Method and device for manufacturing liquid crystal display module

Abstract

The invention is suitable for the technical field of liquid crystal display module manufacturing, and provides a manufacturing method and device of a liquid crystal display module, and the method is applied to a liquid crystal display module manufacturing control system. The system comprises an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center and an intelligent mobile terminal. The information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory and the alarm are respectively connected with the processing center; the intelligent mobile terminal is in wireless network connection with the wireless communication module in the range of a wireless network or the Internet. The invention further provides a liquid crystal display module manufacturing control device. Automatic production and automatic detection of the liquid crystal display module can be realized.

Description

Technical Field

[0001] The present invention relates to the field of liquid crystal display module manufacturing control technology, and in particular to a method and device for manufacturing a liquid crystal display module in the field of artificial intelligence. Background Art

[0002] With the rapid development of emerging markets such as the Internet of Things, smart homes, and in-vehicle displays, LCD display modules will be widely used in consumer electronics, smart phones, tablets, automobiles, industrial and medical equipment, and other fields.

[0003] Existing LCD display module companies often encounter abnormal phenomena such as "bright spots, dark spots and colored spots, screen distortion, light leakage, contamination and foreign matter, and uneven color" during production. Due to human operational errors or processing errors, LCD display module production often requires rework, which keeps production costs high. Therefore, it is necessary to formulate strict production processes for fully automated production to ensure the production quality of each link in the production process, and to take early prevention measures for any quality abnormalities to reduce the number of reworks to ensure module quality and thus reduce production costs. Summary of the Invention

[0004] In order to address the deficiencies in the prior art, the present invention aims to provide a method and device for manufacturing a liquid crystal display module. By setting various functional modules such as an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, and a production application module, production process parameters are preset to perform automated production and automated testing, thereby reducing human intervention and avoiding abnormal phenomena such as "bright spots, dark spots and colored spots, screen distortion, light leakage, contamination and foreign matter, and uneven color" in the liquid crystal display module, thereby improving production efficiency and reducing production costs.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for manufacturing a liquid crystal display module, applied to a liquid crystal display module manufacturing control system, the system comprising an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, memory, and alarm are respectively connected to the processing center; the intelligent mobile terminal comprises a smart phone, a tablet computer, and an intelligent remote control, each of which is wirelessly connected to the wireless communication module within a wireless network or the Internet;

[0007] The wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically networking with the smart mobile terminal and the control device within the effective network range;

[0008] The alarm device compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to continue training; and compares the module quality information with the production quality standard of the liquid crystal module stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to adjust the parameters and rework; and compares the module quality information with the production quality standard of the liquid crystal module stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to rework;

[0009] The memory is responsible for storing information of the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, and alarm, as well as the model evaluation sub-standard and the liquid crystal module production quality standard;

[0010] The processing center is responsible for information transmission among various functional modules, alarms, and memories, and is the hub of the system. The processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters and rework; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is notified that it can be shipped; if it does not meet the standard, it is transmitted to the alarm and notified to rework or repair;

[0011] The information acquisition module includes a data acquisition unit, a data cleaning unit, a data enhancement unit, a data integration unit, a data conversion unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, and is responsible for acquiring and preprocessing normal and abnormal historical image data of the operation and production quality of the liquid crystal display module, and passing it to the model construction module;

[0012] The model construction module includes a network hierarchy unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit. It is responsible for determining the model architecture, designing the network hierarchy structure, adding auxiliary layers, defining model parameters, and constructing the model based on the extracted feature information, and passing it to the model training module.

[0013] The model training module includes an input padding unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a back-propagation unit, and is responsible for training the model based on the collected data and adjusting the model parameters to optimize the model performance to predetermine the LCD module control parameters and pass them to the model evaluation module;

[0014] The model evaluation module includes a classification labeling unit, a learning and training unit, and a model evaluation unit, which is responsible for model verification and evaluation based on the trained model, and adjusting and optimizing the model based on the verification results, and passing them to the parameter determination module;

[0015] The parameter determination module includes a response time unit, an output brightness unit, a color saturation unit, a trial debugging unit, and an abnormality recognition unit. It is responsible for conducting production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module and pass them to the production application module;

[0016] The production application module includes a substrate array unit, a liquid crystal panel unit, a module assembly unit, and a quality inspection unit, which are responsible for producing and inspecting the liquid crystal display modules according to set production process parameters.

[0017] The present invention provides a method for manufacturing a liquid crystal display module, comprising the following steps:

[0018] S10. Before production, the information acquisition module acquires normal and abnormal historical image data of the operation and production quality of the LCD module and pre-processes it for subsequent model construction, and transmits it to the model construction module;

[0019] S20, the model construction module determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters based on the feature information to construct the model for subsequent model training and verification, and passes it to the model training module;

[0020] S30, the model training module trains the model based on the collected data and adjusts the model parameters to optimize the model performance to predetermine the LCD module control parameters, ensure the LCD module operation stability, and pass it to the model evaluation module;

[0021] S40, the model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the performance and accuracy of the model, and passes it to the parameter determination module;

[0022] S50, the parameter determination module performs production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module to ensure subsequent production quality, and transmits the parameters to the production application module;

[0023] S60, the production application module produces and performs various tests on the LCD display module according to the set production process parameters and the LCD module production and testing equipment according to the program instructions to ensure that the LCD module meets the quality requirements.

[0024] Further, the step S10 includes the following steps:

[0025] S11. The data acquisition unit obtains historical data on various electrical, optical, and environmental performance and production process parameters of similar liquid crystal display modules by connecting to the industry database, and transmits the data to the data cleaning unit;

[0026] S12. The data cleaning unit cleans the collected historical data to remove abnormal values, duplicate values or missing values in the data to improve the quality and accuracy of the data, and transmits the data to the data enhancement unit;

[0027] S13, the data enhancement unit increases the quantity and diversity of the LCD module training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation to improve the generalization ability of the model, and transmits it to the data integration unit;

[0028] S14. The data integration unit obtains standardized integrated data according to the data standardization processing formula "z = (x-μ) / σ, z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data" to improve the stability of the model and transmits it to the data conversion unit;

[0029] S15. The data conversion unit obtains normalized data according to the normalization calculation formula "x' = (x-min(x)) / (max(x)-min(x)), x' is the normalized data, x is the original data, min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance and pass it to the filtering and denoising unit;

[0030] S16, filtering and denoising unit calculates the formula " G(x,y) is the two-dimensional Gaussian function pixel, (x,y) is the pixel coordinate, and σ is the standard deviation. The denoised image is obtained for grayscale image conversion and passed to the grayscale conversion unit;

[0031] S17. The grayscale conversion unit obtains the grayscale module image according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), where f(i,j) is the grayscale image and R(i,j), G(i,j), and B(i,j) are the original images of three colors respectively" for subsequent feature extraction and passes it to the feature extraction unit;

[0032] S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts key features of brightness, contrast, color uniformity, and defects to improve the training speed and performance of the model.

[0033] Further, the step S20 includes the following steps:

[0034] S21. The network layer unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network layer structure according to the specific application scenarios and requirements to facilitate subsequent defect detection and quality identification, and the network parameter unit;

[0035] S22, the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and passes it to the hierarchical optimization unit;

[0036] S23, the hierarchical optimization unit adjusts the size and normalization of the input data by adding a zero-filling layer and a normalization layer before and after the convolution layer to improve the model training speed and stability, and passes it to the data partitioning unit;

[0037] S24. The data partitioning unit divides the data set with key feature vectors into training set, validation set and test set according to the extracted data set and establishes a convolutional neural network structure for subsequent model training.

[0038] Further, the step S30 includes the following steps:

[0039] S31, input filling unit according to data filling size calculation formula

[0040] “P H =[(Ho-1)*S H +K H -Hi] / 2,P W =[(Wo-1)*S W +KW-Wi] / 2, PH, PW are the height / width padding sizes, Hi, Wi are the height / width of the input feature map, KH, K Ware the height / width of the convolution kernel, SH and SW are the values of the step size in the height / width direction, Ho and Wo are the height and width of the output feature map respectively. Get the padding data and input it, and pass it to the convolution input unit;

[0041] S32, the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", and passes it to the pooling conversion unit;

[0042] S33, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map respectively, max is to find the maximum value of all pixel values in the input window, X is the input feature map, PS is the window size of the pooling operation, and the maximum pixel value after pooling is obtained to retain important feature information and pass it to the fully connected layer unit;

[0043] S34, the fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(wn*xn)+b), y is the output result, f is the activation function, wn is the weight of the nth input feature, xn is the nth input feature, n is the dimension of the input feature, and b is the bias" and enters the output layer for subsequent output calculation and is passed to the normalized output unit;

[0044] S35, the normalized output unit is calculated according to the Batch Norm layer formula "h=φ(B N (Wx+b)), h is the output of the fully connected layer, φ is the activation function, B N is the batch normalization operator, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter. The output of Batch Norm is obtained and passed to the output conversion unit;

[0045] S36. The output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F+2C) / S+1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of zero added around the image, and S is the step size" for subsequent model analysis and training, and passes it to the back propagation unit;

[0046] S37. The back-propagation unit obtains the loss function value and back-propagates it according to the loss function calculation formula "L = max(0, m + y * (f (x) - b)), L is the loss function value, m is the hyperparameter, y is the sample label (0 or 1), f (x) is the predicted value of the model, and b is the classification boundary" to optimize the performance of the network model.

[0047] Further, the step S40 includes the following steps:

[0048] S41, the classification and marking unit classifies the quality abnormality categories of the liquid crystal module into corresponding data sample categories and marks them for subsequent machine learning of the model, and transmits them to the learning and training unit;

[0049] S42, the learning and training unit determines a training model based on the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition, and transmits the data to the model evaluation unit;

[0050] S43. The model evaluation unit obtains a comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2*(Ac*Re) / (Ac+Re), where F is the training model evaluation score, Ac is the precision, and Re is the recall rate", and transmits it to the processing center;

[0051] S44. The processing center compares the actual evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training.

[0052] Further, the step S50 includes the following steps:

[0053] S51, the response time unit is calculated according to the liquid crystal module response time formula "Tr=γ1*d 2 / [ε*(U 2 -U t 2 )],T d =γ1*d 2 / (ε*U t 2 ),Tr, T d is the rise and fall response time of the liquid crystal module (s), γ1 is the viscosity coefficient of the liquid crystal material (Pa·s), d is the liquid crystal cell gap (m), ε is the dielectric constant of the liquid crystal material (F / m), U is the liquid crystal cell driving voltage (V), U t The threshold voltage (V) of the LCD screen is used to obtain the LCD module response time for subsequent module testing and is passed to the output brightness unit;

[0054] S52, the output brightness unit calculates the output brightness of the liquid crystal module according to the formula "L=(N*Φ*a*b*c*η) / (S*π), L is the output brightness of the liquid crystal module (cd / m 2 ), N is the number of LED lights in the backlight module, Φ is the luminous flux emitted by the LED light (lm), a is the reflectivity of the reflector (%), b is the transmittance of the diffuser (%), c is the gain provided by the brightness enhancement film and the polarization film (%), η is the working efficiency of the light guide module in the module (%), S is the light receiving area of the light guide plate (m 2 )” to obtain the output brightness of the LCD module for subsequent module testing and pass it to the color saturation unit;

[0055] S53. The color saturation unit obtains the color saturation of the LCD module according to the LCD saturation calculation formula: "Sr = (Ic'-Iw') / (Ic-Iw), where Sr is the saturation of the LCD screen, Ic' is the light energy (J) emitted by the measured light source under the same amount of white light, Iw' is the energy (J) emitted by the same amount of white light source, Ic is the light energy (J) emitted by the measured light source under the same amount of light, and Iw is the energy (J) emitted by the same amount of light source." This is used for subsequent module testing and is transmitted to the trial debugging unit.

