A method, system and device for detecting defects in the production of an LCD display screen

Abstract

The present application provides a method, a system and a device for detecting defects in the production of an LCD display screen. Among them, the method includes: when the LCD is sealed, collecting the image of the dispensing port of the dispensing and sealing device, predicting the dispensing amount, and obtaining the predicted dispensing amount; performing glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making to obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient; predicting the uneven thickness of the LCD to obtain a first defect parameter; predicting the damage of the cured liquid crystal to obtain a second defect parameter; generating a defect parameter of the LCD according to the first defect parameter and the second defect parameter as the defect detection result. The present application solves the technical problem of low accuracy and efficiency in defect detection during the LCD sealing and dispensing process in the prior art, and achieves the technical effect of improving the accuracy and efficiency of defect detection in the production of the LCD display screen through the analysis of the dispensing port image and the prediction of multi-parameter defects.

Description

Technical Field

[0001] The present invention relates to the field of LCD production inspection, and particularly to a method, system and device for detecting defects in the production of LCD displays. Background Art

[0002] With the rapid development of display technology, LCD displays have been widely used in various electronic devices. In the production process of LCDs, sealing and dispensing is one of the key process steps, and its quality directly affects the display effect and service life of LCDs. In the prior art, the defect detection of LCD sealing and dispensing mainly relies on manual sampling inspection or post-production inspection of finished products, and it is difficult to detect defects in real time and efficiently during the production process. Some improved methods attempt to judge whether the dispensing amount is qualified by setting a fixed threshold. However, due to the dynamic changes in the operating state of the dispensing equipment, especially the blockage that may be formed due to the solidification of residual glue at the dispensing nozzle, the accuracy of this simple threshold judgment method is limited. Therefore, there are problems of low accuracy and efficiency in defect detection during the LCD sealing and dispensing process in the prior art. Summary of the Invention

[0003] The present invention aims at the technical problems of low accuracy and efficiency in defect detection during the LCD sealing and dispensing process in the prior art, and provides a method, system and device for detecting defects in the production of LCD displays to solve them.

[0004] The technical solutions of the present invention to solve the above technical problems are as follows:

[0005] In a first aspect, the present invention provides a method for detecting defects in the production of LCD displays, including: when sealing the LCD, collecting an image of the dispensing nozzle of the sealing and dispensing equipment, predicting the dispensing amount, and obtaining a predicted dispensing amount; according to the predicted dispensing amount and a preset dispensing amount, performing glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making, and obtaining a redundancy defect analysis coefficient and a shortage defect analysis coefficient; according to the redundancy defect analysis coefficient, predicting the thickness non-uniformity of the LCD based on the predicted dispensing amount, and obtaining a first defect parameter, and according to the shortage defect analysis coefficient, predicting the damage of the cured liquid crystal based on the predicted dispensing amount, and obtaining a second defect parameter; generating a defect parameter of the LCD based on the first defect parameter and the second defect parameter as a defect detection result.

[0006] Optionally, when sealing the LCD, collecting an image of the dispensing nozzle of the sealing and dispensing equipment, predicting the dispensing amount, and obtaining a predicted dispensing amount, includes: when sealing the LCD, collecting an image of the dispensing nozzle of the sealing and dispensing equipment; inputting the image of the dispensing nozzle into a pre-trained dispensing amount predictor, and outputting to obtain a predicted dispensing amount.

[0007] Optionally, the training step of the dispensing amount predictor includes: collecting a set of sample dispensing port images based on the production data of the LCD display screen within a historical time, and collecting the dispensing amount under each sample dispensing port image, which is labeled as the sample dispensing amount, to obtain a set of sample dispensing amounts; constructing a dispensing amount predictor based on a convolutional neural network; using the set of sample dispensing port images and the set of sample dispensing amounts to perform supervised training and testing on the dispensing amount predictor, and completing the pre-training after the accuracy rate is qualified.

[0008] Optionally, based on the predicted dispensing amount and the preset dispensing amount, perform glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making to obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient, including: obtaining the preset dispensing amount of the LCD seal, and collecting the maximum dispensing amount error deviating from the preset dispensing amount according to the dispensing data within a historical time; calculating the difference between the predicted dispensing amount and the preset dispensing amount, and calculating the ratio to the maximum dispensing amount error to obtain an error coefficient; obtaining a preset redundancy defect analysis coefficient and a preset shortage defect analysis coefficient; calculating the sum of the preset redundancy defect analysis coefficient and the error coefficient to obtain a redundancy defect analysis coefficient, and calculating the difference between the preset shortage defect analysis coefficient and the error coefficient to obtain a shortage defect analysis coefficient.

