Backlight packaging process optimization control method and system

Abstract

The invention relates to a backlight source packaging process optimization control method and system, and relates to the field of backlight source production, and the method comprises the steps: randomly configuring LED fixing parameters for fixing an LED chip in a backlight source packaging process; lED chip fixing simulation is carried out according to the LED fixing parameters, and the deviation angle, the actual fixing position and the dispensing thickness of the LED chip are obtained; performing illumination influence calculation according to the deviation angle of the LED chip to obtain an illumination influence coefficient, and performing welding wire influence calculation according to the actual fixing position and the dispensing thickness to obtain a welding wire influence coefficient; and packaging scores of the LED fixed parameters are obtained through calculation, optimization adjustment of the LED fixed parameters is carried out, the optimal LED fixed parameters are obtained, and backlight source packaging control is carried out. The technical problems that in the prior art, due to the fact that deviation occurs in the LED packaging process, illumination is not uniform after packaging, and the service life of a backlight source is affected are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of backlight source production, and in particular to a backlight source packaging process optimization control method and system. Background Art

[0002] The backlight in a liquid crystal display (LCD) provides light for the display. The packaging and production of the backlight source needs to ensure uniform illumination and a long service life to ensure stable use of the liquid crystal display. The packaging of the backlight source includes the packaging and fixing of the LED chip. In the prior art, problems such as offset may occur during the LED packaging process, resulting in uneven illumination after packaging and affecting the service life of the backlight source. There is a technical problem of poor packaging quality of the backlight source. Summary of the invention

[0003] The present invention aims to solve the technical problems in the prior art such as the offset that occurs during the LED packaging process, resulting in uneven lighting after packaging, affecting the service life of the backlight source, and poor packaging quality of the backlight source, and proposes a backlight source packaging process optimization control method and system.

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

[0005] In a first aspect, the present invention provides a method for optimizing and controlling a packaging process of a backlight source, comprising: randomly configuring LED fixed parameters for fixing LED chips during packaging of the backlight source, wherein the LED fixed parameters include a fixed position, a glue dispensing position, and a glue dispensing amount;

[0006] According to the LED fixing parameters, a LED chip fixing simulation is performed to obtain the LED chip offset angle, actual fixing position and dispensing thickness;

[0007] Calculating the illumination influence according to the offset angle of the LED chip to obtain the illumination influence coefficient, and calculating the welding wire influence according to the actual fixing position and the glue dispensing thickness to obtain the welding wire influence coefficient;

[0008] According to the illumination influence coefficient and the welding wire influence coefficient, the packaging score of the LED fixed parameters is calculated, the LED fixed parameters are optimized and adjusted, the optimal LED fixed parameters are obtained, and the backlight source packaging control is performed.

[0009] In a second aspect, the present invention provides a backlight packaging process optimization control system, comprising:

[0010] A fixed parameter configuration module, used to randomly configure LED fixed parameters of LED chips during backlight packaging, wherein the LED fixed parameters include a fixed position, a dispensing position, and a dispensing amount;

[0011] A fixing simulation module, used to perform LED chip fixing simulation according to the LED fixing parameters, and obtain the LED chip offset angle, actual fixing position and dispensing thickness;

[0012] An impact analysis module, used to calculate the illumination impact according to the LED chip offset angle to obtain the illumination impact coefficient, and to calculate the welding wire impact according to the actual fixing position and the glue dispensing thickness to obtain the welding wire impact coefficient;

[0013] The optimization control module is used to calculate the packaging score of the LED fixed parameters according to the illumination influence coefficient and the welding wire influence coefficient, optimize and adjust the LED fixed parameters, obtain the optimal LED fixed parameters, and perform backlight source packaging control.

[0014] The beneficial effects of the present invention are as follows: the present invention provides a method for optimizing and controlling the packaging process of a backlight source, by randomly configuring the fixed parameters of the LED chip, including the fixed position, the dispensing position and the dispensing amount, combined with machine learning modeling, to achieve accurate simulation of the fixation of the LED chip, obtain the offset angle, the actual fixed position and the dispensing thickness of the LED chip, and then perform illumination influence analysis and welding wire influence analysis to quantify the influence on the performance of the LED backlight source and optimize the packaging fixed parameters. The present invention can dynamically evaluate the illumination influence and welding wire influence during the packaging process, and quantify the influence of the LED chip fixed parameters on the packaging quality by calculating the illumination influence coefficient and the welding wire influence coefficient. In addition, through the packaging score calculation and parameter optimization adjustment, the present scheme can iteratively obtain the optimal LED fixed parameters, make the LED chip fixation more accurate, reduce the packaging deviation, and improve the packaging consistency. Finally, the optimized backlight source packaging process not only improves the illumination uniformity, but also improves the performance stability, improves the reliability and optical performance of the LED packaging, and ensures the stability and efficiency of the backlight source in long-term use. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic flow chart of a backlight source packaging process optimization control method provided by the present invention;

[0016] Figure 2 A schematic structural diagram of a backlight source packaging process optimization control system provided by the present invention.