[0056] S54, the trial debugging unit conducts trial production and testing of the liquid crystal display module using production testing equipment according to predetermined production process parameters to obtain quality information to ensure the accuracy of the liquid crystal module parameters and transmits the information to the processing center;

[0057] S55. The processing center compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is set as the module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters and rework.

[0058] S56. The abnormality recognition unit matches the real-time acquired LCD module production inspection image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category for subsequent production improvement and parameter adjustment.

[0059] Further, the step S60 includes the following steps:

[0060] S61, the substrate array unit performs film formation, PR coating, exposure, development, etching, and PR stripping on the glass substrate to form a TFT array with 4 to 5 layers of thin film patterns, and transmits the result to the liquid crystal panel unit;

[0061] S62. The liquid crystal panel unit adheres the TFT substrate to the CF substrate and injects the liquid crystal material according to the control command and predetermined parameters through alignment film printing, sealant coating, spacer spraying, liquid crystal injection, sealing assembly, and polarizer attachment to ensure the correct arrangement of liquid crystal molecules and the stability of the display effect, and then transmits the result to the module assembly unit.

[0062] S63, the module assembly unit performs the COG process, flexible circuit board / printed circuit board lamination, and backlight module assembly according to the control command and predetermined process parameters to display the image, and transmits the result to the quality inspection unit;

[0063] S64. The quality inspection unit uses high-definition cameras and various performance testing equipment to test the appearance and electrical, optical, functional, and reliability performance of the LCD display module to ensure that the module quality and performance meet the requirements and pass it to the processing center;

[0064] S65. The processing center compares the module quality information with the LCD module production quality standards stored in the memory. If the standards are met, the center notifies the user that the module can be shipped. If the standards are not met, the center notifies the user that the module is to be reworked or repaired.

[0065] A liquid crystal display module manufacturing control system provided by the present invention also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the functional modules execute the computer program, the steps of the liquid crystal display module manufacturing method described in any one of the above are implemented; the computer-readable storage medium stores a computer program, and when the functional modules execute the computer program, the steps of the liquid crystal display module manufacturing method described in any one of the above are implemented.

[0066] The present invention also provides a liquid crystal display module manufacturing control device, which is implemented using the above-mentioned method for manufacturing a liquid crystal display module.

[0067] The beneficial effects of the present invention compared with the prior art are as follows:

[0068] By setting up various functional modules such as information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, and production application module, production process parameters can be preset to carry out automated precise production and precise detection, reduce human interference, and avoid abnormal phenomena such as "bright spots, dark spots and colored spots, screen distortion, light leakage, contamination and foreign matter, and uneven color" in LCD display modules, thereby improving production efficiency and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or exemplary technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0070] Figure 1 Schematic diagram of the system module of the present invention;

[0071] Figure 2 This is a schematic diagram of the information acquisition module of the present invention;

[0072] Figure 3 This is a schematic diagram of the model building module of the present invention;

[0073] Figure 4 This is a schematic diagram of the model training module of the present invention;

[0074] Figure 5 Schematic diagram of the model evaluation module of the present invention;

[0075] Figure 6 Schematic diagram of a parameter determination module of the present invention;

[0076] Figure 7 This is a schematic diagram of the production application module of the present invention;

[0077] Figure 8 This is a schematic diagram of the method flow control program of the present invention;

[0078] Figure 9 This is a schematic diagram of step S10 in the method of the present invention;

[0079] Figure 10 Schematic diagram of step S20 in the method of the present invention;

[0080] Figure 11 Schematic diagram of step S30 in the method of the present invention;

[0081] Figure 12 Schematic diagram of step S40 in the method of the present invention;

[0082] Figure 13 Schematic diagram of step S50 in the method of the present invention;

[0083] Figure 14 Schematic diagram of step S60 in the method of the present invention. DETAILED DESCRIPTION

[0084] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0085] The following describes the specific implementation of the present invention in detail with reference to specific embodiments:

[0086] To make the technical problems, technical solutions, and beneficial effects to be solved by this application more clearly understood, the application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to explain this application and are not intended to limit this application. It should be noted that when a module is referred to as being "disposed on" another module, it can be directly on the other module or indirectly on the other module. When a module is referred to as being "connected to" another module, it can be directly connected to the other module or indirectly connected to the other module.

[0087] In this application, "plurality" means two or more, unless otherwise specified. "Several" means one or more, unless otherwise specified. In this application, "liquid crystal display module" is referred to as "liquid crystal module," "display module," or "module," all of which refer to the same module.

[0088] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "connected" and "connection" should be understood broadly. For example, it can mean a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection between two elements or the interaction between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood based on the specific circumstances. The terms "include," "comprising," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0089] See also Figure 1As shown, the present invention provides a method for manufacturing a liquid crystal display module, which is applied to a liquid crystal display module manufacturing control system, wherein the system includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal includes a smart phone, a tablet computer, and a smart remote control, which are respectively connected to the wireless communication module within the range of a wireless network or the Internet.

[0090] The wireless communication module is equipped with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically connects to the smart mobile terminal and production detection and control equipment within the effective network range. The wireless signals include MQTT, CoAP, HTTP, REST API, Zigbee, LoRaWAN, NB-IoT, Bluetooth and other IoT signals.

[0091] The alarm compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to continue training; and compares the module quality information with the liquid crystal module production quality standard stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to adjust the parameters and rework; and compares the module quality information with the liquid crystal module production quality standard stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to rework.

[0092] The memory is responsible for storing information from the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, and alarm, as well as the model evaluation sub-standards and the liquid crystal module production quality standards.

[0093] The processing center is responsible for the information transmission of each functional module, alarm, and memory. It is the hub center of the system and compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is passed to the alarm and notified to continue training; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is set as the formal production process parameter; if it does not meet the standard, it is passed to the alarm and notified to adjust the parameters and rework; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is notified that it can be shipped; if it does not meet the standard, it is passed to the alarm and notified to rework or repair.

[0094] See also Figure 2As shown, the information acquisition module includes a data acquisition unit, a data cleaning unit, a data enhancement unit, a data integration unit, a data conversion unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit. It is responsible for acquiring normal and abnormal historical image data of the operation and production quality of the liquid crystal display module, performing preprocessing, and passing it to the model construction module.

[0095] Furthermore, the data acquisition unit obtains historical data of various electrical, optical, and environmental adaptability performance and production process parameters of similar liquid crystal display modules by networking with the industry database, and passes it to the data cleaning unit; the data cleaning unit cleans the collected historical data to remove abnormal values, duplicate values or missing values in the data, and passes it to the data enhancement unit; the data enhancement unit increases the quantity and diversity of liquid crystal display module training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation, and passes it to the data integration unit; the data integration unit obtains standardized integrated data according to the data normalization processing formula "z = (x-μ) / σ", and passes it to the data conversion unit; the data conversion unit obtains normalized data according to the normalization calculation formula "x' = (x-min(x)) / (max(x)-min(x))", and passes it to the filtering and denoising unit; the filtering and denoising unit calculates the data according to the Gaussian filtering method formula The denoised image is obtained and passed to the grayscale conversion unit; the grayscale conversion unit obtains the grayscale module image according to the grayscale calculation formula "f(i,j)=max(R(i,j),G(i,j),B(I,j))" and passes it to the feature extraction unit; the feature extraction unit converts the labeled data into a feature vector useful for model training and extracts key features of brightness, contrast, color uniformity, and defects to improve the training speed and performance of the model.

[0096] See also Figure 3 As shown, the model construction module includes a network hierarchy unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit. It is responsible for determining the model architecture, designing the network hierarchy structure, adding auxiliary layers, defining model parameters, and constructing the model based on the extracted feature information, and passing it to the model training module.

[0097] Furthermore, the network hierarchy unit customizes the design and optimization of the network hierarchy structure based on the selected convolutional neural network as the model architecture and according to the specific application scenarios and requirements, and establishes a network parameter unit; the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure, and passes them to the hierarchy optimization unit; the hierarchy optimization unit adjusts the size and normalization of the input data by adding a zero padding layer and a normalization layer before and after the convolution layer, respectively, and passes it to the data partitioning unit; the data partitioning unit divides the data set with key feature vectors after extraction into a training set, a validation set and a test set and establishes a convolutional neural network structure for subsequent model training.

[0098] See also Figure 4 As shown, the model training module includes an input padding unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a back-propagation unit. It is responsible for training the model based on the collected data and adjusting the model parameters to optimize the model performance to predetermine the LCD display module control parameters and pass them to the model evaluation module.

[0099] Furthermore, the input filling unit calculates the data filling size according to the formula "P H =[(Ho-1)*S H +K H -H i ] / 2, P W =[(Wo-1)*S W +K W -Wi] / 2" to obtain the padding data and input it, and pass it to the convolution input unit; the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t)=∫x(m)y(tm)dm", and passes it to the pooling conversion unit; the pooling conversion unit obtains the convolution input value and activates the function input according to the maximum pooling calculation formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ])” obtains the maximum pixel value after pooling and enters the fully connected layer, and passes it to the fully connected layer unit; the fully connected layer unit obtains the connection layer output data according to the fully connected layer calculation formula "y=f(∑(wn*xn)+b)" and enters the output layer, and passes it to the normalized output unit; the normalized output unit obtains the connection layer output data according to the Batch Norm layer calculation formula "h=φ(B N(Wx+b))” to obtain the output of Batch Norm and pass it to the output conversion unit; the output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula “N=(P-F+2C) / S+1” and passes it to the back propagation unit; the back propagation unit calculates the loss function according to the formula “L=max(0,m+y*

[0100] (f(x)-b))” obtains the loss function value and backpropagates to optimize the performance of the network model.

[0101] See also Figure 5 As shown, the model evaluation module includes a classification labeling unit, a learning and training unit, and a model evaluation unit, which is responsible for model verification and evaluation based on the trained model, and adjusting and optimizing the model based on the verification results, and passing them to the parameter determination module.

[0102] Furthermore, the classification and marking unit divides the data sample into corresponding categories according to the quality abnormality category of the liquid crystal module and marks them, and transmits them to the learning and training unit; the learning and training unit determines the training model according to the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions, and transmits it to the model evaluation unit; the model evaluation unit obtains the F comprehensive evaluation score according to the model evaluation score calculation formula "F=2*(Ac*Re) / (Ac+Re)", and transmits it to the processing center.

[0103] See also Figure 6 As shown, the parameter determination module includes a response time unit, an output brightness unit, a color saturation unit, a trial debugging unit, and an anomaly recognition unit. It is responsible for conducting production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module and pass them to the production application module.

