate.

[0066] The hierarchical clustering algorithm can gradually merge similar data points into clusters based on the similarity between data points. There is no need to pre-specify the number of clusters. The clustering process is:

[0067] Calculate the Euclidean distance between each two sets of glue filling process parameter data in the historical data, merge the two sets of data with the smallest Euclidean distance value into a new cluster, then recalculate the distance between the new cluster and other data points or clusters, and repeat the merging operation until the preset clustering termination condition is reached;

[0068] Among them, the clustering termination condition is set as: the number of clusters reaches a certain threshold, or the distance between clusters exceeds a specific value, thereby obtaining multiple clusters;

[0069] Specifically, for each cluster, the corresponding colloid solidification time data and structural complexity value data are extracted, and the correlation between the colloid solidification time and the structural complexity value is analyzed by the Pearson correlation coefficient. The process is as follows:

[0070] The Pearson correlation coefficient between the colloid solidification time data and the structural complexity value data was calculated to characterize the correlation, and the corresponding correlation of each cluster was obtained;

[0071] A correlation threshold is set to determine the correlation between the colloid solidification time and the structural complexity value in the corresponding clusters. Clusters with absolute correlation values ​​greater than the correlation threshold are extracted, and their number is counted as the number of strongly correlated clusters.

[0072] The ratio of the number of strongly correlated clusters to the total number of clusters is processed to obtain the proportion of the number of strongly correlated clusters;

[0073] Identify the positive and negative correlations in the strongly correlated clusters, and count the number of clusters with positive correlations and the number of clusters with negative correlations respectively; extract the maximum value between the number of clusters with positive correlations and the number of clusters with negative correlations as the number of clusters with dominant correlation directions, and calculate the ratio of the number of clusters with dominant correlation directions to the number of clusters with strong correlations to obtain the proportion of dominant correlation directions;

[0074] Add the proportion of strongly correlated clusters and the proportion of dominant correlation directions, and output the correlation coefficient;

[0075] The correlation coefficient requires explanation: the proportion of strongly correlated clusters reflects the proportion of clusters with similar casting process parameters that show a strong correlation between the colloid curing time and the structural complexity value; the proportion of dominant correlation directions reflects the number of positive or negative correlation directions that dominate in the strongly correlated clusters, reflecting the directional consistency of the correlation; the correlation coefficient combines strength and directional consistency to provide a comprehensive indicator for evaluating the correlation between the colloid curing time and the structural complexity value;

[0076] By adding the two together, the strength and direction consistency of the correlation are comprehensively quantified;

[0077] Comparing the correlation coefficient with a correlation coefficient limit value, which is set by a person skilled in the art based on actual process requirements and historical experience, to determine whether the correlation relationship meets the conditions for constructing a correlation model;

[0078] If the correlation coefficient is less than the correlation coefficient limit, it means that there is no significant correlation between the colloid curing time and the structural complexity value, and the direction consistency of the correlation is weak;

[0079] If the correlation coefficient is greater than or equal to the correlation coefficient limit, it means that there is a significant correlation between the colloid curing time and the structural complexity value, and the direction of the correlation is highly consistent, and the correlation model construction process is executed;

[0080] Specifically, the process of building the relevant model is:

[0081] Since, when determining the relationship between the colloid solidification time and the structural complexity value, by calculating the Pearson correlation coefficient between the colloid solidification time and the structural complexity value, it can be determined whether there is a linear relationship between the two. When the absolute value of the correlation coefficient exceeds the set correlation threshold, it indicates that there is a strong linear relationship between the two. Therefore, in this embodiment, a linear model can be selected to construct a correlation model;

[0082] Among them, clustering cluster modeling can divide data with similar glue filling process parameters into the same cluster, eliminating the interference of different process parameters on the correlation analysis of colloid curing time and structural complexity value, making the data characteristics within the cluster more consistent, thereby constructing a correlation model that is more in line with the actual process scenario. It can accurately capture the correlation between the two under different process parameters, improve the model's prediction accuracy for curing time, and provide a basis for the glue filling system to match the corresponding model according to real-time process parameters, enhancing the pertinence of process parameter adjustment and the adaptability of system decision-making;