[0017] Reference numerals: fixed parameter configuration module 11 , fixed simulation module 12 , impact analysis module 13 , optimization control module 14 . DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a backlight packaging process optimization control method, the method specifically includes the following steps:

[0022] S100: randomly configuring LED fixing parameters for fixing the LED chip during the backlight source packaging process, wherein the LED fixing parameters include a fixing position, a glue dispensing position, and a glue dispensing amount;

[0023] In the embodiment of the present application, the backlight source packaging process includes the fixation of the LED chip. The embodiment of the present application optimizes the fixing parameters of the LED chip in the packaging process to optimize the backlight source packaging process.

[0024] First, the LED fixing parameters for fixing the LED chip are randomly configured, including the fixing position, glue dispensing position and glue dispensing amount. These parameters determine the installation stability of the LED chip, the quality of the welding wire connection and the final optical performance.

[0025] Step S100 in the method provided in the embodiment of the present application includes:

[0026] Obtain the fixed position interval, dispensing position interval and dispensing amount interval of the LED chip, and traverse and combine the three types of parameters to obtain the LED fixed parameter interval;

[0027] In the LED fixed parameter interval, LED fixed parameters are obtained by random configuration.

[0028] In an embodiment of the present application, a fixed position interval, a dispensing position interval, and a dispensing amount interval of the LED chip are obtained. The backlight source package may involve the fixation of multiple LED chips, and each LED chip has corresponding fixed coordinates. In an embodiment of the present application, fixed parameters are optimized for each LED chip, wherein the fixed parameter optimization of a single LED chip is taken as an example for explanation.

[0029] For example, the ideal fixed coordinates of the LED chip on the substrate of the backlight source are (x, y). When fixing it, the robot arm moves it according to the set (x, y) coordinates and fixes it by dispensing glue. However, due to control errors, the actual fixed position coordinates may differ from the ideal fixed coordinates, resulting in positional offset of the LED chip. In addition, the positional error of dispensing glue and the error of the amount of dispensing glue may also affect the fixation of the LED chip. For example, the deviation between the dispensing position and the fixed position may cause the LED chip to tilt and shift. Therefore, the fixing position, dispensing position and dispensing amount are optimized.

[0030] Get the fixed position interval, dispensing position interval and dispensing amount interval of the LED chip, including the fixed position coordinate parameters that can be set, all dispensing position coordinate parameters that control the dispensing robot to adjust the dispensing position, and the dispensing amount parameters that can be set. For example, the dispensing amount interval is [0.9mg, 1.5mg]. For example, the fixed position interval and the dispensing position interval are (x+10, x-10)*(y+10, y-10). 10 is the distance between the fixed position and the dispensing position, for example, 10μm.

[0031] Then, the fixed positions, dispensing positions and dispensing amounts in the fixed position interval, dispensing position interval and dispensing amount interval are traversed and combined to form a complete LED fixed parameter interval. The purpose of the traversal combination is to construct all possible LED fixed parameter configurations and evaluate the impact of different configurations on packaging quality. For example, all possible fixed positions, dispensing positions and dispensing amounts are selected and traversed one by one to obtain all possible LED fixed parameters and construct LED fixed parameter intervals.

[0032] Furthermore, within the LED fixed parameter interval, LED fixed parameters are randomly selected as randomly configured LED fixed parameters and used as initial solutions in optimizing the LED fixed parameters for subsequent fixed simulation and impact analysis.

[0033] The embodiment of the present application constructs a complete LED fixed parameter interval by acquiring the fixed position interval, the dispensing position interval and the dispensing amount interval, and uses the traversal combination + random configuration method to find the optimal packaging parameter combination. Through this method, the LED chip fixing accuracy can be accurately controlled, the reliability can be improved, the illumination uniformity of the backlight source can be optimized, and finally the packaging quality and production yield can be improved.