[0009] Optionally, based on the redundancy defect analysis coefficient, perform uneven thickness prediction of the LCD based on the predicted dispensing amount to obtain a first defect parameter, and based on the shortage defect analysis coefficient, perform cured liquid crystal damage prediction based on the predicted dispensing amount to obtain a second defect parameter, including: using the redundancy defect analysis coefficient, combining the number of N uneven thickness prediction branches in the pre-trained uneven thickness predictor, and calculating to obtain U, where N is a positive integer and U is a positive integer less than or equal to N; randomly selecting U uneven thickness prediction branches, inputting the predicted dispensing amount, predicting and outputting U uneven thickness prediction parameters, and calculating the mean value to obtain a first defect parameter; using the shortage defect analysis coefficient, combining the number of N liquid crystal damage prediction branches in the pre-trained liquid crystal damage predictor, and calculating to obtain U; randomly selecting U liquid crystal damage prediction branches, inputting the predicted dispensing amount, predicting and outputting U liquid crystal damage prediction parameters, and calculating the mean value to obtain a second defect parameter.

[0010] Optionally, the pre-training step of the thickness non-uniformity predictor includes: according to the LCD sealing data within a historical time, collecting a set of sample predicted dispensing amounts, and collecting the amplitude of thickness non-uniformity of the LCD under different sample predicted dispensing amounts, and obtaining a set of sample thickness non-uniformity parameters through annotation; randomly selecting with replacement to obtain the first thickness non-uniformity training data from the set of sample predicted dispensing amounts and the set of sample thickness non-uniformity parameters; continuously randomly selecting with replacement to obtain N pieces of thickness non-uniformity training data; using deep learning to construct N thickness non-uniformity prediction branches, and respectively using the N pieces of thickness non-uniformity training data for supervised training and testing until the accuracy rate is qualified, and completing the pre-training.

[0011] Optionally, generating the defect parameter of the LCD as the defect detection result according to the first defect parameter and the second defect parameter includes: generating the defect parameter of the LCD according to the first defect parameter and the second defect parameter; using the defect parameter as the defect detection result for display and reminder.

[0012] In a second aspect, the present invention provides a defect detection system for LCD display production, including: a dispensing amount prediction module, configured to collect an image of the dispensing port of a sealing dispensing device during LCD sealing, perform dispensing amount prediction, and obtain a predicted dispensing amount; a glue amount analysis module, configured to perform glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making according to the predicted dispensing amount and a preset dispensing amount, and obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient; a defect prediction module, configured to perform thickness non-uniformity prediction of the LCD based on the predicted dispensing amount according to the redundancy defect analysis coefficient to obtain a first defect parameter, and perform cured liquid crystal damage prediction based on the predicted dispensing amount according to the shortage defect analysis coefficient to obtain a second defect parameter; a result generation module, configured to generate a defect parameter of the LCD according to the first defect parameter and the second defect parameter as the defect detection result.

[0013] In a third aspect, the present application provides an electronic device, which includes: a processor; a memory for storing executable instructions of the processor; wherein, the processor is configured to execute a defect detection method for LCD display production provided by the present application.

[0014] The beneficial effects of the present invention are:

[0015] When sealing the LCD, capture the image of the dispensing nozzle of the dispensing and sealing equipment, predict the dispensing volume, obtain the predicted dispensing volume, be able to obtain the working state image of the dispensing equipment in real time, and predict the actual dispensing volume based on image analysis, which solves the problem that the traditional method cannot know the dispensing volume in time and provides basic data for subsequent defect analysis. According to the predicted dispensing volume and the preset dispensing volume, conduct glue volume redundancy defect analysis decision-making and glue volume shortage defect analysis decision-making, obtain the redundancy defect analysis coefficient and the shortage defect analysis coefficient, and by comparing the difference between the predicted dispensing volume and the preset dispensing volume, calculate the possible defect risk coefficients in the cases of excessive glue volume and insufficient glue volume respectively, providing parameter support for subsequent specific defect prediction. According to the redundancy defect analysis coefficient, based on the predicted dispensing volume, predict the uneven thickness of the LCD to obtain the first defect parameter; at the same time, according to the shortage defect analysis coefficient, based on the predicted dispensing volume, predict the damage of the cured liquid crystal to obtain the second defect parameter, and conduct targeted defect prediction for different types of dispensing abnormalities: when the glue volume is excessive, it may lead to uneven liquid crystal thickness, and when the glue volume is insufficient, it may lead to damage to the liquid crystal during the curing process, thereby obtaining the corresponding defect parameters. According to the first defect parameter and the second defect parameter, generate the defect parameter of the LCD as the defect detection result, realizing the accurate and efficient detection of defects on the LCD display screen.

[0016] Through the above technical solutions, the present application realizes real-time defect prediction and detection during the LCD sealing and dispensing process, improves the accuracy and efficiency of defect detection, and avoids the problems of low accuracy and efficiency caused by relying on manual sampling inspection or later finished product inspection in the traditional method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic flow chart of a method for detecting defects in the production of an LCD display screen provided by the present invention;

[0018] Figure 2 It is a schematic structural diagram of a system for detecting defects in the production of an LCD display screen provided by the present invention;

[0019] Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention.

[0020] In the drawings, the components represented by the reference numerals are as follows:

[0021] Dispensing volume prediction module 11, glue volume analysis module 12, defect prediction module 13, result generation module 14, electronic device 200, memory 210, processor 220, computer program 211. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or advantageous than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0025] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a method for detecting defects in the production of an LCD display screen, including:

[0026] S100: When sealing the LCD, collect the image of the dispensing port of the dispensing and sealing device, predict the dispensing amount, and obtain the predicted dispensing amount.