[0083] Extract the data of each cluster from all the dominant correlation direction clusters as the model construction dataset; divide the dataset into training set and validation set;

[0084] The glue filling process parameters and structural complexity are used as input features, and the glue curing time is used as the output target;

[0085] Among them, the glue filling process parameters are used as input features to distinguish the clusters to which they belong and select the corresponding correlation model;

[0086] The least squares method is used to fit the data sets in each cluster to obtain the corresponding correlation model, and the performance of the model is verified using the test set; the verified correlation model is integrated into the glue filling control system;

[0087] It should be noted that if the correlation is nonlinear, polynomial regression or support vector regression can be used to fit the correlation model;

[0088] This step has at least the following beneficial effects: building a model based on clustered data of similar glue-filling process parameters, reducing prediction deviations caused by process differences, and making the curing time calculation more suitable for actual production scenarios;

[0089] By identifying the dominant relationship direction of strongly correlated clusters, the curing time parameters can be dynamically adjusted for modules with different structural characteristics, reducing incomplete curing or time waste caused by structural complexity;

[0090] After the model is integrated into the glue filling control system, the system can automatically match the corresponding model according to the real-time structural complexity value, realize the intelligent calculation of the curing time, and provide data support for subsequent process optimization such as flow rate adjustment;

[0091] Step 3: Based on the relevant model and the structural complexity of the current display module, the actual colloid curing time value is calculated, and the deviation between the actual colloid curing time value and the theoretical colloid curing time value is calculated to obtain a time deviation value. When the time deviation value is positive, the glue filling flow rate is adjusted based on the time deviation value;

[0092] In some embodiments, current potting process parameters are obtained, and corresponding correlation models are identified as target correlation models;

[0093] The glue dispensing system can quickly locate the relevant models of the corresponding clusters based on the current process parameters, reducing the parameter deviation caused by adapting one model to all scenarios;

[0094] Substitute the structural complexity value of the current display module into the target-related model as a known value and output the corresponding actual colloid curing time value;

[0095] The actual colloid curing time is the colloid curing time required for the current display module structure, calculated based on the target-related model, that is, the relationship between the colloid curing time and the structural complexity value.

[0096] Obtain theoretical colloid solidification value;

[0097] It will be understood by those skilled in the art that the theoretical colloid solidification value refers to the time required for the colloid to transform from a liquid state to a solid state, which can be found in the technical manual or product specification provided by the supplier;

[0098] The time deviation value is obtained by performing a difference calculation between the actual colloid solidification value and the theoretical colloid solidification value;

[0099] Identify the positive and negative of the time deviation value. If the time deviation value is negative or equal to zero, it means that the actual colloid solidification value is less than or equal to the theoretical colloid solidification value. Therefore, the colloid solidification can be completed within the theoretical time.

[0100] If the time deviation value is positive, it means that the actual colloid solidification value is greater than the theoretical colloid solidification value. Therefore, the glue filling process may not be completed within the theoretical colloid solidification time, and the colloid flow rate adjustment process needs to be performed;

[0101] Colloid flow rate adjustment is performed to speed up the flow of colloid so that the colloid solidification time can be completed within a reasonable time;

[0102] Get the total glue injection amount and the current glue injection speed value, calculate the ratio of the total glue injection amount to the current glue injection speed value, and get the current glue injection completion time;

[0103] Calculate the difference between the current glue filling completion time and the time deviation value to obtain the target glue filling completion time;

[0104] Calculate the ratio of the total glue filling volume to the target glue filling completion time to obtain the target glue filling speed;

[0105] The target glue filling speed is the target glue filling speed value that needs to be adjusted;

[0106] This step has at least the following beneficial effects: by combining the relevant model with the real-time structural complexity value to calculate the actual curing time, and dynamically adjusting the colloid flow rate based on the time deviation, it can match the structural characteristics of the display module with the requirements of the glue filling process;

[0107] This can reduce incomplete curing or time waste caused by the mismatch between theoretical curing time and actual structure, and ensure that the colloid is filled within a reasonable time by adjusting the flow rate, reducing quality problems such as glue shortage and bubbles.