[0034] S200: performing LED chip fixing simulation according to the LED fixing parameters to obtain the LED chip offset angle, actual fixing position and dispensing thickness;

[0035] In an embodiment of the present application, during the backlight source packaging process, in order to optimize the fixing accuracy of the LED chip and improve the packaging consistency and reliability, it is necessary to perform LED chip fixing simulation based on the LED fixing parameters to accurately predict the offset angle, actual fixing position and glue dispensing thickness of the LED chip, thereby optimizing the packaging process.

[0036] Among them, when following the LED fixing parameters, due to errors such as mechanical structure control, the actual fixing position, glue dispensing position and glue dispensing amount may be different from the settings, which may lead to tilt offset and position offset of the LED chip. Therefore, it is necessary to simulate the LED chip fixing based on machine learning according to the LED chip fixing data in the historical time to analyze the specific parameters after the LED chip is fixed according to the current LED fixing parameters, including the LED chip offset angle, actual fixing position and glue dispensing thickness of the LED chip after actual fixing. The LED chip offset angle is the tilt angle of the LED chip after fixing, which is generally caused by the deviation between the actual fixing position and the actual glue dispensing position and the error of glue dispensing amount.

[0037] Through the above content, the errors in the packaging process can be effectively quantified, and optimization adjustment strategies can be provided to improve the stability of the packaging process.

[0038] Step S200 in the method provided in the embodiment of the present application includes:

[0039] According to the data recorded at the backlight packaging station, a set of sample LED fixed parameters is collected, and the offset angle, actual fixed position and dispensing thickness of the LED chip under different sample LED fixed parameters are collected and marked to obtain a set of sample LED chip offset angles, a set of sample actual fixed positions and a set of sample dispensing thicknesses;

[0040] Using machine learning, an LED chip fixing simulator is constructed according to the sample LED fixing parameter set, the sample LED chip offset angle set, the sample actual fixing position set and the sample dispensing thickness set;

[0041] The LED fixing parameters are input into the LED chip fixing simulator, and the LED chip offset angle, actual fixing position and dispensing thickness are obtained as output.

[0042] In the embodiment of the present application, according to the production record data of the backlight source packaging station during the backlight source packaging production process, the sample LED fixed parameters of the LED chip at the current position when it was previously packaged and fixed are retrieved to obtain a set of sample LED fixed parameters. Each sample LED fixed parameter includes a sample fixed position, a sample dispensing position, and a sample dispensing amount.

[0043] Also, collect the tilt offset angle of the LED chip after fixation, the coordinates of the actual fixed position and the average thickness of the glue after fixation, and mark them as a set of sample LED chip offset angles, a set of sample actual fixed positions and a set of sample glue thicknesses. Among them, the LED chip should ideally be parallel to the substrate. When the LED chip is tilted, the tilt offset angle is, for example, 15°. The glue thickness can be measured by the equipment after the glue fixation is completed. For example, the sample glue thickness is 270μm, 290μm, 260μm, etc.

[0044] Furthermore, machine learning is adopted to construct and train an LED chip fixing simulator with a set of sample LED fixed parameters, a set of sample LED chip offset angles, a set of sample actual fixed positions and a set of sample glue dispensing thicknesses as machine learning training data. The trained LED chip fixing simulator can simulate and predict the LED chip offset angle, actual fixed position and glue dispensing thickness after the LED chip is fixed according to the LED fixing parameters.

[0045] After the LED chip fixing simulator training is completed, the currently configured LED fixing parameters are input into the LED chip fixing simulator, and the LED chip offset angle, actual fixing position and dispensing thickness of the LED chip to be simulated and fixed are obtained as output.

[0046] In the embodiment of the present application, machine learning is used to construct an LED chip fixing simulator according to the sample LED fixing parameter set, the sample LED chip offset angle set and the sample actual fixing position set, including:

[0047] Divide the sample LED fixed parameter set, the sample LED chip offset angle set, the sample actual fixed position set and the sample dispensing thickness set to obtain angle training data, angle verification data, angle test data, position training data, position verification data, position test data, thickness training data, thickness verification data and thickness test data;

[0048] Use machine learning to build chip offset angle simulation path, chip position simulation path, and dispensing thickness simulation path;

[0049] The chip offset angle simulation path, chip position simulation path and glue dispensing thickness simulation path are supervisedly trained, verified and tested using training data, verification data and test data. After the convergence conditions are met, a completed LED chip fixing simulator is obtained by combining them.