[0027] Specifically, when the LCD liquid crystal panel is in the sealing process, the image acquisition device is used to perform real-time image acquisition on the dispensing port of the dispensing and sealing device to obtain the dispensing port image, which reflects the state of the dispensing port of the dispensing and sealing device. The state of the dispensing port affects the actual dispensing amount. When the residual glue at the dispensing port of the dispensing and sealing device solidifies and forms a blockage, it will significantly affect the output of the actual dispensing amount. After obtaining the dispensing port image, the actual state of the dispensing port is processed through image analysis technology to predict the dispensing amount that will be output under the current dispensing port state, so as to obtain the predicted dispensing amount, providing necessary parameters for subsequent glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making.

[0028] S200: Based on the predicted dispensing volume and the preset dispensing volume, perform glue volume redundancy defect analysis decision-making and glue volume shortage defect analysis decision-making to obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient.

[0029] Specifically, after obtaining the predicted dispensing volume, compare and analyze it with the preset dispensing volume in the LCD display sealing process, and perform glue volume redundancy defect analysis decision-making and glue volume shortage defect analysis decision-making respectively. Among them, the preset dispensing volume refers to the standard dispensing volume pre-determined according to the product design requirements and production process standards in the LCD display sealing process, which represents the optimal dispensing volume that should be used during the sealing process under ideal conditions. The glue volume redundancy defect analysis decision-making is for the situation where the predicted dispensing volume exceeds the preset dispensing volume. In this case, too much glue volume will cause the liquid crystal to be squeezed, resulting in uneven thickness of the LCD display and affecting the display effect. The glue volume shortage defect analysis decision-making is for the situation where the predicted dispensing volume is lower than the preset dispensing volume. Insufficient glue volume may cause the glue to cure prematurely during the curing process, allowing ultraviolet light to directly irradiate the liquid crystal and causing damage to the liquid crystal.

[0030] Through the glue volume redundancy defect analysis decision-making and the glue volume shortage defect analysis decision-making, the redundancy defect analysis coefficient and the shortage defect analysis coefficient are calculated respectively. These two coefficients reflect the risk levels of corresponding defects that may occur under the current dispensing state, providing a parameter basis for subsequent steps of predicting LCD thickness non-uniformity and curing liquid crystal damage prediction, thereby improving the pertinence and accuracy of defect detection.

[0031] S300: Based on the redundancy defect analysis coefficient and the predicted dispensing volume, perform prediction of LCD thickness non-uniformity to obtain a first defect parameter. Based on the shortage defect analysis coefficient and the predicted dispensing volume, perform prediction of cured liquid crystal damage to obtain a second defect parameter.

[0032] Specifically, first, use the redundancy defect analysis coefficient to perform prediction of LCD thickness non-uniformity based on the predicted dispensing volume. When the dispensing volume is too large, the excess glue will squeeze the liquid crystal, resulting in uneven thickness of the liquid crystal layer in different regions of the LCD display, and further affecting the consistency of the display effect. Through this prediction process, a first defect parameter is obtained, which quantitatively represents the degree of thickness non-uniformity that may be generated under the current dispensing state. At the same time, use the shortage defect analysis coefficient to perform prediction of cured liquid crystal damage based on the predicted dispensing volume. When the dispensing volume is insufficient, during the sealing and curing process, the glue may cure prematurely, allowing ultraviolet light to directly irradiate the liquid crystal, thereby causing damage to the liquid crystal material. Through this prediction process, a second defect parameter is obtained, which quantitatively represents the degree of liquid crystal damage that may be generated under the current dispensing state.

[0033] Through the first defect parameter and the second defect parameter, the defect risk of the current dispensing state that may cause on the LCD display screen is reflected from two directions of excessive dispensing amount and insufficient dispensing amount respectively, providing a comprehensive parameter basis for the subsequent generation of defect detection results.

[0034] S400: Generate a defect parameter of the LCD as the defect detection result according to the first defect parameter and the second defect parameter.

[0035] Specifically, based on the first defect parameter predicted from thickness non-uniformity and the second defect parameter predicted from cured liquid crystal damage, through a specific data fusion algorithm, a defect parameter of the LCD that can comprehensively reflect the sealing quality of the LCD display screen is generated as the defect detection result. This defect parameter takes into account both the thickness non-uniformity problem that may be caused by excessive dispensing amount and the liquid crystal damage problem that may be caused by insufficient dispensing amount, thus realizing a comprehensive evaluation of the sealing quality of the LCD display screen. For example, the defect risks of thickness non-uniformity and liquid crystal damage are weighted and combined, and appropriate weights are assigned to different types of defects according to the current production requirements. In some product models, more attention may be paid to display uniformity, so the weight of the defect parameter of thickness non-uniformity will be higher; while in other product models, more attention may be paid to liquid crystal life, so the weight of the defect parameter of liquid crystal damage will be higher. Through defect parameter fusion, it can flexibly adapt to the quality control requirements of different products and provide more accurate defect detection results.