[0108] At the same time, the glue pouring parameters can be dynamically adjusted to improve the adaptability of the production line to modules with different structures, optimize production efficiency while ensuring the reliability of glue pouring, and reduce production costs caused by process delays.

[0109] This example optimizes the situation where the complex internal structure of the display module affects the flow of the colloid during glue pouring, thereby causing changes in the curing time. Specifically, by calculating the structural complexity value, the degree of obstruction of the complex structure is converted into a quantifiable numerical indicator. Combined with the relevant model constructed based on historical data, the prediction accuracy of the curing time is improved, and incomplete curing caused by the deviation between the theoretical value and the actual value is reduced. When the complex structure causes the actual curing time to exceed the theoretical value, the glue pouring speed is automatically adjusted according to the time deviation value. By accelerating the colloid flow rate to offset the structural obstruction, the colloid is completed and cured within the target time, reducing the bubble rate caused by flow lag.

[0110] Example 2:

[0111] Based on the same inventive concept as the glue filling method of a display module in the above embodiment, Figure 2 As shown, the present application provides a glue filling system for a display module, wherein the system specifically includes:

[0112] Module structure analysis module: Before the glue filling process, the module structure of the display module is obtained, the density and height difference of the internal components of the module structure are analyzed, the complexity of the module structure is evaluated, and the complexity type of the module structure is determined;

[0113] This module performs the following process: before glue pouring, the module structure of the display module is first obtained. With the help of design drawings and drawing software, a schematic diagram of the internal component layout is drawn and the positional relationship is marked. The connection density is obtained by counting the ratio of the number of component connection points to the total number to characterize the component density. The height difference between the highest point and the lowest point of the component is measured and compared with the height of the lowest point to obtain the height deviation. The connection density and height deviation are weighted and fused by the experimental verification method to determine the weights and obtain the structural complexity value. This value is used to reflect the comprehensive degree of obstruction of the module structure to the flow of colloid. The experimental verification method is to conduct glue pouring experiments by designing module samples with different structures, and combine subjective scoring and linear regression to determine the weights, so as to complete the evaluation of the module structure complexity and type determination.

[0114] Data relationship analysis module: Extract historical data from the glue potting process of the display module, cluster the data according to the glue potting process parameters, obtain the glue curing time data and structural complexity value data corresponding to each cluster, analyze whether the glue curing time and structural complexity value are correlated, and if so, construct correlation models for each cluster;

[0115] This module performs the following process: first, extract historical glue pouring data (including glue pouring process parameters, glue curing time, and structural complexity values), use a hierarchical clustering algorithm to cluster the data according to process parameters, and merge similar data clusters by calculating the Euclidean distance until the cluster number threshold or distance condition is reached. Multiple clusters with similar process parameters are obtained. The curing time and structural complexity values ​​in each cluster are analyzed by the Pearson correlation coefficient. The proportion of the number of strongly correlated clusters and the proportion of the dominant correlation direction are calculated. The correlation coefficient is obtained comprehensively. After comparing with the preset limit, a correlation model is constructed for the strongly correlated clusters. The data is divided into a training set and a validation set. The process parameters and structural complexity values ​​are used as input and the curing time is used as output. The model is fitted and verified by the least squares method and finally integrated into the glue pouring system. If a nonlinear relationship exists, the polynomial regression method is used for modeling.