[0050] In the embodiment of the present application, the sample LED fixed parameter set, the sample LED chip offset angle set, the sample actual fixed position set and the sample dispensing thickness set are respectively combined, wherein the sample LED fixed parameter set is used as the input feature, and the LED chip offset angle set, the sample actual fixed position set and the sample dispensing thickness set are used as the three output features. The input feature and the three output features are respectively combined to obtain three types of construction data, specifically angle construction data, position construction data and thickness construction data. They are respectively used for the training of subsequent chip offset angle simulation path, chip position simulation path and dispensing thickness simulation path, so as to simulate and predict the LED chip offset angle, actual fixed position and dispensing thickness after the LED chip is fixed according to the LED fixed parameters.

[0051] Furthermore, the combined angle construction data, position construction data and thickness construction data are divided, for example, in a ratio of 7:2:1, to obtain angle training data, angle verification data, angle test data, position training data, position verification data, position test data, thickness training data, thickness verification data, and thickness test data, which are respectively used for training, verification and testing of chip offset angle simulation path, chip position simulation path and glue dispensing thickness simulation path to ensure the accuracy and robustness of the three paths.

[0052] Furthermore, machine learning is used to construct chip offset angle simulation path, chip position simulation path and dispensing thickness simulation path. Exemplarily, a neural network model in machine learning is used to construct three simulation paths respectively. The input feature of the chip offset angle simulation path is the LED fixed parameter, and the output feature is the offset angle θ of the LED chip. The input feature of the chip position simulation path is the LED fixed parameter, and the output feature is the actual fixed position (Xr, Yr). The input feature of the dispensing thickness simulation path is the LED fixed parameter, and the output feature is the dispensing thickness hr.

[0053] Taking the training process of the chip offset angle simulation path as an example, the training steps of the three paths are described. First, the chip offset angle simulation path is constructed, which includes an input layer, a hidden layer, and an output layer. The input feature dimension is 3, which are the fixed position coordinates, the dispensing position coordinates, and the dispensing amount. The output feature dimension is 1, which is the chip offset angle θ (unit: °). The hidden layer includes three layers, all of which use the ReLU activation function, and the output layer activation function is a linear activation function. During the training process, the mean square error is used as the loss function, and the Adam optimizer is used to update the gradient of the path network parameters. The sample LED fixed parameters in the angle training data are input to obtain the output LED chip offset angle, and the error is calculated with the corresponding real sample LED chip offset angle. Then, the path network parameters such as weights are updated and adjusted according to the error to reduce the error. After multiple rounds of training, when the error is less than the requirement, for example, the error is less than 0.5°, the angle verification data and angle test data are used for verification and testing. If the error is still less than 0.5°, the convergence condition is met and the training is completed. If the error is greater than 0.5°, iterative training continues until the verification test meets the requirements. In this way, the construction of the chip offset angle simulation path is completed.

[0054] Based on the same steps, the position training data, position verification data, position test data, thickness training data, thickness verification data, and thickness test data are used to train the chip position simulation path and the glue dispensing thickness simulation path to obtain the trained chip offset angle simulation path, chip position simulation path, and glue dispensing thickness simulation path. The chip offset angle simulation path, chip position simulation path, and glue dispensing thickness simulation path are combined to obtain a constructed LED chip fixing simulator.

[0055] Based on the above steps, the embodiment of the present application constructs an LED chip fixing simulator through data collection, machine learning modeling, supervised training, and optimization testing, which can quickly predict the package fixing deviation, quantify the package fixing error, and then optimize the LED chip fixing parameters.

[0056] S300: performing a lighting influence calculation according to the LED chip offset angle to obtain a lighting influence coefficient, and performing a welding wire influence calculation according to the actual fixing position and the glue dispensing thickness to obtain a welding wire influence coefficient;

[0057] In the embodiment of the present application, during the backlight packaging process, the offset angle, actual fixed position and glue thickness of the LED chip will directly affect the optical performance of the backlight and the quality of the welding wire connection. For example, the tilt offset of the LED chip will cause uneven LED light emission. When the actual fixed position of the LED chip changes and the glue thickness increases, the distance between the LED chip and the substrate solder joint may increase, thereby increasing the stress on the welding wire and reducing the life of the welding wire, thereby affecting the life of the backlight source. In order to optimize the packaging process, it is necessary to calculate the illumination influence coefficient and the welding wire influence coefficient respectively to quantify the influence of the fixed deviation of the LED chip on the illumination uniformity and welding wire stress, so as to quantify the influence on the backlight performance.