[0036] The generated defect parameter of the LCD as the final result of defect detection can be used to guide quality control decisions on the production line. Through this parameter, potential defect risks in the LCD production process can be detected in a timely manner, and corresponding adjustment measures can be taken to improve the production yield and product quality of the LCD display screen.

[0037] Furthermore, when sealing the LCD, collect the dispensing port image of the sealing dispensing device, perform dispensing amount prediction, and obtain the predicted dispensing amount, including:

[0038] S110: When sealing the LCD, collect the dispensing port image of the sealing dispensing device;

[0039] S120: Input the dispensing port image into a pre-trained dispensing amount predictor, and output and obtain the predicted dispensing amount.

[0040] In a feasible implementation manner, during the LCD sealing process, an image acquisition device is used to perform real-time image acquisition on the dispensing port of the dispensing and sealing device to obtain a dispensing port image. This dispensing port image contains key information such as the current opening state of the dispensing port and the residual glue situation, and this information is closely related to the actual dispensing volume. Subsequently, the obtained dispensing port image is input into a pre-trained dispensing volume predictor for processing. The dispensing volume predictor is an algorithm model specifically used to predict the dispensing volume. By analyzing the features in the dispensing port image, such as the opening size, shape, and residual glue distribution, it outputs the predicted dispensing volume. This dispensing volume predictor has been fully trained and can accurately predict the glue volume that will be output during the actual dispensing process based on the features of the dispensing port image, obtaining the predicted dispensing volume.

[0041] Through the above steps, it is possible to obtain an accurate prediction of the dispensing volume to be used before actual dispensing, providing a reliable data basis for subsequent defect analysis and decision-making. By means of pre-prediction, the problem in traditional methods that the suitability of the dispensing volume can only be detected after dispensing is effectively solved, realizing the pre-positioning of defect detection.

[0042] Furthermore, the training steps of the dispensing volume predictor include:

[0043] S131: According to the LCD display production data within the historical time, collect a set of sample dispensing port images, and collect the dispensing volume under each sample dispensing port image, label it as the sample dispensing volume, and obtain a set of sample dispensing volumes;

[0044] S132: Based on a convolutional neural network, construct a dispensing volume predictor;

[0045] S133: Use the set of sample dispensing port images and the set of sample dispensing volumes to perform supervised training and testing on the dispensing volume predictor. After the accuracy is qualified, complete the pre-training.

[0046] In a preferred implementation manner, first, based on the LCD display production data within the historical time, a training data set is constructed. Specifically, a large number of sample dispensing port images are collected from the LCD display production data within the historical time to form a set of sample dispensing port images. At the same time, for each sample dispensing port image, record its corresponding actual dispensing volume as the sample dispensing volume to form a set of sample dispensing volumes. In this way, a complete training data set containing input features (dispensing port images) and output labels (sample dispensing volumes) is obtained.

[0047] Next, a dispensing volume predictor is constructed based on convolutional neural network technology. Convolutional neural network is a deep learning algorithm used to process image data. Through multiple layers of convolution and pooling operations, it can effectively extract feature information in images and is suitable for extracting features related to the dispensing volume from the dispensing nozzle images. After that, the constructed dispensing volume predictor is supervised and trained using the obtained sample dispensing nozzle image set and sample dispensing volume set. During the training process, the sample dispensing nozzle images are input, and the dispensing volume predictor outputs the predicted dispensing volume, which is then compared with the known sample dispensing volume. The error is calculated and the parameters of the dispensing volume predictor are adjusted accordingly. At the same time, test verification is carried out to ensure that the accuracy of the dispensing volume predictor reaches the predetermined standard, completing the entire pre-training process.

[0048] Through the training method based on a large amount of historical data, a high-precision dispensing volume predictor can be constructed, providing reliable support for detecting defects in the sealing of LCD displays.

[0049] Furthermore, it is characterized in that, according to the predicted dispensing volume and the preset dispensing volume, glue volume redundancy defect analysis decision-making and glue volume shortage defect analysis decision-making are carried out to obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient, including:

[0050] S210: Obtain the preset dispensing volume for LCD sealing, and collect the maximum dispensing volume error deviating from the preset dispensing volume according to the dispensing data within the historical time.

[0051] S220: Calculate the difference between the predicted dispensing volume and the preset dispensing volume, and calculate the ratio with the maximum dispensing volume error to obtain an error coefficient.

[0052] S230: Obtain the preset redundancy defect analysis coefficient and the preset shortage defect analysis coefficient.

[0053] S240: Calculate the sum of the preset redundancy defect analysis coefficient and the error coefficient to obtain the redundancy defect analysis coefficient, and calculate the difference between the preset shortage defect analysis coefficient and the error coefficient to obtain the shortage defect analysis coefficient.

[0054] In a preferred embodiment, first, obtain the preset dispensing volume for the LCD sealing process. This preset dispensing volume is a standard dispensing volume pre-determined based on product design and process requirements. At the same time, based on the statistical analysis of dispensing data within a historical time period, collect the maximum dispensing volume error deviating from the preset dispensing volume. This maximum dispensing volume error serves as the reference for subsequent calculations and reflects the maximum fluctuation range of the dispensing volume during the production process. Then, calculate the difference between the current predicted dispensing volume and the preset dispensing volume, and calculate the ratio of this difference to the maximum dispensing volume error to obtain an error coefficient. The obtained error coefficient is a numerical value with a plus or minus sign. When the predicted dispensing volume is greater than the preset dispensing volume, the error coefficient is positive; when the predicted dispensing volume is less than the preset dispensing volume, the error coefficient is negative. For example, if the maximum error amount of the predicted dispensing volume is 10% less than the preset dispensing volume, the error coefficient is -10%.