[0116] Flow rate adjustment module: Based on the relevant model and the structural complexity of the current display module, the actual colloid curing time value is calculated, and the deviation between the actual colloid curing time value and the theoretical colloid curing time value is calculated to obtain a time deviation value. When the time deviation value is positive, the colloid flow rate is adjusted based on the time deviation value;

[0117] This module performs the following process: first, obtain the current glue pouring process parameters to identify the corresponding target-related model, substitute the structural complexity value of the current display module into the model to calculate the actual glue curing time, and then subtract it from the theoretical curing time (obtained from the supplier's technical manual) to obtain the time deviation value; if the deviation value is positive, it means that the actual curing time is longer than the theoretical value, and the flow rate needs to be adjusted. The current completion time is calculated by the total amount of glue poured and the current speed, and the time deviation is subtracted to obtain the target completion time. The total amount of glue poured is then divided by the target time to obtain the target glue pouring speed that needs to be adjusted, so as to speed up the glue flow and ensure that the curing process is completed within a reasonable time.

[0118] Example 3:

[0119] like Figure 3 and Figure 4 As shown, this instruction also provides a glue pouring jig for performing a glue pouring method of a display module in the above embodiment, and the glue pouring jig specifically includes: a male mold and a female mold;

[0120] The master mold is fixedly installed on the reference surface of the glue filling equipment, with multiple sets of positioning columns as positioning components.

[0121] They are distributed in an array on the master mold substrate, and each group consists of a main positioning column and an auxiliary positioning column;

[0122] The bottom of the positioning column is fixed to the reference surface by T-slot bolts, and the top is processed into a frustum shape to facilitate the rapid alignment and insertion of the male mold;

[0123] A groove matching the equipment reference surface is milled on the bottom surface of the master mold base plate and locked with countersunk bolts (M8-M10) to ensure the installation rigidity.

[0124] The male mold cooperates with the female mold through a guide mechanism;

[0125] A stepped hole is provided on the bottom plate of the male mold corresponding to the position of the positioning column of the female mold. The diameter of the upper hole is larger than the top of the positioning column, and the diameter of the lower hole is interference fit with the cylindrical section of the positioning column.

[0126] Guide sleeves are installed on both sides of the male mold to form a sliding pair with the female mold guide pins. The length of the guide pins must be the same as the male mold pressing stroke to prevent collision during disengagement. The guide pins are made of self-lubricating copper alloy.

[0127] The top of the male mold is hinged to the piston rod of the equipment cylinder through a connecting plate.

[0128] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for glue filling of a display module, characterized in that: The following steps are involved: Before the glue filling process, the module structure of the display module is obtained, the connection density and height deviation of the internal components of the module structure are analyzed, the structural complexity value is output, and the complexity of the module structure is evaluated; The process of outputting the complex structure value is as follows: Count the number of connection points between components and the total number of components in the display module, and calculate the ratio of the number of connection points to the total number of components as the connection density; Measure the height of the highest point and the lowest point of all components in the display module, calculate the difference between the highest point and the lowest point, and then calculate the ratio with the height of the lowest point to obtain the height deviation; By fusing the connection density and the height deviation, the structural complexity value is output; Extract historical data from the glue potting process of the display module, cluster the historical data according to the glue potting process parameters, obtain the glue curing time data and structural complexity value data corresponding to each cluster, analyze the glue curing time and structural complexity value, and use two indicators to identify two correlation indicators: the proportion of strongly correlated clusters and the proportion of dominant correlation directions to determine whether there is a correlation. If a correlation is found, construct a correlation model for each cluster. The process of determining whether there is a correlation is as follows: Obtain the correlation of each cluster, extract clusters whose absolute correlation value is greater than the correlation threshold, and count their number as the number of strongly correlated clusters; then perform a ratio processing on this value with the total number of clusters to obtain the proportion of strongly correlated clusters; Identify the positive and negative correlations in the strongly correlated clusters, and count the number of clusters with positive correlations and the number of clusters with negative correlations respectively; extract the maximum value as the number of dominant correlation direction clusters, and calculate the ratio of the number of dominant correlation direction clusters to the number of strongly correlated clusters to obtain the proportion of dominant correlation directions; Add the proportion of strongly correlated clusters and the proportion of dominant correlation directions, and output the correlation coefficient; If the correlation coefficient is greater than or equal to the correlation coefficient limit, it means that there is a correlation between the colloid curing time and the structural complexity value; The process of building a correlation model for clustering clusters is as follows: Extract each cluster data from all dominant correlation direction clusters as the model building dataset; divide the dataset into training set and validation set; The glue filling process parameters and structural complexity are used as input features, and the glue curing time is used as the output target; Among them, the glue filling process parameters are used as input features to distinguish the clusters to which they belong and select the corresponding correlation model; The least squares method is used to fit the data sets in each cluster to obtain the corresponding correlation model, and the performance of the model is verified using the test set; the verified correlation model is integrated into the glue filling control system; According to each cluster correlation model, the current glue pouring process parameters are input to identify the target correlation model. The target correlation model is input in combination with the structural complexity value of the current display module, and the actual colloid curing time value is output. The deviation between the actual colloid curing time value and the theoretical colloid curing time value is calculated to obtain the time deviation value. The positive and negative nature of the time deviation value is identified. If the time deviation value is positive, the glue pouring flow rate is adjusted based on the time deviation value.