[0058] Step S300 in the method provided in the embodiment of the present application includes:

[0059] Get the preset illumination angle of the LED chip;

[0060] The illumination influence coefficient is calculated based on the LED chip offset angle and the preset illumination angle.

[0061] In the embodiment of the present application, during the backlight packaging process, the illumination angle of the LED chip is an important parameter that affects the optical performance. The illumination angle refers to the angle of the optical axis direction of the LED chip, which affects the uniformity of light illumination and the overall brightness distribution of the backlight. Due to packaging errors, the LED chip may tilt, causing the optical axis to shift, thereby affecting the consistency of illumination. Therefore, it is necessary to calculate the illumination impact coefficient to quantify the impact of the LED chip offset angle on illumination.

[0062] First, the preset illumination angle of the LED chip is obtained. The preset illumination angle of the LED chip is the angle between the optical axis of the LED chip and the substrate under ideal conditions, specifically the direction perpendicular to the substrate, that is, the angle is 90°.

[0063] Further, according to the LED chip offset angle and the preset illumination angle, the illumination influence coefficient is calculated, for example, the ratio of the LED chip offset angle to the preset illumination angle is calculated as the illumination influence coefficient, for example, the LED chip offset angle is 15°, and the ratio to the preset illumination angle of 90° is 0.167, which is used as the illumination influence coefficient to affect the accuracy of the illumination direction and the amplitude of the illumination uniformity. Among them, the larger the LED chip offset angle, the larger the illumination influence coefficient.

[0064] Step S300 in the method provided in the embodiment of the present application also includes:

[0065] Get the preset wire length of the LED chip;

[0066] According to the actual fixed position and the dispensing thickness, the actual welding wire distance is calculated as follows:

[0067]

[0068] Among them, x j and j are the x-axis coordinate value and y-axis coordinate value of the fixed coordinate of the welding wire on the substrate, x r and r are the x-axis and y-axis coordinate values ​​of the actual fixed position, h s is the preset dispensing thickness, h r is the dispensing thickness;

[0069] The deviation between the actual welding wire distance and the preset welding wire length is calculated as the welding wire influence coefficient.

[0070] In the embodiment of the present application, the preset wire length of the wire for welding the LED chip to the substrate after the LED chip is fixed is first obtained. The preset wire length L 0 It is the length of the welding wire between the LED chip electrode and the substrate welding point under the ideal packaging state. In the case of no offset and no fixed position error, the starting point and end point of the welding wire connection are fixed, and the welding wire has the best curvature to ensure the stability of the electrical connection. For example, the preset welding wire length L 0 is 2mm.

[0071] Furthermore, the distance between the LED chip and the soldering point of the substrate after the LED chip is actually fixed is calculated according to the actual fixing position and the dispensing thickness, that is, the actual solder wire distance, as shown in the following formula:

[0072]

[0073] Among them, x j and j is the x-axis coordinate value and y-axis coordinate value of the fixed coordinate of the welding wire on the substrate, that is, the welding position coordinate on the substrate, which is determined by the design position of the welding pad. r and r are the x-axis and y-axis coordinate values ​​of the actual fixed position, h s is the preset dispensing thickness, i.e. the standard dispensing thickness, such as 250μm, h r The actual glue dispensing thickness predicted by the current simulation. When the glue dispensing thickness is greater than the preset glue dispensing thickness, the LED chip will become higher, thereby increasing the distance between the LED chip and the connection fixing position of the welding wire on the substrate.

[0074] The actual wire distance is calculated through the three-dimensional Euclidean distance. In the formula, the first term reflects the wire offset in the X-axis direction, the second term reflects the wire offset in the Y-axis direction, and the third term reflects the change in the wire distance in the height direction. In this way, the actual distance of the welding connection after the LED chip is fixed and welded according to the current LED fixed parameters can be calculated. The closer the actual wire distance is to the preset wire length, the better the wire performance is. The larger the gap is, the greater the stress on the wire is, and it may be damaged prematurely during use, affecting the electrical performance and thus the quality of the backlight source.

[0075] Further, the deviation between the actual welding wire distance and the preset welding wire length is calculated as the welding wire influence coefficient. For example, the absolute value of the difference between the actual welding wire distance and the preset welding wire length is calculated, and then the ratio of the absolute value to the preset welding wire length is calculated as the welding wire influence coefficient. For example, if the preset welding wire length is 2 mm and the actual welding wire distance is 2.2 mm, the welding wire influence parameter is 0.2 / 2=0.1.