[0104] Furthermore, the response time unit is calculated according to the liquid crystal module response time formula "Tr = γ1*d 2 / [ε*(U 2 -U t 2)]” to obtain the response time of the liquid crystal module and pass it to the output brightness unit; the output brightness unit obtains the output brightness of the liquid crystal module according to the liquid crystal module output brightness calculation formula "L=(N*Φ*a*b*c*η) / (S*π)" and passes it to the color saturation unit; the color saturation unit obtains the color saturation of the liquid crystal module according to the liquid crystal display saturation calculation formula "Sr=(Ic′-Iw′) / (Ic-Iw)" and passes it to the trial debugging unit; the trial debugging unit conducts trial production and detection of the liquid crystal display module through production detection equipment according to predetermined production process parameters to obtain quality information to ensure the accuracy of the liquid crystal module parameters and pass it to the processing center; the abnormality recognition unit matches the real-time liquid crystal module production detection image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category for subsequent production improvement and parameter adjustment.

[0105] See also Figure 7 As shown, the production application module includes a substrate array unit, a liquid crystal panel unit, a module assembly unit, and a quality inspection unit, which are responsible for producing and inspecting the liquid crystal display modules according to the set production process parameters.

[0106] Furthermore, the substrate array unit forms a TFT array with 4 to 5 thin film patterns on a glass substrate through film formation, PR coating, exposure, development, etching, and PR stripping according to control commands and predetermined process parameters, and transmits the results to the liquid crystal panel unit; the liquid crystal panel unit adheres the TFT substrate to the CF substrate and injects liquid crystal material through alignment film printing, sealant coating, spacer spraying, liquid crystal injection, sealing assembly, and polarizer attachment according to control commands and predetermined parameters, and transmits the results to the module assembly unit; the module assembly unit displays images and undergoes aging testing through COG process, flexible circuit board / printed circuit board lamination, and backlight module assembly according to control commands and predetermined process parameters, and transmits the results to the quality inspection unit; the quality inspection unit uses high-definition cameras and various performance inspection equipment to inspect the appearance and electrical, optical, functional, and reliability performance of the liquid crystal display module, and transmits the results to the processing center.

[0107] System operation working principle:

[0108] Before production, the information acquisition module obtains normal and abnormal historical image data of the operation and production quality of the LCD display module and performs preprocessing to facilitate subsequent model construction, which is then passed to the model construction module. The model construction module then determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters based on the extracted feature information to construct the model for subsequent model training and verification, and passes the model to the model training module. The model training module trains the model based on the collected data and adjusts the model parameters to optimize the model performance to predetermine the LCD display module control parameters to ensure the operational stability of the LCD display module, and passes the model to the model evaluation module. The model evaluation module then performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the model performance and accuracy, and passes the model to the parameter determination module. The parameter determination module conducts production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the LCD module to ensure subsequent production quality, and passes the parameters to the production application module. The production application module then produces and performs various tests on the LCD display module according to the program instructions on the LCD module production and testing equipment based on the set production process parameters to ensure that the LCD module meets quality requirements.

[0109] When operators or managers are outdoors or in other places, they can use smart mobile terminals to automatically connect to the wireless network or the Internet through the wireless communication module, realizing the integration of smart mobile terminals, the Internet and the Internet of Things technology. Through the APP software on the smart mobile terminal or the remote control software on the computer, they can control the LCD module production under normal conditions at close range or remotely to meet the user's quality requirements. Managers can remotely control and monitor all LCD modules, view daily operating status, data changes, equipment activity logs, etc., and realize remote connection and control of LCD module production by pre-fabricated deployment codes or adding deployment codes. Remote LCD module production inspection can be viewed in real time through smart mobile terminals or computers, thereby improving production efficiency and reducing production costs.

[0110] See also Figure 8 As shown, the present invention provides a method for manufacturing a liquid crystal display module, comprising the following steps:

[0111] S10. Before production, the information acquisition module acquires normal and abnormal historical image data of the operation and production quality of the LCD module and pre-processes it for subsequent model construction, and transmits it to the model construction module;

[0112] See also Figure 9 As shown, the step S10 includes the following steps:

[0113] S11. The data acquisition unit obtains historical data on various electrical, optical, and environmental performance and production process parameters of similar liquid crystal display modules by connecting to the industry database, and transmits the data to the data cleaning unit;

[0114] It is further explained that the material processing, process processing, and production process parameters of finished modules of various LCD modules, as well as the quality information of images or videos of the corresponding modules and the data of the usage effects of users in different industries are collected from domestic and foreign LCD module databases through data collectors and their software, and classified and aggregated; the LCD module data includes but is not limited to historical data of different users' evaluations of the usage effects of different such LCD modules, and also includes normal and abnormal quality information of similar LCD modules obtained from the Internet, social media, professional testing institutions, processing trade platforms, or third-party sharing platforms such as public data sets through web crawlers, sensor collection, manual annotation, data set purchase, crowdsourcing, etc. The information and historical data of different users' usage effects are collected to obtain high-quality, diverse and rich historical data of similar LCD modules, specifically including historical data of quality information such as raw materials, performance parameters, process parameters, test data and images of LCD modules; the raw material data include shape drawings and processing drawings and data of electronic components of various LCD modules; the performance parameters include optical performance, transmittance, electrical performance, reliability performance and other performance data; the process parameters include manufacturing process flow, production equipment control parameters, test equipment control parameters, as well as operating temperature, operating voltage and other data; the test data include resolution, brightness, contrast, response time and viewing angle and other data.

[0115] S12. The data cleaning unit cleans the collected historical data to remove abnormal values, duplicate values or missing values in the data to improve the quality and accuracy of the data, and transmits the data to the data enhancement unit;

[0116] It is further explained that due to sensor failure, recording errors or system abnormalities in the operation of the LCD display module, abnormal values appear, which affect the accuracy of subsequent analysis; missing value processing is performed on data with missing parts; each feature in the data set is detected by writing code to determine the missing values, and the missing value pattern is identified. According to the number and impact of the missing values, the code is written to select or delete samples or variables with missing values. For time series data, forward filling or backward filling is used to fill the missing values; the processing effect is verified by comparing indicators such as data quality before and after processing, model accuracy and reliability. If the processing effect is not good, the processing method is reselected or the data is re-cleaned until the best effect is achieved, so as to remove duplicate, erroneous, and invalid data to effectively handle missing values for subsequent model construction and analysis.

[0117] S13, the data enhancement unit increases the quantity and diversity of the LCD module training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation to improve the generalization ability of the model, and transmits it to the data integration unit;

[0118] It is further explained that after the cleaned LCD display module data is rotated by a certain angle through the LCD display module data rotation, multiple pixels will be generated and correspond to the same pixel after rotation, resulting in pixel loss in the rotated LCD display module data. Therefore, reverse thinking is used to construct a mapping to map the pixel coordinates after rotation to the pixel coordinates of the original LCD display module data, so that each pixel after rotation can be guaranteed to have a pixel value; the neighborhood interpolation algorithm is used to copy each original pixel in the rotated LCD display module data intactly and map it to the corresponding four pixels after expansion, retaining all information of the original LCD display module data; the LCD display module data with abnormal orientation after scaling is flipped 180 degrees around the center axis or symmetry axis of the original image to ensure the orientation consistency of the LCD display module data; the flipped LCD display module data is cropped to ensure image integrity and clarity.

[0119] S14. The data integration unit obtains standardized integrated data according to the data standardization processing formula "z = (x - μ) / σ, z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data" to improve the stability of the model and passes it to the data conversion unit;

[0120] It is further explained that the collected raw data is calibrated, including time synchronization, unit conversion, range adjustment, etc., such as ensuring that all timestamps are in a unified format and synchronized with the system clock; converting data collected by different sensors, detection equipment, etc. to the same unit to ensure data accuracy; using the above-mentioned data standardization processing formula "z = (x-μ) / σ" through the written code to convert data from different sources such as dates, numbers, texts, etc. into a standard normal distribution with a mean of 0 and a standard deviation of 1, subtracting the mean and dividing by the standard deviation to make it a unified standard format to ensure data consistency and comparability for subsequent processing; encoding unstructured data and converting it into structured data, or converting text data into numerical representation for model processing and analysis, thereby processing the raw data into a form that meets specific standards for subsequent model training and analysis.

[0121] S15. The data conversion unit obtains normalized data according to the normalization calculation formula "x' = (x-min(x)) / (max(x)-min(x)), x' is the normalized data, x is the original data, min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance and pass it to the filtering and denoising unit;

[0122] It is further explained that the above normalization calculation formula "x'=(x-min(x)) / (max(x)-min(x))" is used by the written code to proportionally map the cleaned data to the specified range of [0,1], convert the data into a unified format or range of data normalization, convert continuous features into discrete features of data discretization, etc. to convert the data to eliminate the total amount difference between different samples or features and the dimensional influence between the data, make the distribution of the data consistent, and confirm whether the data has been normalized to the specified range or distribution as expected, and verify the normalization effect through statistical descriptions such as maximum and minimum values; the data includes multiple types such as text, pictures, audio, video, etc., to eliminate the dimensional differences between different data, thereby improving the accuracy and efficiency of data analysis, so as to better adapt to subsequent analysis and processing.

[0123] S16, filtering and denoising unit calculates the formula " G(x,y) is the two-dimensional Gaussian function pixel, (x,y) is the pixel coordinate, and σ is the standard deviation. The denoised image is obtained for grayscale image conversion and passed to the grayscale conversion unit;

[0124] It is further explained that the Gaussian filter output pixel value obtained according to the Gaussian filter calculation formula is the weighted average of the input pixel values in its neighborhood, and the weight is given by the Gaussian function, where the standard deviation σ determines the width of the Gaussian function, and the Gaussian function is discretized, that is, the weight is calculated within a certain window size, and then these weights are applied to the corresponding neighborhood pixel values of the input image to obtain the output pixel value, and the pixels are arranged from small to large according to the grayscale value and the median is taken as the new grayscale value; the sampling value in the input signal is checked to determine whether it represents the signal itself, and the numerical value in the window is sorted by using an observation window composed of an odd number of samples, the middle value is taken as the output, the earliest value is discarded, and a new sample is obtained, and the above calculation process is repeated to reduce the random noise in the image and make the image smoother.

[0125] S17. The grayscale conversion unit obtains the grayscale module image according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), where f(i,j) is the grayscale image and R(i,j), G(i,j), and B(i,j) are the original images of three colors respectively" for subsequent feature extraction and passes it to the feature extraction unit;

[0126] It is further explained that the grayscale calculation formula is used to obtain the grayscale LCD module image, the sampling value in the input signal is checked to determine whether it represents the signal itself, and the values in the window are sorted by using an observation window composed of an odd number of samples, the middle value is taken as the output, the earliest value is discarded, and a new sample is obtained. The above calculation process is repeated to remove the noise in the LCD module image or other signals, so as to subsequently extract the key features of the LCD module image, including overall information such as edges, textures, colors, shapes, and whether there are bright spots, dark spots, missing pictures, poor alignment, and other appearance quality information on the surface; then the standardized data is classified through the written code, and the classified data is sorted. Automatic labeling, adding accurate labels or annotations to the data, which will serve as target variables or features in subsequent model training, and be used as training sets and validation sets to ensure that the model has accurate data references during the training process, so that it can learn how to generate corresponding labels based on data features to improve labeling efficiency and accuracy; for some data, users are required to enter the system remotely through their mobile phones to manually add new labels or modify existing labels to ensure that they accurately reflect the essential characteristics of the data, and deploy the labeled data to the corresponding system platform for subsequent application or analysis to improve the accuracy and reliability of the labels, so as to facilitate the extraction of key features in the subsequent data, which is more conducive to model training, testing and verification.