2. The method for glue-filling a display module according to claim 1, wherein: A hierarchical clustering algorithm is used to cluster the historical data according to the glue filling process parameters, which is used to analyze the relationship between the colloid curing time and the structural complexity value under the premise of similar glue filling process parameters.

3. The method for glue-filling a display module according to claim 1, wherein: The relevance is obtained in the following manner: For each cluster, the corresponding colloid solidification time data and structural complexity value data are extracted, and the Pearson correlation coefficient of the colloid solidification time data and the structural complexity value data is calculated to characterize the correlation, thereby obtaining the corresponding correlation of each cluster.

4. The method for glue-filling a display module according to claim 1, wherein: The process of obtaining the time deviation value is as follows: Obtain the current glue filling process parameters and identify the corresponding related model as the target related model; Substitute the structural complexity value of the current display module into the target-related model and output the corresponding actual colloid curing time value; Obtain theoretical colloid solidification time value; The time deviation value is obtained by calculating the difference between the actual colloid solidification value and the theoretical colloid solidification time value.

5. The method for glue-filling a display module according to claim 1, wherein: The process of identifying the positive and negative time deviation values ​​is as follows: Identify the positive and negative of the time deviation value. If the time deviation value is negative or equal to zero, it means that the actual colloid curing time value is less than or equal to the theoretical colloid curing time value; If the time deviation value is positive, it means that the actual colloid curing time value is greater than the theoretical colloid curing time value, and the glue filling flow rate adjustment process needs to be performed.

6. The method for glue-filling a display module according to claim 1, wherein: The process of adjusting the glue filling flow rate is as follows: Get the total glue injection amount and the current glue injection speed value, calculate the ratio of the total glue injection amount to the current glue injection speed value, and get the current glue injection completion time; Calculate the difference between the current glue filling completion time and the time deviation value to obtain the target glue filling completion time; The target glue dispensing speed is obtained by calculating the ratio of the total glue dispensing amount to the target glue dispensing completion time.

7. A glue pouring jig, characterized in that: The jig is used to perform the method described in any one of claims 1 to 6 above, and the glue-filling jig specifically comprises: a male mold and a female mold; The master mold includes multiple sets of positioning columns and guide columns fixedly mounted on the reference surface, and the bottom surface of the master mold base plate is milled with a groove matching the equipment reference surface and locked by bolts; The male mold bottom plate is provided with positioning holes corresponding to the female mold positioning columns, and guide sleeves are installed on both sides of the male mold to slide with the female mold guide columns.

Images