[0076] The embodiment of the present application calculates the actual required welding wire distance after fixation and compares it with the preset welding wire length to quantify the stress condition of the welding wire, which can be used for welding wire reliability analysis to ensure that the welding wire is evenly stressed during the packaging process in the subsequent optimization of packaging fixing parameters, reduce welding failures, and improve the long-term stability of LED backlight products.

[0077] S400: Calculate and obtain the packaging score of the LED fixed parameters according to the illumination influence coefficient and the welding wire influence coefficient, optimize and adjust the LED fixed parameters, obtain the optimal LED fixed parameters, and perform backlight source packaging control.

[0078] In the embodiment of the present application, the packaging score of the currently configured LED fixed parameters is quantitatively calculated based on the quantified illumination influence coefficient and welding wire influence coefficient that affect the backlight LED illumination and the electrical performance of the welding wire.

[0079] Then, based on the same steps as in the above content, continue to optimize and adjust the LED fixed parameters, and finally obtain the optimal LED fixed parameters with the least impact on the backlight LED illumination and the electrical performance of the welding wire, and perform backlight packaging control.

[0080] Step S400 in the method provided in the embodiment of the present application includes:

[0081] Calculate the light source performance influence coefficient according to the illumination influence coefficient and the welding wire influence coefficient;

[0082] According to the light source performance influence coefficient, a packaging score of the LED fixed parameters is calculated, wherein the size of the packaging score is negatively correlated with the size of the light source performance influence coefficient;

[0083] Continue to randomly adjust and configure the LED fixed parameters, process and obtain the package score, optimize the LED fixed parameters until convergence, output the LED fixed parameters with the largest package score, and obtain the optimal LED fixed parameters;

[0084] The optimal LED fixing parameters are used to fix the LED chip and control the backlight source packaging.

[0085] In the embodiment of the present application, during the LED backlight packaging process, the fixing accuracy of the LED chip directly affects its optical performance and the stability of the welding wire connection. To ensure the packaging quality, it is necessary to calculate the light source performance influence coefficient based on the illumination influence coefficient and the welding wire influence coefficient, and calculate the packaging score of the LED fixed parameters accordingly. Furthermore, by randomly adjusting the LED fixed parameters and iteratively optimizing the packaging quality, the optimal LED fixed parameters are finally obtained and applied to the backlight packaging control.

[0086] For example, according to the illumination influence coefficient and the welding wire influence coefficient, the comprehensive performance influence degree of the two dimensions on the backlight source, that is, the light source performance influence coefficient, is calculated. For example, the average of the illumination influence coefficient and the welding wire influence coefficient is calculated as the light source performance influence coefficient.

[0087] Optionally, the illumination influence coefficient and the welding wire influence coefficient can also be weighted to obtain the light source performance influence coefficient. Among them, the illumination influence coefficient has a larger weight. For example, CP = w1CL + w2CW, CP is the light source performance influence coefficient, CL is the illumination influence coefficient, CW is the welding wire influence coefficient, w1 and w2 are weights, which are 0.6 and 0.4 respectively.

[0088] Furthermore, according to the light source performance influence coefficient, the packaging score of the LED fixed parameters is calculated, and the size of the packaging score is negatively correlated with the size of the light source performance influence coefficient. Exemplarily, 1-light source performance influence coefficient is used to obtain the packaging score. The larger the light source performance influence coefficient, the greater the impact on the backlight source performance, and the smaller the packaging score.

[0089] Furthermore, other LED fixed parameters are adjusted and configured randomly, and the package fixation simulation and calculation are performed through the aforementioned steps to obtain the package score, and the LED fixed parameters are iteratively optimized until convergence. For example, 100 LED fixed parameters are randomly configured and 200 package scores are calculated, and the optimization converges. Finally, the LED fixed parameters with the largest package score (i.e., the smallest light source performance impact coefficient) are output, and the optimal LED fixed parameters are obtained to ensure the package fixation quality of the backlight source.

[0090] The embodiment of the present application calculates the light source performance influence coefficient, quantifies the impact of LED fixing error on lighting and welding wire quality, and then calculates the packaging score, and performs optimization and adjustment based on the packaging score, ultimately reducing lighting offset and abnormal welding wire stress, ensuring the LED chip fixing accuracy, and improving the optical uniformity and long-term reliability of LED backlight products.