[0127] S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts key features of brightness, contrast, color uniformity, and defects to improve the training speed and performance of the model.

[0128] It is further explained that the most representative features and the most useful features for the model that can reflect the essential content of the data and have discriminative and descriptive properties are selected from the preprocessed data to reduce the dimension of the features, reduce the computational complexity, and at the same time improve the performance and generalization ability of the model; after feature extraction, principal component analysis is used to perform feature dimensionality reduction to obtain a large amount of feature information in order to reduce the dimension of the features and reduce the computational complexity; after feature dimensionality reduction, the features are binary encoded to improve the interpretability of the features and the performance of the model; since some original data information may be lost after feature extraction and dimensionality reduction, feature reconstruction such as principal component reconstruction or least squares reconstruction is performed to restore the data information as much as possible; evaluation is performed through cross-validation, and the feature extraction method and parameters are adjusted according to the evaluation results to evaluate the quality and effect of the extracted features, improve the training speed and performance of the model, and improve the efficiency of data analysis by reducing the amount or complexity of the data while keeping the original appearance of the data as much as possible.

[0129] S20, the model construction module determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters based on the extracted feature information to construct the model for subsequent model training and verification, and passes it to the model training module;

[0130] See also Figure 10 As shown, the step S20 includes the following steps:

[0131] S21. The network layer unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network layer structure according to the specific application scenarios and requirements to facilitate subsequent defect detection and quality identification, and the network parameter unit;

[0132] Further explanation: Since convolutional neural network (CNN) is a deep neural network, it is particularly suitable for processing data with grid topology. In the production of LCD modules, it can automatically learn and extract useful features such as edges, lines, corners, and more complex combination features from images for subsequent defect detection, quality classification, etc.; since the basic structure of CNN includes input layer, convolution layer, activation function layer, pooling layer, full connection layer, and output layer, these layers can work together in the CNN model of LCD module production to extract and process image features, including: the input layer can receive LCD display data. The image data of the module is used as input; multiple convolution layers are set up, each layer contains multiple convolution kernels, which can extract local features in the image. As the network structure deepens, the appearance gradually becomes abstract; adding a ReLU activation function layer after the convolution layer can introduce nonlinear factors and enhance the expressive ability of the model; adding a pooling layer after the convolution layer can reduce the dimension of the feature map and reduce the amount of calculation while maintaining the spatial invariance of important features; adding a fully connected layer at the end of the network is used to convert the feature maps output by the convolution layer and the pooling layer into classification results, that is, the category or quality level of the LCD display module.

[0133] S22, the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and passes it to the hierarchical optimization unit;

[0134] It is further explained that the model parameters are defined according to the network layer design, including the size, step size, padding method, activation function, etc. of the convolution kernel, as well as the pooling method, pooling window size, etc. of the pooling layer, the number of neurons in the fully connected layer and other layer parameters, which directly affect the performance and accuracy of the model; then the size of the input image, the number of label types, the total training cycle, the batch size and other hyperparameters related to the model training are set, and adjusted according to the specific data set and task requirements; the selection of optimization algorithms such as SGD and Adam, and the setting of corresponding learning rate, momentum and other parameters directly affect the training effect and convergence speed of the model to ensure that the model can accurately extract features from the image and perform effective classification or prediction.

[0135] S23, the hierarchical optimization unit adjusts the size and normalization of the input data by adding a zero-filling layer and a normalization layer before and after the convolution layer to improve the model training speed and stability, and passes it to the data partitioning unit;

[0136] It is further explained that by setting the zero padding layer to fill the edges of the input image with zero values before the convolution operation, the size of the input data is adjusted to facilitate the convolution operation, maintain the image edge information, ensure that the convolution kernel can be correctly applied to the image boundary, and at the same time help maintain the image edge information to avoid information loss during the convolution process; zero padding can more effectively process input images of different sizes without complex preprocessing, which helps to control the size of the convolution layer output feature map, making the network design more flexible and controllable, and ensuring that the network can adapt to changes in LCD display modules of different sizes and resolutions, and accurately extract and process image features; the distribution of the input data is normalized to improve the training speed and stability of the model and accelerate the training process of the neural network. It also improves the convergence speed and enhances the stability of the model. The input of the activation function is normalized before the activation function of each layer of the network. The mean and variance of the batch are calculated for each small batch of data, and then the linear calculation results are batch normalized, that is, the mean is subtracted and divided by the standard deviation to ensure that the calculation results conform to the standard normal distribution with a mean of 0 and a variance of 1. Then, translation and scaling operations are performed to adapt to different data distribution requirements, so that the input of the middle layer of the network remains relatively stable, which helps to solve the problem of gradient disappearance or gradient explosion during training, thereby accelerating training and enhancing the stability of the model. It can improve the robustness of the model to the weight initialization method, alleviate the troubles caused by weight initialization selection, and improve the generalization ability and training efficiency of the model.

[0137] S24. The data partitioning unit divides the data set with key feature vectors into training set, validation set and test set according to the extracted data set and establishes a convolutional neural network structure for subsequent model training.

[0138] Further explanation: According to a preselected segmentation strategy, the ratios of the training set, validation set, and test set are determined, and the data distribution between each subset is ensured to be as consistent as possible to avoid introducing bias. In some application scenarios, due to the time series characteristics of the data, the written code divides the dataset into a training set for training the model, a validation set for adjusting model parameters and selecting the best model, and a test set for evaluating the final performance of the model according to the time series to ensure the temporal consistency of the training and test sets. The dataset is passed through the convolutional neural network deep learning method in a 9:1 ratio to establish the training set and test set required for training the LCD display module quality anomaly recognition pattern prediction model under different environments, thereby establishing a deep convolutional neural network structure: 3 convolutional layers, 3 maximum pooling layers, 2 fully connected layers, 1 softmax layer, and 1 output layer. Zero padding layers and normalization layers are added when necessary. Since the convolution kernel in the convolution layer contains weight coefficients, while the pooling layer does not, the pooling layer is not an independent layer. The convolution layer is used to extract local features of the image, the pooling layer is used to reduce the dimension of the feature map, and the fully connected layer is used to integrate features and perform classification.

[0139] S30, the model training module trains the model based on the collected data and adjusts the model parameters to optimize the model performance to predetermine the LCD module control parameters, ensure the LCD module operation stability, and pass it to the model evaluation module;

[0140] See also Figure 11 As shown, the step S30 includes the following steps:

[0141] S31, input filling unit according to the data filling size calculation formula "P H =[(Ho-1)*S H +K H -H i ] / 2,P W =[(Wo-1)*S W +K W -Wi] / 2,P H 、P W are the height / width filling sizes, Hi and Wi are the height / width of the input feature map, K H , K W are the height / width of the convolution kernel, S H 、S W Where Ho and Wo are the values of the step length in the height / width direction, respectively. The height and width of the output feature map are obtained and input, and passed to the convolution input unit.

[0142] It is further explained that after the image is standardized, the liquid crystal module data first enters the input layer and obtains the padding data through the padding size calculation formula to enter the zero padding layer, fills the edges of the convolution layer input data with zero values, and adjusts the size of the input data for convolution operation to maintain the same spatial dimensions of the input and output, thereby preventing the loss of image edge information, so that the spatial dimensions of the input data can be kept unchanged during subsequent convolution operations to maintain the image edge information and the processing of subsequent layers; the amount of padding is determined by the size of the convolution kernel, the step size and the padding size. In order to keep the height and width of the input and output images the same, or to reduce the size quickly in continuous convolution operations, the amount is usually set to the convolution kernel size minus the convolution kernel size; the height Hi / width Wi of the input feature map, the height K of the convolution kernel H / Width K W , the step value S in the height / width direction H / S W ,The height Ho / width Wo of the output feature map are obtained through model design parameters.

[0143] S32, the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", and passes it to the pooling conversion unit;

[0144] It is further explained that the "width" or "increment" of the integral differential element dm when integrating each infinitesimal interval of the variable m is obtained by accumulating the function values on these infinitesimal intervals (i.e., x(m)y(tm)) to obtain the cumulative effect on the entire definition domain, i.e., z(t). dm is the integral differential element of the variable m, that is, the infinitesimal quantity in the integration process; and convolution calculation is performed to obtain the convolution value and enter the convolution layer and obtain the activation function value through the ReLU function calculation formula "f(x)=max(0,x+Y)" and enter the activation function layer, where f(x) is the activated function, x is the eigenvalue output of the convolution layer or the fully connected layer, and Y is a random variable. When the input x is greater than 0, x is output, when the input x is less than or equal to 0, 0 is output, and when x=0, it is not differentiable, that is, when the input is positive, the original value is maintained, and when the input is negative, 0 is output; but the ReLU activation function is used after the convolution layer to increase the nonlinearity of the network and promote the model to learn complex patterns.

[0145] S33, the pooling conversion unit calculates the maximum pooling formula "Z(i,j)=max(X[i*P S (i+1)*P S ,j*P S (j+1)*P S]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values in the input window, X is the input feature map, P S The maximum pixel value after pooling is obtained by "window size of pooling operation" and enters the fully connected layer to retain important feature information and pass it to the fully connected layer unit;

[0146] Further explanation: by calculating the average value of all values in each region as the output through the maximum pooling calculation formula, more information in the feature map can be retained, which helps to improve the accuracy of the model, retain more detailed information, and is used in the deeper layers of the network to ensure the integrity of the information; before the maximum pooling, according to the average pooling calculation formula "Z(i,j)=mean(X[i*P S (i+1)*P S ,j*P S (j+1)*P S ])” obtains the maximum pixel value after average pooling, Z(i,j) is the pixel value in the output feature map after pooling, mean is the average value of all pixel values in the input window, and the maximum value is selected from each area of the input feature map as the output according to this formula, retaining the most significant features in the feature map, reducing the size of the feature map, and losing some useful information. Since the maximum value of each area is focused on, the grain size feature is retained, and features with better classification recognition are selected.

[0147] S34, the fully connected layer unit calculates the formula of the fully connected layer "y=f(∑(w n *x n )+b), y is the output result, f is the activation function, w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, and b is the bias. The output data of the connection layer is obtained and enters the output layer for subsequent output calculation and is passed to the normalized output unit.

[0148] Further explanation: after pooling, the data is fully connected according to the fully connected layer calculation formula "y=f(∑(w n *x n )+b)” calculation to obtain the output value after convolution, where y is the output result, f is the activation function, and w n is the weight of the nth input feature, x n is n input features, n is the dimension of the input features, b is the bias; the “y=f(∑(w n *x n )+b)” is calculated from “y=f(w*x+b)” to “y=f(w1*x1+w2*x2+…+w n *xn +b)” and transformed, where w is the weight, x n The features extracted by the convolution layer and the pooling layer are integrated and classified through the fully connected layer, so that each neuron is connected to all neurons in the previous layer, and the output is generated through weighted summation and nonlinear activation function.