[0055] Then, obtain a preset redundant defect analysis coefficient and a preset insufficient defect analysis coefficient. The preset redundant defect analysis coefficient refers to the benchmark analysis intensity set for the problem of uneven LCD thickness that may be caused by excessive dispensing volume under standard working conditions. This coefficient is preset based on product characteristics, process requirements, and historical data analysis results. For example, it is set to 50%, indicating that under standard conditions, 50% of the computing resources will be allocated for uneven thickness prediction. The preset insufficient defect analysis coefficient refers to the benchmark analysis intensity set for the problem of liquid crystal damage that may be caused by insufficient dispensing volume under standard working conditions. This coefficient is also preset based on product characteristics, process requirements, and historical data analysis results. For example, it is set to 50%, indicating that under standard conditions, 50% of the computing resources will be allocated for liquid crystal damage prediction. After that, obtain the final redundant defect analysis coefficient and insufficient defect analysis coefficient through different calculation methods. For the redundant defect analysis coefficient, it is obtained by adding the preset redundant defect analysis coefficient and the error coefficient. For example, 50% + 10% = 60%. For the insufficient defect analysis coefficient, it is obtained by subtracting the error coefficient from the preset insufficient defect analysis coefficient. For example, 50% - 10% = 40%. Since a large dispensing volume will cause the liquid crystal to be squeezed and result in uneven thickness, the above calculation method makes the redundant defect analysis coefficient increase correspondingly when the predicted dispensing volume is large, and more resources will be allocated for uneven thickness prediction. At the same time, since a large dispensing volume results in a lower risk of ultraviolet damage to the liquid crystal, the insufficient defect analysis coefficient will decrease correspondingly, and the resources used for liquid crystal damage prediction will be reduced. Through this dynamic adjustment mechanism, it is possible to perform targeted defect detection based on the current dispensing state, improving the detection efficiency and accuracy.

[0056] Furthermore, based on the redundant defect analysis coefficient and the predicted dispensing volume, perform uneven thickness prediction of the LCD to obtain a first defect parameter. Based on the insufficient defect analysis coefficient and the predicted dispensing volume, perform cured liquid crystal damage prediction to obtain a second defect parameter, including:

[0057] S310: Using the redundant defect analysis coefficient, in combination with the number of N thickness non-uniformity prediction branches in the pre-trained thickness non-uniformity predictor, calculate to obtain U, where N is a positive integer and U is a positive integer less than or equal to N;

[0058] S320: Randomly select U thickness non-uniformity prediction branches, input the predicted dispensing amount, predict and output U thickness non-uniformity prediction parameters, calculate the mean value to obtain the first defect parameter;

[0059] S330: Using the insufficient defect analysis coefficient, in combination with the number of N liquid crystal damage prediction branches in the pre-trained liquid crystal damage predictor, calculate to obtain U;

[0060] S340: Randomly select U liquid crystal damage prediction branches, input the predicted dispensing amount, predict and output U liquid crystal damage prediction parameters, calculate the mean value to obtain the second defect parameter.

[0061] In a preferred embodiment, the idea of ensemble learning is adopted to dynamically adjust the number of prediction branches, realizing the reasonable allocation of computing resources and the optimization of prediction accuracy.

[0062] First, using the redundant defect analysis coefficient, in combination with the total number of N thickness non-uniformity prediction branches in the pre-trained thickness non-uniformity predictor, calculate the number of prediction branches U actually needed. Here, N is a positive integer representing the total number of all thickness non-uniformity prediction branches in the thickness non-uniformity predictor; U is also a positive integer and satisfies U ≤ N, representing the number of branches actually needed to be called for this prediction. The larger the redundant defect analysis coefficient, the larger the calculated value of U, which means more computing resources will be allocated for thickness non-uniformity prediction. Then, randomly select U branches from the N thickness non-uniformity prediction branches, input the predicted dispensing amount as an input parameter into these U prediction branches, and obtain U thickness non-uniformity prediction parameters. Subsequently, calculate the mean value of these U thickness non-uniformity prediction parameters as the first defect parameter. By randomly selecting multiple thickness non-uniformity prediction branches and taking the mean value, the deviation of a single thickness non-uniformity prediction branch can be reduced, improving the stability and accuracy of the overall prediction.

[0063] Similarly, an insufficient defect analysis coefficient is adopted, and combined with the total number of N liquid crystal damage prediction branches in the pre-trained liquid crystal damage predictor, the number of prediction branches U that actually need to be used is calculated. The larger the insufficient defect analysis coefficient, the larger the calculated value of U, which means that more computing resources will be allocated for liquid crystal damage prediction. Then, randomly select U liquid crystal damage prediction branches from the N liquid crystal damage prediction branches, input the predicted dispensing amount into these U liquid crystal damage prediction branches, obtain U liquid crystal damage prediction parameters, and calculate the mean value of these U liquid crystal damage prediction parameters as the second defect parameter.