[0091] The embodiment of the present invention provides a backlight packaging process optimization control method, which has at least the following technical effects:

[0092] The embodiment of the present invention realizes accurate simulation of LED chip fixation by randomly configuring LED chip fixed parameters, including fixed position, glue dispensing position and glue dispensing amount, combined with machine learning modeling, to obtain the offset angle, actual fixed position and glue dispensing thickness of the LED chip, and then performs illumination influence analysis and welding wire influence analysis to quantify the influence on the performance of the LED backlight source and optimize the packaging fixed parameters. The present invention can dynamically evaluate the illumination influence and welding wire influence during the packaging process, and quantify the influence of LED chip fixed parameters on the packaging quality by calculating the illumination influence coefficient and welding wire influence coefficient. In addition, through packaging score calculation and parameter optimization adjustment, this scheme can iteratively obtain the optimal LED fixed parameters, make the LED chip fixation more accurate, reduce packaging deviation, and improve packaging consistency. Finally, the optimized backlight source packaging process not only improves the illumination uniformity, but also improves the performance stability, improves the reliability and optical performance of LED packaging, and ensures the stability and efficiency of the backlight source in long-term use.

[0093] Embodiment 2, as Figure 2 As shown, the invention concept is the same as that of the packaging process optimization control method of a backlight source in the first embodiment. The embodiment of the present invention further provides a packaging process optimization control system for a backlight source. The explanation of the packaging process optimization control method of the backlight source in the first embodiment is also applicable to a packaging process optimization control system for a backlight source, which includes:

[0094] A fixed parameter configuration module 11, used for randomly configuring LED fixed parameters of LED chips during backlight packaging, wherein the LED fixed parameters include a fixed position, a dispensing position and a dispensing amount;

[0095] A fixing simulation module 12, used to perform LED chip fixing simulation according to the LED fixing parameters, and obtain the LED chip offset angle, actual fixing position and dispensing thickness;

[0096] The impact analysis module 13 is used to calculate the illumination impact according to the LED chip offset angle to obtain the illumination impact coefficient, and to calculate the welding wire impact according to the actual fixing position and the glue dispensing thickness to obtain the welding wire impact coefficient;

[0097] An optimization control module 14 is configured to calculate a packaging score of the LED fixed parameters based on the light influence coefficient and the wire influence coefficient, optimize and adjust the LED fixed parameters, obtain the optimal LED fixed parameters, and perform backlight packaging control.

[0098] Further, the fixed parameter configuration module 11 is further configured to:

[0099] Obtain the fixed position interval, the dispensing position interval, and the dispensing amount interval of the LED chip fixation, and traverse and combine the three types of parameters to obtain the LED fixed parameter interval;

[0100] Randomly configure the LED fixed parameters within the LED fixed parameter interval.

[0101] Further, the fixed simulation module 12 is further configured to:

[0102] According to the data recorded at the backlight packaging station, collect the sample LED fixed parameter set, and collect the offset angle, the actual fixed position, and the dispensing thickness of the LED chip under different sample LED fixed parameters, and perform labeling to obtain the sample LED chip offset angle set, the sample actual fixed position set, and the sample dispensing thickness set;

[0103] Adopt machine learning to construct an LED chip fixation simulator according to the sample LED fixed parameter set, the sample LED chip offset angle set, the sample actual fixed position set, and the sample dispensing thickness set;

[0104] Input the LED fixed parameters into the LED chip fixation simulator, and output the obtained LED chip offset angle, actual fixed position, and dispensing thickness.

[0105] Among them, adopting machine learning to construct an LED chip fixation simulator according to the sample LED fixed parameter set, the sample LED chip offset angle set, and the sample actual fixed position set includes:

[0106] Divide the sample LED fixed parameter set, the sample LED chip offset angle set, the sample actual fixed position set, and the sample dispensing thickness set to obtain angle training data, angle verification data, angle test data, position training data, position verification data, position test data, thickness training data, thickness verification data, and thickness test data;

[0107] Adopt machine learning to construct a chip offset angle simulation path, a chip position simulation path, and a dispensing thickness simulation path;

[0108] The chip offset angle simulation path, chip position simulation path and glue dispensing thickness simulation path are supervisedly trained, verified and tested using training data, verification data and test data. After the convergence conditions are met, a completed LED chip fixing simulator is obtained by combining them.