[0149] S35, the normalized output unit is calculated according to the Batch Norm layer formula "h=φ(B N (Wx+b)), h is the output of the fully connected layer, φ is the activation function, B N is the batch normalization operator, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter. The output of Batch Norm is obtained and passed to the output conversion unit;

[0150] Further explanation, the "h=φ(B N (Wx+b))” through “B N (x) = γ⊙[(x-μ B ) / σ B ]+β”, where μ B is the mean, σ B is the standard deviation, γ is the stretch parameter, β is the offset parameter, (x-μ B ) / σ B To standardize the normal distribution; the Batch Norm layer (referred to as "BN layer") is placed between the affine transformation and the activation function in the fully connected layer, and the output value of each layer in the network is standardized to make it more subject to the normal distribution, which can accelerate the training speed of the neural network and help prevent gradient disappearance and gradient explosion; the BN layer reduces the correlation between the input data by standardizing the data of each mini-batch, so that the mean of each sample is 0 and the variance is 1, thereby reducing the internal covariate shift problem, helping to accelerate the training process, improve the stability and generalization ability of the model, and avoid reducing the problem of reducing the representation ability of the neural network.

[0151] S36. The output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F+2C) / S+1, N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of zero added around the image, and S is the step size" for subsequent model analysis and training, and passes it to the back propagation unit;

[0152] Further explanation: the output size N is the size of the feature map after the convolution operation, the input size P is the width or height of the input image or feature map, and the padding size P in the height direction is obtained by calculating the above step S21. H , the padding size P in the width direction WThe convolution kernel size F is obtained by calculating the above step S22. The number of layers C of 0 added around the image is the number of layers of 0 added around the input image or feature map to control the size of the output feature map, which is also obtained by the above network construction. The step size S is the distance that the convolution kernel slides on the input image or feature map obtained by the above calculation.

[0153] S37. The back-propagation unit obtains the loss function value and back-propagates it according to the loss function calculation formula "L = max(0, m + y * (f (x) - b)), L is the loss function value, m is the hyperparameter, y is the sample label (0 or 1), f (x) is the predicted value of the model, and b is the classification boundary" to optimize the performance of the network model.

[0154] Further explanation, in the loss function calculation formula "L=max(0,m+y*(f(x)-b))", when f(x)≤b, then L=m+y(f(x)-b), when f(x)>b, then L=0; in machine learning or optimization problems, f(x) is an optimization target, b is a threshold, m and y are parameters; when the target value f(x) is less than or equal to the threshold b, then the value of L is equal to m+y(f(x)-b); when the target value f(x) is greater than the threshold b, then the value of L is 0; use the training set data to train the model, adjust the model parameters to minimize the loss function, so that the predicted value of the positive sample is greater than a certain threshold, and the predicted value of the negative sample is less than a certain threshold; then use the backpropagation calculation formula "dz[l]=da[l]*g[l]′(z[l])" to obtain the convolution output values dw[l]=dz[l]*a[l-1], db[l]=dz[l], da[l- 1]=W[l]T*dz[l], where da[l] is the input data, da[1] is the output data, and g[l]′ is the derivative of the activation function sigmoid; the back propagation of the convolution layer transfers the error term da[l]da[l] to the previous layer through the convolution operation, flips the convolution kernel and applies it to the error map, calculates the local gradient by the derivative of the activation function, and implements it through matrix operations, transforms the input and the convolution kernel into matrices, and performs matrix multiplication, that is, pulls the numbers in the convolution window into a row to form a column vector, and performs matrix multiplication; the back propagation of the fully connected layer calculates the gradient of the weight and the gradient of the bias through the chain rule, and for each node, the error term is transferred to the node of the previous layer through the weight matrix, and calculates the local gradient by the derivative of the activation function, and implements it through matrix operations, multiplies the error term by the output of the current layer and the input of the previous layer, so that it is updated in the direction of minimizing the loss function.

[0155] S40, the model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the performance and accuracy of the model, and passes it to the parameter determination module;

[0156] See also Figure 12 As shown, the step S40 includes the following steps:

[0157] S41, the classification and marking unit classifies the quality abnormality categories of the liquid crystal module into corresponding data sample categories and marks them for subsequent machine learning of the model, and transmits them to the learning and training unit;

[0158] Further explanation, data classification is performed according to various quality abnormalities of the LCD module: "light leakage" is category 1, "poor display" is category 2, "garbled code" is category 3, "uneven grayscale" is category 4, "color deviation" is category 5, and "physical damage" is category 6; when category 1 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (1, 0, 0, 0, 0), when category 2 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 1, 0, 0, 0, 0), when category 3 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 1, 0, 0, 0), when category 4 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0, 0, 1, 0, 0, 0), The data is recorded as (0,0,0,1,0,0). When category 5 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,0,0,1,0). When category 6 is a positive sample, the remaining categories are negative samples, that is, the labeled data is (0,0,0,0,0,1). The above 6 abnormal categories are relatively typical abnormal classifications of LCD modules, including but not limited to the above 6 categories. One or more categories can also be reclassified into more categories, and a more detailed and in-depth classification can be performed based on the actual production test results. The above classification is not fixed. The model is retrained each time the category is changed to adapt to the actual production needs.

[0159] S42, the learning and training unit determines a training model based on the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition, and transmits the data to the model evaluation unit;

[0160] It is further explained that the loss function is minimized and the prediction accuracy of the model is improved by continuously adjusting the model parameters to ensure that the model can accurately identify the adaptability of temperature control of the LCD display module in different environments; the model is trained through the data set in the training set to fit the data analysis rules, that is, to determine the various learning parameters such as the model weight and bias; and the model parameters and hyperparameters are adjusted during the model training process through the data set in the validation set to optimize the model performance and avoid overfitting. The model is selected, but it does not participate in the determination of the learning parameters, and the model parameters and hyperparameters with smaller model errors are selected; then the data set in the test set is used to evaluate the generalization ability of the model on unknown data after the model training is completed, and it is used once after training to evaluate the effect of the final model. It does not participate in the learning parameter process or the hyperparameter selection process.

[0161] S43. The model evaluation unit obtains a comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2*(Ac*Re) / (Ac+Re), where F is the training model evaluation score, Ac is the precision, and Re is the recall rate", and transmits it to the processing center;

[0162] Further explanation, the Ac, Re are respectively expressed by "Ac=(T P +T N ) / (T P +F P +F N +T N ), Re=T P / (T P +F N )” is calculated, where T P is the number of true positive samples, F P is the actual number of false positive samples, F N is the number of false negative samples, T N is the number of true negative samples; after the model training is completed, a test is performed to verify the accuracy and reliability of the model. During the test, problems with the model may be found and optimized and adjusted; the training model evaluation score, namely the F value, is the harmonic mean of precision and recall, which can evaluate the performance of the classification model. The value range is 0 to 1, where 1 is the best performance and 0 is the worst performance. The higher the F value, the better the prediction effect of the model, and vice versa. Therefore, if the F value is close to 1, it indicates that the model performs well while maintaining a balance between precision and recall; adjust the hyperparameters according to the model's learning rate, regularization coefficient and other performance to optimize the model performance.

[0163] S44. The processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training until the standard is met.

[0164] It is further explained that the test evaluation score standard of the control category identification training model of the liquid crystal display module is preferably greater than 0.8, which is determined according to factors such as the resolution, contrast, brightness, color reproduction, viewing angle, flatness, high temperature resistance, low temperature resistance, vibration resistance, and impact resistance of the liquid crystal display module; the module production process parameters include the operating parameters, operation parameters, and production inspection process of the production inspection equipment of the liquid crystal display module, among which the operating parameters of the production inspection equipment of the liquid crystal display module are: the resolution, contrast, brightness, and viewing angle of the automated production equipment. Angle, etc., the bonding accuracy, action cycle, hot pressing time, workbench size and pressure head size, temperature, working air pressure, etc. of the ACF attaching machine, the working air pressure, welding pressure, temperature, hot pressing time, temperature and humidity, hot pressing accuracy, pressure head size and body size, etc. of the IC pre-pressing machine, the working air pressure, welding pressure, temperature, hot pressing time, temperature and humidity, hot pressing accuracy, etc. of the IC main press, the working air pressure, hot pressing time, temperature, power supply voltage, power, etc. of the IC pressing machine; the operating parameters of the liquid crystal display module include contrast, brightness, pixels, response time, viewing angle, etc.

[0165] S50, the parameter determination module performs production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module to ensure subsequent production quality, and transmits the parameters to the production application module;

[0166] See also Figure 13 As shown, the step S50 includes the following steps:

[0167] S51, the response time unit is calculated according to the liquid crystal module response time formula "Tr=γ1*d 2 / [ε*(U 2 -Ut 2 )],T d =γ1*d 2 / (ε*U t 2 ),Tr, T d is the rise and fall response time of the LCD module (s), γ1 is the viscosity coefficient of the liquid crystal material (Pa·s), d is the liquid crystal cell gap (m), ε is the dielectric constant of the liquid crystal material (F / m), U is the liquid crystal cell driving voltage (V), and Ut is the threshold voltage of the LCD screen (V). The LCD module response time is obtained for subsequent module testing and passed to the output brightness unit;

[0168] It is further explained that the viscosity coefficient γ1 of the liquid crystal material and the dielectric constant ε of the liquid crystal material can be checked through the industry database; the liquid crystal cell gap d (i.e., the thickness of the liquid crystal layer in the liquid crystal display unit) can be obtained through design data; the liquid crystal cell drive voltage U and the threshold voltage Ut of the liquid crystal display are obtained through sensor detection; since the actual unit of the liquid crystal cell gap is nanometer (nm), it is converted into meter (m) during calculation for the sake of uniformity of unit, and "1 farad (F) equals 1 coulomb per volt (C / V), 1 volt (V) = 1 joule per coulomb (J / C), 1 Pascal (Pa) = 1 Newton per square meter (N / m 2 ), therefore, the unit obtained by the automatic unit conversion during the calculation of the liquid crystal module response time calculation formula is hours (s); the liquid crystal module rising response time Tr refers to the time required for the image to change from the initial white or black to another color when the driving voltage of the liquid crystal panel changes from a low voltage to a high voltage, and is the speed at which the liquid crystal molecules change from one arrangement state to another under the action of the electric field; the liquid crystal module falling response time Td refers to the time required for the image to change from the above-mentioned color to the initial color again when the driving voltage of the liquid crystal panel changes from a high voltage to a low voltage, and is the speed at which the liquid crystal molecules return from one arrangement state to the original arrangement state when the electric field is removed or reversed.

[0169] S52, the output brightness unit calculates the output brightness of the liquid crystal module according to the formula "L=(N*Φ*a*b*c*η) / (S*π), L is the output brightness of the liquid crystal module (cd / m 2 ), N is the number of LED lights in the backlight module, Φ is the luminous flux emitted by the LED light (lm), a is the reflectivity of the reflector (%), b is the transmittance of the diffuser (%), c is the gain provided by the brightness enhancement film and the polarizing film (%), η is the working efficiency of the light guide module in the module (%), S is the light receiving area of the light guide plate (m 2 )” to obtain the output brightness of the LCD module for subsequent module testing and pass it to the color saturation unit;

[0170] Further explanation: the unit of the number N of LED lamps in the backlight module is "pieces", which is only used as a counting unit in the calculation formula of the output brightness of the liquid crystal module. Its unit is not included in the calculation, so it does not affect the final unit conversion; the unit of the output brightness of the liquid crystal module obtained according to the calculation formula of the output brightness of the liquid crystal module is "lumens per square meter (lm / m 2 )”, and “1 candela (cd) is equal to the light intensity of 1 lumen evenly distributed on a spherical surface of 1 square meter”, so the unit of brightness output by the LCD module is “lumens per square meter (lm / m 2 )" can be converted to "candela per square meter (cd / m 2)”, represents the brightness level of the display screen; the number of LED lamps N in the backlight module, the luminous flux Φ emitted by the LED, the reflectivity a of the reflector, the transmittance b of the diffuser plate, the gain c provided by the brightness enhancement film and the polarizing film, the working efficiency η of the light guide module in the module, and the light receiving area S of the light guide plate are all design parameter values or obtained from historical experience data.