[0064] Through dynamic prediction based on ensemble learning, the computing resource allocation can be flexibly adjusted according to the current dispensing state, improving the computing efficiency while ensuring the prediction accuracy, providing an efficient and reliable technical means for detecting production defects of LCD displays.

[0065] Further, the pre-training steps of the thickness non-uniformity predictor include:

[0066] S351: According to the LCD sealing data within the historical time, collect a set of sample predicted dispensing amounts, and collect the amplitude of thickness non-uniformity of the LCD under different sample predicted dispensing amounts, and label to obtain a set of sample thickness non-uniformity parameters;

[0067] S352: Randomly select the first thickness non-uniformity training data with replacement within the set of sample predicted dispensing amounts and the set of sample thickness non-uniformity parameters;

[0068] S353: Continue to randomly select N pieces of thickness non-uniformity training data with replacement;

[0069] S354: Use deep learning to construct N thickness non-uniformity prediction branches, and respectively use the N pieces of thickness non-uniformity training data for supervised training and testing until the accuracy rate is qualified to complete the pre-training.

[0070] In a preferred embodiment, to train the thickness non-uniformity predictor, first, according to the LCD sealing data collected within the historical time, collect a set of sample predicted dispensing amounts as the input features of the training data. At the same time, collect the actual measurement data of the LCD thickness non-uniformity phenomenon corresponding to different sample predicted dispensing amounts, and label these data as sample thickness non-uniformity parameters to form a set of sample thickness non-uniformity parameters as the output labels of the training data. In this way, the correspondence between the input features (predicted dispensing amount) and the output labels (thickness non-uniformity parameters) is established. Then, use the method of sampling with replacement to randomly select data from the set of sample predicted dispensing amounts and the set of sample thickness non-uniformity parameters to construct the first piece of thickness non-uniformity training data. Among them, sampling with replacement means that the same sample may be selected multiple times, and this sampling method helps to increase the diversity of the training data.

[0071] Subsequently, continue to use the same sampling method with replacement to randomly select data from the sample predicted dispensing volume set and the sample thickness non-uniformity parameter set to construct a total of N pieces of thickness non-uniformity training data. Although each piece of training data is derived from the same original data set, due to the characteristics of random sampling, there are differences between each piece of training data, and this difference is the basis for the effectiveness of ensemble learning. After that, adopt deep learning technology to construct N prediction branches for thickness non-uniformity with the same structure but independent parameters. Each prediction branch for thickness non-uniformity uses a corresponding piece of thickness non-uniformity training data for supervised training and testing until the prediction accuracy of each branch reaches the preset standard, completing the entire pre-training process.

[0072] It should be noted that a similar method can also be used for the pre-training process of the liquid crystal damage predictor. That is, based on historical data, sample the predicted dispensing volume and the corresponding liquid crystal damage parameters, construct multiple pieces of training data through sampling with replacement, and train multiple independent liquid crystal damage prediction branches to form a complete liquid crystal damage predictor.

[0073] Through this pre-training method based on ensemble learning, a predictor model with high robustness and prediction accuracy can be constructed, providing reliable technical support for defect detection in the LCD display production process.

[0074] Furthermore, according to the first defect parameter and the second defect parameter, generate the defect parameter of the LCD as the defect detection result, including:

[0075] S410: Generate the defect parameter of the LCD according to the first defect parameter and the second defect parameter;

[0076] S420: Use the defect parameter as the defect detection result and display a reminder.

[0077] In a feasible implementation, summarize the obtained first defect parameter and the second defect parameter to generate a comprehensive LCD defect parameter. This defect parameter comprehensively considers the thickness non-uniformity problem that may be caused by excessive dispensing volume (characterized by the first defect parameter) and the liquid crystal damage problem that may be caused by insufficient dispensing volume (characterized by the second defect parameter), and can comprehensively reflect the current sealing quality status of the LCD display.

[0078] Subsequently, use the generated defect parameter as the final defect detection result, display it through the human-machine interface of the production line control system, and trigger the corresponding reminder mechanism when necessary. This display reminder mechanism enables production personnel to timely understand the possible sealing defect risks of the currently produced LCD displays, and then take necessary adjustment measures, such as adjusting the parameters of the dispensing equipment, cleaning the blockage of the dispensing port, replacing the dispensing equipment, etc., thereby effectively preventing the production of defective products.

[0079] Through the above steps, the conversion from defect parameters to defect detection results is achieved, and the detection results are organically combined with the production control system, forming a complete closed-loop for defect detection and prevention of LCD display sealing, effectively improving the production yield and product quality of LCD displays.