[0171] S53. The color saturation unit obtains the color saturation of the LCD module according to the LCD saturation calculation formula: "Sr = (Ic'-Iw') / (Ic-Iw), where Sr is the LCD saturation, Ic' is the light energy (J) emitted by the measured light source under the same amount of white light, Iw' is the energy (J) emitted by the same amount of white light source, Ic is the light energy (J) emitted by the measured light source under the same amount of light, and Iw is the energy (J) emitted by the same amount of light source." This is used for subsequent module testing and is transmitted to the trial debugging unit.

[0172] It is further explained that the light energy Ic′ emitted by the measured light source under the irradiation of equal amounts of white light is the measured value of a certain component of the color light intensity under a certain specific color, such as red, green, or blue; the energy Iw′ emitted by the equal amounts of white light is the measured value of the component of the same color light intensity under white light (or reference light) under the same conditions; the light energy Ic emitted by the measured light source under the irradiation of equal amounts of light is the maximum value or theoretical saturation value of the color light intensity; the energy Iw emitted by the equal amounts of light light source is the maximum value or reference value of the white light intensity; the light energy Ic′ emitted by the measured light source under the irradiation of equal amounts of white light, the energy Iw′ emitted by the equal amounts of white light, the light energy Ic emitted by the measured light source under the irradiation of equal amounts of light, and the energy Iw emitted by the equal amounts of light light source are all obtained through detection equipment such as a spectrometer or a color analyzer.

[0173] S54, the trial debugging unit conducts trial production and testing of the liquid crystal display module using production testing equipment according to predetermined production process parameters to obtain quality information to ensure the accuracy of the liquid crystal module parameters and transmits the information to the processing center;

[0174] Further explanation: According to predetermined operating parameters and prepared raw materials such as liquid crystal panel, driver chip, backlight module, connecting circuit board, various plastic frames and supporting structures, thin film, yellow light, etching, stripping and other processes are carried out through automated production equipment to form a TFT array, the TFT substrate and the CF substrate are bonded and injected with liquid crystal material, the driver IC of the liquid crystal substrate is pressed and integrated with the printed circuit board, and the backlight part is integrated with the liquid crystal substrate to complete the complete liquid crystal panel, the liquid crystal panel is connected to the driver chip, the backlight module is installed, and the plastic frame and other components are fixed to complete the assembly of the liquid crystal display module, and then the ACF attachment machine is used. , IC pre-pressing machine, IC main press, pressing machine and other professional equipment to ensure that each component can be accurately fitted and fixed; then the LCD module is imaged through the automatic detection system, and the captured image is analyzed by the detection software to evaluate the appearance quality information of the LCD module, and the parameters are calculated with reference to the above steps S51-S53 to detect the VDD, IDD, VOP, backlight voltage, current, color, brightness, contrast, color accuracy, resolution and other parameters of the LCD display module through lighting detection equipment and other equipment to ensure the normal display of the module under various signal inputs and meet industry standards and customer needs.

[0175] S55. The processing center compares the module quality information with the LCD module production quality standards stored in the memory: if the standards are met, the parameters are set as formal production process parameters; if the standards are not met, the parameters are transmitted to the alarm and the adjustment parameters are notified for rework.

[0176] It is further explained that the production quality standards of the liquid crystal module include: no scratches, cracks, workmanship defects and other problems on the surface, ensuring that the screws are firmly connected and not falling off, and the polarizer is free of bubbles, degumming, foreign matter, black spots, white spots, etc.; the display quality such as size and resolution, brightness, contrast, color saturation, and viewing angle meets the requirements; accurately restore the color in the image and meet the industry standard or higher level; can withstand high temperature, low temperature, vibration, impact and other harsh environments to work stably; can maintain good heat dissipation performance during efficient operation; there are no missing horizontal or vertical lines, poor display contrast, missing characters, Electrical characteristic problems such as dots or patterns, abnormal display function, no function or no display, current consumption exceeding that specified in the specification, abnormal LCD viewing angle, mixing of different types of modules, and abnormal LCD contrast; when displaying, white dots or black dots must be smaller than a certain size, the number cannot exceed the specified number, and the distance between two adjacent dots must meet certain standards. When not displaying, the detection of white and black dots must meet the size and number requirements, and the number and distribution of bad pixels such as bright dots, dark dots, connected dots, micro-bright dots, and micro-dark dots must comply with relevant standards; after installation, there is no obvious elastic deformation when hitting the surface and edge of the screen.

[0177] S56. The abnormality recognition unit matches the real-time acquired LCD module production inspection image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category for subsequent production improvement and parameter adjustment.

[0178] To further illustrate, the image is input into the model and the trained model is used to predict the new monitoring image. The type of abnormality of the LCD module is judged according to the output result. If the model's judgment on the abnormality of the LCD module reaches a certain threshold, the early warning system is triggered and corresponding solutions are taken in time. The abnormality types of the LCD module include: 1) Light leakage: When displaying a black picture, a halo appears on the edge or a corner of the screen, which is caused by the frame pressing on the screen during assembly; 2) Poor display: The screen displays light, messy, missing horizontal or vertical bars, no display, etc., due to PCB board short circuit, dirt, zebra paper short circuit, electrode misalignment when pressing the screen, etc.; 3) Garbled code: The content displayed on the display is chaotic and unrecognizable, due to the misalignment between the PCB board and the LCD screen PIN pin, the electrodes cannot correspond one to one, or the PCB substrate is damaged, the external 4) Uneven grayscale: color bands or obvious steps appear in the displayed image, which is caused by insufficient resolution of the display device, improper grayscale ratio adjustment or improper use of calibration tools; 5) Color deviation: the displayed color deviates from the true color, which is caused by insufficient color management of the display device or improper use of color correction tools; 6) Physical damage: the gold finger ITO on the LCD screen is broken, ITO is corroded, or the conductive layer on the conductive strip is damaged, etc., due to improper operation or material problems in the production process; etc. These trained models are applied to subsequent LCD module inspections. By inputting new sample data, the trained model and its corresponding production process parameters can quickly obtain production inspection results, replacing manual judgment of the quality status of the LCD module.

[0179] S60, the production application module produces and performs various tests on the LCD display module according to the set production process parameters and the LCD module production and testing equipment according to the program instructions to ensure that the LCD module meets the quality requirements.

[0180] See also Figure 14 As shown, the step S60 includes the following steps:

[0181] S61, the substrate array unit performs film formation, PR coating, exposure, development, etching, and PR stripping on the glass substrate to form a TFT array with 4 to 5 layers of thin film patterns, and transmits the result to the liquid crystal panel unit;

[0182] To further explain, in the front-end array process, physical vapor deposition (PVD) or chemical vapor deposition (CVD) technology is used to sputter the gate material on the borosilicate glass substrate to form the required metal layer, or non-metal layer, or semiconductor layer and other thin film layers; a mask is used for exposure to transfer the required pattern from the mask to the photoresist, and the photosensitive part of the photoresist is washed away by development, leaving the required gate wiring pattern coated on the substrate; the PECVD method is used for continuous film formation to form a SiNx film, or a non-doped a-Si film, or a phosphorus-doped n+a-Si film, and then the mask exposure and Dry etching forms the a-Si thin film pattern of the TFT part; sputtering film forming method is used to form the transparent electrode (ITO film), and then mask exposure and wet etching are used to form the display electrode pattern; mask exposure and dry etching are used to form the contact hole pattern of the gate end insulating film; AL is sputtered to form a film and mask exposure and etching are used to form a glass substrate (TFT), and auxiliary processes such as cleaning, marking and edge exposure, AOI (automatic optical inspection), Mic, Mac observation, film performance testing, electrical testing and laser repair are carried out to ensure that the quality and performance of the TFT array meet the requirements.

[0183] S62. The liquid crystal panel unit adheres the TFT substrate to the CF substrate and injects the liquid crystal material according to the control command and predetermined parameters through alignment film printing, sealant coating, spacer spraying, liquid crystal injection, sealing assembly, and polarizer attachment to ensure the correct arrangement of liquid crystal molecules and the stability of the display effect, and then transmits the result to the module assembly unit.

[0184] Further explanation: In the mid-cell process, the surfaces of the TFT substrate and the CF substrate are cleaned and then coated with PI to provide an oriented substrate for the liquid crystal to ensure that the liquid crystal molecules have the correct orientation and pre-tilt angle in the cell; the PI film on the top of the glass substrate is rubbed with an alignment cloth to create grooves for liquid crystal orientation, so that the liquid crystal is neatly arranged between the upper and lower alignment films according to the specified direction; a sealant is applied to the edges of the glass substrate to seal it, and 5-10um spacers are scattered on it as support points. At the same time, the silicon balls in it act as gaskets to ensure a uniform spacing between the two glass substrates; the liquid crystal is dripped between the two glass substrates using a drop-fill method and hot-pressed to bond the glass substrates to ensure that the liquid crystal is evenly and stably enclosed between the two glass substrates; the bonded large-size LCD panel is cut into multiple small-size LCD screens to improve production efficiency; then polarizers are attached to both sides of the LCD panel to enable the LCD screen to display clear images, ensuring the normal operation and display effect of the LCD screen.

[0185] S63, the module assembly unit performs the COG process, flexible circuit board / printed circuit board lamination, and backlight module assembly according to the control command and predetermined process parameters to display the image, and transmits the result to the quality inspection unit;

[0186] To further explain, in the back-end Module Assembly process, the driver chip is fixed to the LCD panel through pressing technologies such as TAB tape carrier packaging or COG chip direct mounting, and is electrically connected to the printed circuit board PCB, so that the driver chip can receive signals from the main control circuit and control the rotation of the liquid crystal molecules to display images; the backlight module is assembled and integrated with the LCD panel to ensure that light can penetrate the liquid crystal layer and be displayed correctly, so that it provides evenly distributed light and enables the LCD panel to display clear images; in order to protect the LCD panel and backlight source, and to provide necessary mechanical support, the outer frame and other components such as iron frame, plastic frame, support structure, etc. are installed to jointly ensure the stability and durability of the LCD display module.