[0080] Example two, as Figure 2 shown, based on the same inventive concept as the defect detection method for LCD display production provided in Example one, the present invention embodiment also provides a defect detection system for LCD display production, including:

[0081] The dispensing amount prediction module 11 is used to collect the image of the dispensing port of the sealing dispensing equipment during LCD sealing, perform dispensing amount prediction, and obtain the predicted dispensing amount;

[0082] The glue amount analysis module 12 is used to perform glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making based on the predicted dispensing amount and the preset dispensing amount, and obtain the redundancy defect analysis coefficient and the shortage defect analysis coefficient;

[0083] The defect prediction module 13 is used to perform uneven thickness prediction of the LCD based on the redundancy defect analysis coefficient and the predicted dispensing amount to obtain the first defect parameter, and perform cured liquid crystal damage prediction based on the shortage defect analysis coefficient and the predicted dispensing amount to obtain the second defect parameter;

[0084] The result generation module 14 is used to generate the defect parameters of the LCD based on the first defect parameter and the second defect parameter as the defect detection result.

[0085] Furthermore, the dispensing amount prediction module 11 includes the following execution steps:

[0086] During LCD sealing, collect the image of the dispensing port of the sealing dispensing equipment;

[0087] Input the dispensing port image into the pre-trained dispensing amount predictor, and output to obtain the predicted dispensing amount.

[0088] Furthermore, the dispensing amount prediction module 11 also includes the following execution steps:

[0089] According to the production data of LCD displays within the historical time, collect the sample dispensing port image set, and collect the dispensing amount under each sample dispensing port image, which is labeled as the sample dispensing amount, to obtain the sample dispensing amount set;

[0090] Based on the convolutional neural network, construct a dispensing amount predictor;

[0091] Using the sample dispensing port image set and the sample dispensing volume set, the dispensing volume predictor is supervised and trained and tested. After the accuracy is qualified, the pre-training is completed.

[0092] Further, the glue volume analysis module 12 includes the following execution steps:

[0093] Obtain the preset dispensing volume for the LCD sealing, and collect the maximum dispensing volume error deviating from the preset dispensing volume according to the dispensing data within the historical time.

[0094] Calculate the difference between the predicted dispensing volume and the preset dispensing volume, and calculate the ratio with the maximum dispensing volume error to obtain the error coefficient.

[0095] Obtain the preset redundant defect analysis coefficient and the preset insufficient defect analysis coefficient.

[0096] Calculate the sum of the preset redundant defect analysis coefficient and the error coefficient to obtain the redundant defect analysis coefficient, and calculate the difference between the preset insufficient defect analysis coefficient and the error coefficient to obtain the insufficient defect analysis coefficient.

[0097] Further, the defect prediction module 13 includes the following execution steps:

[0098] Using the redundant defect analysis coefficient, combined with the number of N thickness non-uniformity prediction branches in the pre-trained thickness non-uniformity predictor, calculate to obtain U, where N is a positive integer and U is a positive integer less than or equal to N.

[0099] Randomly select U thickness non-uniformity prediction branches, input the predicted dispensing volume, predict and output U thickness non-uniformity prediction parameters, and calculate the mean value to obtain the first defect parameter.

[0100] Using the insufficient defect analysis coefficient, combined with the number of N liquid crystal damage prediction branches in the pre-trained liquid crystal damage predictor, calculate to obtain U.

[0101] Randomly select U liquid crystal damage prediction branches, input the predicted dispensing volume, predict and output U liquid crystal damage prediction parameters, and calculate the mean value to obtain the second defect parameter.

[0102] Further, the defect prediction module 13 further includes the following execution steps:

[0103] According to the LCD sealing data within the historical time, collect the sample predicted dispensing volume set, and collect the amplitude of the thickness non-uniformity of the LCD under different sample predicted dispensing volumes, and label to obtain the sample thickness non-uniformity parameter set.

[0104] Randomly select the first thickness non-uniformity training data from the sample predicted dispensing volume set and the sample thickness non-uniformity parameter set with replacement.

[0105] Continue to randomly select N pieces of training data with uneven thicknesses with replacement;

[0106] Using deep learning, construct N prediction branches for uneven thicknesses, and separately use the N pieces of training data with uneven thicknesses for supervised training and testing until the accuracy rate is qualified to complete the pre-training.

[0107] Further, the result generation module 14 includes the following execution steps:

[0108] Generate the defect parameters of the LCD according to the first defect parameter and the second defect parameter;

[0109] Use the defect parameters as the defect detection result and display a reminder.

[0110] Embodiment III, please refer to Figure 3 , Figure 3 This is a schematic diagram of the embodiment of the electronic device provided by the embodiment of the present invention. As Figure 3 shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a computer program 211 stored on the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, it implements the defect detection method for LCD display production in Embodiment I.