[0187] S64. The quality inspection unit uses high-definition cameras and various performance testing equipment to test the appearance and electrical, optical, functional, and reliability performance of the LCD display module to ensure that the module quality and performance meet the requirements and pass it to the processing center;

[0188] It is further explained that according to the set process parameters, the high-definition camera is controlled to perform 360-degree shooting, and images of various positions of the LCD module are taken from multiple different angles. Different positions of the LCD module are identified at different angles, so that the various positions and shapes of the LCD module can be identified more accurately and comprehensively, or based on multiple images of the LCD module taken from different angles, the LCD module is identified by multi-angle matching, so as to determine whether there are scratches, stains, bubbles or damage on the surface of the LCD module, whether the shell and connecting parts are intact, and whether there is any deformation or damage; then, according to the control instructions and operating parameters, the LCD display tester and its supporting equipment are used to measure the electrical parameters such as VDD, IDD, VOP, backlight voltage and current, TCO layer resistance, transmittance and response time of the LCD display module, as well as the optical parameters such as brightness, contrast, color gamut, color accuracy, brightness uniformity, viewing angle, color gamut coverage, color uniformity, as well as color performance, brightness, etc. of the LCD display module. Functional parameters such as brightness, contrast, and response time are tested to check whether there are display defects such as dead pixels, bright spots, or dark spots to evaluate the display performance and stability of the module; finally, the LCD module is tested for environmental stress tests such as high temperature, low temperature, vibration, and impact using an LCD module reliability test device and its supporting equipment to evaluate the reliability and durability of the LCD module, and a life test is performed to evaluate the service life of the module under specific environmental and working conditions; the LCD module image data includes: 1) real-time images during the production process, which can monitor the operating status of the production line and promptly detect and handle abnormal situations; 2) images of module products, which are used to perform quality inspections on the module to check for defects, color uniformity, and other abnormalities; 3) images of raw materials, which ensure that the quality of the raw materials meets production requirements and avoid production problems caused by raw material problems; according to specific production needs and algorithm requirements, other types of image data such as images under different lighting conditions and images from different angles need to be collected to improve the accuracy and robustness of the algorithm.

[0189] S65. The processing center compares the module quality information with the LCD module production quality standards stored in the memory. If the standards are met, the center notifies the user that the module can be shipped. If the standards are not met, the center notifies the user that the module is to be reworked or repaired.

[0190] It is further explained that in addition to the production quality standards of the liquid crystal modules described in step S55 above, the production quality standards of the liquid crystal modules also include: the module surface is free of scratches, bubbles, foreign matter and other appearance abnormalities, and the size and number of defects such as point defects, line defects, and polarizer bubbles cannot exceed the limit; the liquid crystal module does not have problems such as missing horizontal or vertical lines, poor line display contrast, missing characters, dots or patterns, abnormal display functions, and the current consumption must not exceed that shown in the specification; white dots or black dots must be less than a certain number of millimeters when displayed, and the number cannot exceed the specified value; the viewing angle, contrast and other display effects of the LCD screen meet customer requirements; the screen has no obvious elastic deformation when hitting the surface and edge of the screen to ensure that the module can maintain stability and reliability during use; the backlight brightness, touch function and other functions meet customer requirements and are based on the customer's requirements. The special requirements and actual application scenarios of the module are different to ensure that the quality of the module meets customer needs and industry standards; the said appearance abnormality problem is obtained by processing the real-time detection image data of the LCD panel with a high-definition camera, and the real-time image data is used to detect the LCD panel, specifically including defect type analysis of the LCD panel detection results, comparing the actual brightness of each position in the LCD panel detection surface collected by the real-time image with the set brightness threshold range, and the position that is not in the set brightness threshold range will be marked as an abnormal point, and its position will be merged to construct an abnormal surface. If there is no adjacent abnormal point, the corresponding abnormal point will be marked as an abnormal point, and the defect type of the LCD panel will be analyzed, and targeted defect maintenance will be carried out according to different types, thereby improving the detection efficiency of the LCD panel and the timeliness of defect repair.

[0191] Further explanation: the above steps are displayed in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps. These steps can also be executed in other orders, and some steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps; if the quality of the TFT array in the above-mentioned front-end Array process does not meet the standards, return to step S61 for rework; if the quality of the liquid crystal panel in the above-mentioned middle-stage Cell process does not meet the standards, return to step S62 for rework; if the quality of the liquid crystal panel in the above-mentioned back-end Module If the quality of module assembly in the Assembly process does not meet the standards, return to step S63 for rework; if the quality of two or one of the three, namely, the TFT array in the front-end Array process, the liquid crystal panel in the middle-stage Cell process, and the module assembly in the back-end ModuleAssembly process, does not meet the standards, return to the corresponding steps in the above steps S61-S63 respectively, rework according to the process requirements, and then re-test until they meet the standards.

[0192] Further explanation: The present invention is described based on the content implemented by the software program of the aforementioned liquid crystal display module manufacturing control system. Each method for manufacturing a liquid crystal display module is divided into several modules or units to implement the software program instructions generated by each step. The software program instructions include the aforementioned method for manufacturing a liquid crystal display module.

[0193] A liquid crystal display module manufacturing control system provided by the present invention also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the functional modules execute the computer program, the steps of the liquid crystal display module manufacturing method described in any one of the above are implemented; the computer-readable storage medium stores a computer program, and when the functional modules execute the computer program, the steps of the liquid crystal display module manufacturing method described in any one of the above are implemented.

[0194] It is further explained that the computer-readable storage medium includes a memory, which can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the program and instructions corresponding to the method for manufacturing a liquid crystal display module in the present invention, including information transmission instructions for each module; the memory executes various functional applications and data processing of each module by running the stored non-volatile software programs and instructions, that is, implements the method for manufacturing a liquid crystal display module in the above-mentioned process embodiment; one or more units are stored in the memory, and when executed by the one or more modules, execute the method for manufacturing a liquid crystal display module in any of the above-mentioned process embodiments; the computer-readable storage medium stores computer-executable instructions, which are executed by one or more modules and can also be a method for manufacturing a liquid crystal display module in any of the above-mentioned process embodiments.

[0195] It is further explained that the computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two, and can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or component, including but not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, wherein the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable program code, and the propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals or any suitable combination of the above, and may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate or transmit a program for use by or in combination with an instruction execution system, device or component, and the program code that may be contained may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0196] It is further explained that the computer program is divided into multiple modules / units, which are stored in the memory and executed by each module / unit to complete the present invention; the multiple modules / units can be a series of computer program instructions that can perform specific functions, and the instructions are used to describe the execution process of the computer program in each module / unit.

[0197] It is further explained that the content described above in the present invention is written with reference to the implemented parts of the software copyrights such as "Liquid Crystal Display Color Real-time Optimization Tuning Control System (Registration Number: 2024SR0613057)" and "High-Definition Liquid Crystal Display Intelligent Backlight Brightness Control System (Registration Number: 2024SR0621649)" that our company has applied for successively since April 2017.

[0198] The present invention also provides a liquid crystal display module manufacturing control device, which is implemented using the above-mentioned method for manufacturing a liquid crystal display module.

[0199] It is further explained that the control device is composed of the above-mentioned associated detection equipment or devices, and can be made into a complete set of automatic production and detection equipment for LCD modules together with the production and detection equipment for LCD modules according to the needs of LCD module manufacturers; it can also be made into a unit device of each functional module belonging to each step or the entire control device, and during installation, each control device is connected to each production and detection equipment of the LCD module through a wireless connection; the structures of these devices are not described in detail here; the control device can also be used in professional detection institutions for LCD modules to improve detection efficiency.

[0200] It is obvious to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application. Therefore, from all perspectives, the embodiments should be considered as illustrative and non-restrictive. The scope of the present application is defined by the appended claims rather than the foregoing description, and it is intended that all changes that fall within the meaning and range of equivalents of the claims be encompassed within the present application.

[0201] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents, and all of these should be included in the scope of protection of the present application.

Claims

1. A method for manufacturing a liquid crystal display module, characterized in that: The method comprises the following steps: S10. Before production, the information acquisition module acquires normal and abnormal historical image data of the operation and production quality of the LCD module and pre-processes it for subsequent model construction, and transmits it to the model construction module; S20, the model construction module determines the model architecture, designs the network hierarchy, adds auxiliary layers, and defines model parameters based on the feature information to construct the model for subsequent model training and verification, and passes it to the model training module; S30, the model training module trains the model based on the collected data and adjusts the model parameters to optimize the model performance to predetermine the LCD module control parameters, ensure the LCD module operation stability, and pass it to the model evaluation module; S40, the model evaluation module performs model verification and evaluation based on the trained model, and adjusts and optimizes the model based on the verification results to improve the performance and accuracy of the model, and passes it to the parameter determination module; S50, the parameter determination module performs production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module to ensure subsequent production quality, and transmits the parameters to the production application module; S60 , the production application module produces and performs various tests on the liquid crystal display modules according to the set production process parameters and the program instructions of the liquid crystal module production and testing equipment.

2. A method for manufacturing a liquid crystal display module according to claim 1, characterized in that The method is applied to a liquid crystal display module manufacturing control system, which includes an information acquisition module, a model construction module, a model training module, a model evaluation module, a parameter determination module, a production application module, a wireless communication module, a memory, an alarm, a processing center, and an intelligent mobile terminal; the information acquisition module, the model construction module, the model training module, the model evaluation module, the parameter determination module, the production application module, the wireless communication module, the memory, and the alarm are respectively connected to the processing center; the intelligent mobile terminal is respectively connected to the wireless communication module wireless network within the range of a wireless network or the Internet; The wireless communication module is provided with a wireless network unit, which is responsible for sending and receiving wireless signals and automatically networking with the smart mobile terminal and the control device within the effective network range; The alarm device compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to continue training; and compares the module quality information with the production quality standard of the liquid crystal module stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to adjust the parameters and rework; and compares the module quality information with the production quality standard of the liquid crystal module stored in the memory. If the standard is not met, it automatically sounds an alarm and notifies to rework; The memory is responsible for storing information of the information acquisition module, model construction module, model training module, model evaluation module, parameter determination module, production application module, wireless communication module, and alarm, as well as the model evaluation sub-standard and the liquid crystal module production quality standard; The processing center is responsible for information transmission among various functional modules, alarms, and memories, and is the hub of the system. The processing center compares the actual evaluation score of the model with the evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is set as the official production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters and rework; and compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is notified that it can be shipped; if it does not meet the standard, it is transmitted to the alarm and notified to rework or repair; The information acquisition module includes a data acquisition unit, a data cleaning unit, a data enhancement unit, a data integration unit, a data conversion unit, a filtering and denoising unit, a grayscale conversion unit, and a feature extraction unit, and is responsible for acquiring and preprocessing normal and abnormal historical image data of the operation and production quality of the liquid crystal display module, and passing it to the model construction module; The model construction module includes a network hierarchy unit, a network parameter unit, a hierarchical optimization unit, and a data partitioning unit. It is responsible for determining the model architecture, designing the network hierarchy structure, adding auxiliary layers, defining model parameters, and constructing the model based on the extracted feature information, and passing it to the model training module. The model training module includes an input padding unit, a convolution input unit, a pooling conversion unit, a fully connected layer unit, a normalized output unit, an output conversion unit, and a back-propagation unit, and is responsible for training the model based on the collected data and adjusting the model parameters to optimize the model performance to predetermine the LCD module control parameters and pass them to the model evaluation module; The model evaluation module includes a classification labeling unit, a learning and training unit, and a model evaluation unit, which is responsible for model verification and evaluation based on the trained model, and adjusting and optimizing the model based on the verification results, and passing them to the parameter determination module; The parameter determination module includes a response time unit, an output brightness unit, a color saturation unit, a trial debugging unit, and an abnormality recognition unit. It is responsible for conducting production tests under different conditions based on the production process parameters predicted by the trained model to obtain the optimal production process parameters for the liquid crystal module and pass them to the production application module; The production application module includes a substrate array unit, a liquid crystal panel unit, a module assembly unit, and a quality inspection unit, which are responsible for producing and inspecting the liquid crystal display modules according to set production process parameters.