[0111] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0112] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0113] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing the process Figure 1one or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks

[0114] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions in the process Figure 1 one or more processes and / or blocks Figure 1 the functions specified in one or more blocks

[0115] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions in the process Figure 1 one or more processes and / or blocks Figure 1 the functions specified in one or more blocks

[0116] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept

[0117] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations

Claims

1. A method for detecting defects in the production of an LCD display screen, characterized in that, The method includes: When sealing the LCD, collect the image of the dispensing nozzle of the dispensing equipment for sealing, predict the dispensing amount, and obtain the predicted dispensing amount; According to the predicted dispensing amount and the preset dispensing amount, perform glue amount redundancy defect analysis decision-making and glue amount shortage defect analysis decision-making, and obtain a redundancy defect analysis coefficient and a shortage defect analysis coefficient, including: Obtain the preset dispensing amount for LCD sealing, and according to the dispensing data within the historical time, collect the maximum dispensing amount error deviating from the preset dispensing amount; Calculate the difference between the predicted dispensing amount and the preset dispensing amount, and calculate the ratio with the maximum dispensing amount error to obtain an error coefficient; Obtain a preset redundancy defect analysis coefficient and a preset shortage defect analysis coefficient; Calculate the sum of the preset redundancy defect analysis coefficient and the error coefficient to obtain a redundancy defect analysis coefficient, and calculate the difference between the preset shortage defect analysis coefficient and the error coefficient to obtain a shortage defect analysis coefficient; According to the redundancy defect analysis coefficient, based on the predicted dispensing amount, perform uneven thickness prediction of the LCD to obtain a first defect parameter, and according to the shortage defect analysis coefficient, based on the predicted dispensing amount, perform cured liquid crystal damage prediction to obtain a second defect parameter, including: Use the redundancy defect analysis coefficient, combined with the number of N uneven thickness prediction branches in the pre-trained uneven thickness predictor, to calculate and obtain U, where N is a positive integer and U is a positive integer less than or equal to N; Randomly select U uneven thickness prediction branches, input the predicted dispensing amount, predict and output U uneven thickness prediction parameters, and calculate the mean value to obtain a first defect parameter; Use the shortage defect analysis coefficient, combined with the number of N liquid crystal damage prediction branches in the pre-trained liquid crystal damage predictor, to calculate and obtain U; Randomly select U liquid crystal damage prediction branches, input the predicted dispensing amount, predict and output U liquid crystal damage prediction parameters, and calculate the mean value to obtain a second defect parameter; Generate a defect parameter of the LCD according to the first defect parameter and the second defect parameter as the defect detection result.

2. The method for detecting defects in the production of an LCD display screen according to claim 1, wherein When sealing the LCD, collect the image of the dispensing nozzle of the dispensing equipment for sealing, predict the dispensing amount, and obtain the predicted dispensing amount, including: When sealing the LCD, collect the image of the dispensing nozzle of the dispensing equipment for sealing; Input the dispensing nozzle image into the pre-trained dispensing amount predictor, and output to obtain the predicted dispensing amount.

3. The method for detecting defects in the production of an LCD display according to claim 2, wherein The training steps of the dispensing amount predictor include: According to the LCD display production data within the historical time, collect a set of sample dispensing nozzle images, and collect the dispensing amount under each sample dispensing nozzle image, and label it as the sample dispensing amount to obtain a set of sample dispensing amounts; Based on the convolutional neural network, construct a dispensing amount predictor; Use the set of sample dispensing nozzle images and the set of sample dispensing amounts to perform supervised training and testing on the dispensing amount predictor, and after the accuracy is qualified, complete the pre-training.

4. The method for detecting defects in the production of an LCD display screen according to claim 1, characterized in that, The pre-training steps of the uneven thickness predictor include: According to the LCD sealing data within the historical time, collect a set of sample predicted dispensing amounts, and collect the amplitude of uneven thickness of the LCD under different sample predicted dispensing amounts, and label to obtain a set of sample uneven thickness parameters; Randomly select the first thickness non-uniform training data from the sample predicted dispensing volume set and the sample thickness non-uniformity parameter set with replacement; Continue to randomly select N pieces of thickness non-uniform training data with replacement; Use deep learning to construct N thickness non-uniform prediction branches, and use the N pieces of thickness non-uniform training data for supervised training and testing respectively until the accuracy rate is qualified to complete the pre-training.

5. The method for detecting defects in the production of an LCD display screen according to claim 1, characterized in that, Generate the defect parameters of the LCD based on the first defect parameter and the second defect parameter as the defect detection result, including: Generate the defect parameters of the LCD based on the first defect parameter and the second defect parameter; Use the defect parameters as the defect detection result for display and reminder.

6. A defect detection system for LCD display production, characterized in that, For implementing the defect detection method for LCD display production according to any one of claims 1-5, the system includes: A dispensing volume prediction module, which is used to collect the image of the dispensing port of the sealing dispensing device during LCD sealing, predict the dispensing volume, and obtain the predicted dispensing volume; A glue volume analysis module, which is used to make glue volume redundancy defect analysis decisions and glue volume shortage defect analysis decisions based on the predicted dispensing volume and the preset dispensing volume, and obtain the redundancy defect analysis coefficient and the shortage defect analysis coefficient; A defect prediction module, which is used to predict the thickness non-uniformity of the LCD based on the redundancy defect analysis coefficient and the predicted dispensing volume to obtain the first defect parameter, and predict the cured liquid crystal damage based on the shortage defect analysis coefficient and the predicted dispensing volume to obtain the second defect parameter; A result generation module, which is used to generate the defect parameters of the LCD based on the first defect parameter and the second defect parameter as the defect detection result.

7. An electronic device, characterized in that, Including: A memory for storing computer software programs; A processor for reading and executing the computer software program, thereby implementing the defect detection method for LCD display production according to any one of claims 1-5.

Images