3. The method for manufacturing a liquid crystal display module according to claim 1, characterized in that : Described step S10 comprises the following steps: S11. The data acquisition unit obtains historical data on various electrical, optical, and environmental performance and production process parameters of similar liquid crystal display modules by connecting to the industry database, and transmits the data to the data cleaning unit; S12. The data cleaning unit cleans the collected historical data to remove abnormal values, duplicate values or missing values in the data to improve the quality and accuracy of the data, and transmits the data to the data enhancement unit; S13, the data enhancement unit increases the quantity and diversity of the LCD module training data through data enhancement methods such as rotation, scaling, flipping, cropping, and color transformation to improve the generalization ability of the model, and transmits it to the data integration unit; S14. The data integration unit obtains standardized integrated data according to the data standardization processing formula "z = (x-μ) / σ, z is the standardized data, x is the original data, μ is the mean of the data, and σ is the standard deviation of the data" to improve the stability of the model and passes it to the data conversion unit; S15. The data conversion unit obtains normalized data according to the normalization calculation formula "x' = (x-min(x)) / (max(x)-min(x)), x' is the normalized data, x is the original data, min(x) and max(x) are the minimum and maximum values of the data respectively" to improve the model performance and pass it to the filtering and denoising unit; S16, filtering and denoising unit is calculated according to the Gaussian filtering method" G(x,y) is the two-dimensional Gaussian function pixel, (x,y) is the pixel coordinate, and σ is the standard deviation. The denoised image is obtained for grayscale image conversion and passed to the grayscale conversion unit; S17. The grayscale conversion unit obtains the grayscale module image according to the grayscale calculation formula "f(i,j) = max(R(i,j), G(i,j), B(i,j)), where f(i,j) is the grayscale image and R(i,j), G(i,j), and B(i,j) are the original images of three colors respectively" for subsequent feature extraction and passes it to the feature extraction unit; S18. The feature extraction unit converts the labeled data into feature vectors useful for model training and extracts key features of brightness, contrast, color uniformity, and defects to improve the training speed and performance of the model.

4. The method for manufacturing a liquid crystal display module according to claim 1, wherein: The step S20 comprises the following steps: S21. The network layer unit uses the selected convolutional neural network as the model architecture and customizes and optimizes the network layer structure according to the specific application scenarios and requirements to facilitate subsequent defect detection and quality identification, and the network parameter unit; S22, the network parameter unit adjusts the number of network layers, convolution kernel size, step size, padding method and selects the loss function and optimization algorithm according to the network hierarchy structure to ensure the performance and accuracy of the model, and passes it to the hierarchical optimization unit; S23, the hierarchical optimization unit adjusts the size and normalization of the input data by adding a zero-filling layer and a normalization layer before and after the convolution layer to improve the model training speed and stability, and passes it to the data partitioning unit; S24. The data partitioning unit divides the data set with key feature vectors into training set, validation set and test set according to the extracted data set and establishes a convolutional neural network structure for subsequent model training.

5. The method for manufacturing a liquid crystal display module according to claim 1, characterized in that : The step S30 comprises the following steps: S31, input filling unit according to data filling size calculation formula "P H =[(Ho-1)*S H +K H -Hi] / 2,P W =[(Wo-1)*SW+KW-Wi] / 2, PH and PW are the padding sizes in the height / width direction respectively, Hi and Wi are the height / width of the input feature map respectively, KH and KW are the height / width of the convolution kernel respectively, SH and SW are the values of the step size in the height / width direction respectively, and Ho and Wo are the height and width of the output feature map respectively. Get the padding data and input it, and pass it to the convolution input unit; S32, the convolution input unit obtains the convolution input value and activates the function input according to the convolution input calculation formula "z(t) = ∫x(m)y(tm)dm, z(t) is the output function, x(t) is the input function, y(t) is the convolution kernel function, and dm is the integral differential element of the variable m", and passes it to the pooling conversion unit; S33. The pooling conversion unit obtains the maximum pixel value after pooling according to the maximum pooling calculation formula "Z(i,j)=max(X[i*PS(i+1)*PS,j*PS(j+1)*PS]), Z(i,j) is a pixel value in the output feature map after pooling, i and j are the positions in the output feature map, max is the maximum value of all pixel values in the input window, X is the input feature map, and PS is the window size of the pooling operation" to retain important feature information and pass it to the fully connected layer unit; S34, the fully connected layer unit obtains the output data of the connection layer according to the fully connected layer calculation formula "y = f(∑(wn*xn)+b), y is the output result, f is the activation function, wn is the weight of the nth input feature, xn is the nth input feature, n is the dimension of the input feature, and b is the bias" and enters the output layer for subsequent output calculation and is passed to the normalized output unit; S35, the normalized output unit is calculated according to the Batch Norm layer formula "h=φ(B N (Wx+b)), h is the output of the fully connected layer, φ is the activation function, BN is the batch normalization operator, W is the weight parameter, x is the input of the fully connected layer, and b is the bias parameter" to obtain the output of Batch Norm and pass it to the output conversion unit; S36. The output conversion unit obtains the output value size after convolution according to the output layer conversion calculation formula "N = (P-F+2C) / S+1, where N is the output size after convolution, P is the input size before convolution, F is the convolution kernel size, C is the number of layers of zero added around the image, and S is the step size" for subsequent model analysis and training, and passes it to the back propagation unit; S37. The back-propagation unit obtains the loss function value and back-propagates it according to the loss function calculation formula "L = max(0, m + y * (f(x) - b)), L is the loss function value, m is the hyperparameter, y is the sample label (0 or 1), f(x) is the predicted value of the model, and b is the classification boundary" to optimize the performance of the network model.

6. The method for manufacturing a liquid crystal display module according to claim 1, characterized in that : The step S40 comprises the following steps: S41, the classification and marking unit classifies the quality abnormality categories of the liquid crystal module into corresponding data sample categories and marks them for subsequent machine learning of the model, and transmits them to the learning and training unit; S42, the learning and training unit determines a training model based on the gradient descent data, and inputs the data in the training set into the model for simulation training under different environmental conditions to ensure the accuracy of model recognition, and transmits the data to the model evaluation unit; S43. The model evaluation unit obtains a comprehensive evaluation score F according to the model evaluation score calculation formula "F = 2*(Ac*Re) / (Ac+Re), where F is the training model evaluation score, Ac is the precision, and Re is the recall", and transmits it to the processing center; S44. The processing center compares the actual evaluation score of the model with the comprehensive evaluation score standard of the model stored in the memory: if it meets the standard, it is the predetermined module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to continue training.

7. The method for manufacturing a liquid crystal display module according to claim 1, wherein: The step S50 comprises the following steps: S51, the response time unit is calculated according to the liquid crystal module response time formula "Tr=γ1*d 2 / [ε*(U 2 -U t 2 )],T d =γ1*d 2 / (ε*Ut 2 ),Tr, T d is the rise and fall response time of the LCD module (s), γ1 is the viscosity coefficient of the liquid crystal material (Pa·s), d is the liquid crystal cell gap (m), ε is the dielectric constant of the liquid crystal material (F / m), U is the liquid crystal cell driving voltage (V), and Ut is the threshold voltage of the LCD screen (V). The LCD module response time is obtained for subsequent module testing and passed to the output brightness unit; S52, the output brightness unit calculates the output brightness of the liquid crystal module according to the formula "L=(N*Φ*a*b*c*η) / (S*π), where L is the output brightness of the liquid crystal module (cd / m 2 ), N is the number of LED lights in the backlight module, Φ is the luminous flux emitted by the LED light (lm), a is the reflectivity of the reflector (%), b is the transmittance of the diffuser (%), c is the gain provided by the brightness enhancement film and the polarization film (%), η is the working efficiency of the light guide module in the module (%), S is the light receiving area of the light guide plate (m 2 )” to obtain the output brightness of the LCD module for subsequent module testing and pass it to the color saturation unit; S53. The color saturation unit obtains the color saturation of the LCD module according to the LCD saturation calculation formula "Sr = (Ic'-Iw') / (Ic-Iw), where Sr is the saturation of the LCD screen, Ic' is the light energy (J) emitted by the measured light source under the same amount of white light, Iw' is the energy (J) emitted by the same amount of white light source, Ic is the light energy (J) emitted by the measured light source under the same amount of light, and Iw is the energy (J) emitted by the same amount of light source." for use in subsequent module testing and is transmitted to the trial debugging unit. S54, the trial debugging unit conducts trial production and testing of the liquid crystal display module using production testing equipment according to predetermined production process parameters to obtain quality information to ensure the accuracy of the liquid crystal module parameters and transmits the information to the processing center; S55. The processing center compares the module quality information with the LCD module production quality standard stored in the memory: if it meets the standard, it is set as the module production process parameter; if it does not meet the standard, it is transmitted to the alarm and notified to adjust the parameters and rework. S56. The abnormality recognition unit matches the real-time acquired LCD module production inspection image with the corresponding image in the trained convolutional neural network model and confirms its abnormality category for subsequent production improvement and parameter adjustment.

8. The method for manufacturing a liquid crystal display module according to claim 1, characterized in that : The step S60 comprises the following steps: S61, the substrate array unit performs film formation, PR coating, exposure, development, etching, and PR stripping on the glass substrate to form a TFT array with 4 to 5 layers of thin film patterns, and transmits the result to the liquid crystal panel unit; S62. The liquid crystal panel unit adheres the TFT substrate to the CF substrate and injects the liquid crystal material according to the control command and predetermined parameters through alignment film printing, sealant coating, spacer spraying, liquid crystal injection, sealing assembly, and polarizer attachment to ensure the correct arrangement of liquid crystal molecules and the stability of the display effect, and then transmits the result to the module assembly unit. S63, the module assembly unit performs the COG process, flexible circuit board / printed circuit board lamination, and backlight module assembly according to the control command and predetermined process parameters to display the image, and transmits the result to the quality inspection unit; S64. The quality inspection unit uses high-definition cameras and various performance testing equipment to test the appearance and electrical, optical, functional, and reliability performance of the LCD display module to ensure that the module quality and performance meet the requirements and pass it to the processing center; S65. The processing center compares the module quality information with the LCD module production quality standards stored in the memory. If the standards are met, the center notifies the user that the module can be shipped. If the standards are not met, the center notifies the user that the module is to be reworked or repaired.

9. A method for manufacturing a liquid crystal display module according to any one of claims 1 to 8, characterized in that: The system also includes a computer-readable storage medium containing a memory; the memory stores a computer program, and when the functional modules execute the computer program, the steps of the method for manufacturing a liquid crystal display module described in any one of claims 1 to 8 are implemented; the computer-readable storage medium stores a computer program, and when the computer program is executed by the functional modules, the steps of the method for manufacturing a liquid crystal display module described in any one of claims 1 to 8 are implemented.

10. A liquid crystal display module manufacturing control device, characterized in that: This is achieved by using a method for manufacturing a liquid crystal display module as described in any one of claims 1 to 8.

Images