[0109] Furthermore, the impact analysis module 13 is also used for:

[0110] Get the preset illumination angle of the LED chip;

[0111] The illumination influence coefficient is calculated based on the LED chip offset angle and the preset illumination angle.

[0112] Furthermore, the impact analysis module 13 is also used for:

[0113] Get the preset wire length of the LED chip;

[0114] According to the actual fixed position and the dispensing thickness, the actual welding wire distance is calculated as follows:

[0115]

[0116] Among them, x j and j are the x-axis coordinate value and y-axis coordinate value of the fixed coordinate of the welding wire on the substrate, x r and r are the x-axis and y-axis coordinate values ​​of the actual fixed position, h s is the preset dispensing thickness, h r is the dispensing thickness;

[0117] The deviation between the actual welding wire distance and the preset welding wire length is calculated as the welding wire influence coefficient.

[0118] Furthermore, the optimization control module 14 is also used for:

[0119] Calculate the light source performance influence coefficient according to the illumination influence coefficient and the welding wire influence coefficient;

[0120] According to the light source performance influence coefficient, a packaging score of the LED fixed parameters is calculated, wherein the size of the packaging score is negatively correlated with the size of the light source performance influence coefficient;

[0121] Continue to randomly adjust and configure the LED fixed parameters, process and obtain the package score, optimize the LED fixed parameters until convergence, output the LED fixed parameters with the largest package score, and obtain the optimal LED fixed parameters;

[0122] The optimal LED fixing parameters are used to fix the LED chip and control the backlight source packaging.

[0123] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to the flow diagrams and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flow diagram and / or block diagram, as well as the combination of flows and / or blocks in the flow diagram and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the flow diagram and / or block diagram. Figure 1 flow or flows and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the flow Figure 1 flow or flows and / or boxes Figure 1 A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the flow Figure 1 flow or flows and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0129] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A backlight packaging process optimization control method, characterized in that: The method comprises: Randomly configure LED fixed parameters for fixing the LED chip during the backlight source packaging process, wherein the LED fixed parameters include a fixed position, a glue dispensing position, and a glue dispensing amount; According to the LED fixing parameters, a LED chip fixing simulation is performed to obtain the LED chip offset angle, actual fixing position and dispensing thickness; Calculating the illumination influence according to the offset angle of the LED chip to obtain the illumination influence coefficient, and calculating the welding wire influence according to the actual fixing position and the glue dispensing thickness to obtain the welding wire influence coefficient; According to the illumination influence coefficient and the welding wire influence coefficient, the packaging score of the LED fixed parameters is calculated, the LED fixed parameters are optimized and adjusted, the optimal LED fixed parameters are obtained, and the backlight source packaging control is performed.

2. The backlight packaging process optimization control method according to claim 1, characterized in that: Randomly configure the LED fixed parameters of the LED chip during the backlight packaging process, including: Obtain the fixed position interval, dispensing position interval and dispensing amount interval of the LED chip, and traverse and combine the three types of parameters to obtain the LED fixed parameter interval; In the LED fixed parameter interval, LED fixed parameters are obtained by random configuration.

3. The backlight packaging process optimization control method according to claim 1, characterized in that: According to the LED fixing parameters, an LED chip fixing simulation is performed to obtain the LED chip offset angle, actual fixing position and dispensing thickness, including: According to the data recorded at the backlight packaging station, a set of sample LED fixed parameters is collected, and the offset angle, actual fixed position and dispensing thickness of the LED chip under different sample LED fixed parameters are collected and marked to obtain a set of sample LED chip offset angles, a set of sample actual fixed positions and a set of sample dispensing thicknesses; Using machine learning, an LED chip fixing simulator is constructed according to the sample LED fixing parameter set, the sample LED chip offset angle set, the sample actual fixing position set and the sample dispensing thickness set; The LED fixing parameters are input into the LED chip fixing simulator, and the LED chip offset angle, actual fixing position and dispensing thickness are obtained as output.

4. The backlight packaging process optimization control method according to claim 3, characterized in that: By adopting machine learning, an LED chip fixing simulator is constructed according to the sample LED fixing parameter set, the sample LED chip offset angle set and the sample actual fixing position set, including: Divide the sample LED fixed parameter set, the sample LED chip offset angle set, the sample actual fixed position set and the sample dispensing thickness set to obtain angle training data, angle verification data, angle test data, position training data, position verification data, position test data, thickness training data, thickness verification data and thickness test data; Use machine learning to build chip offset angle simulation path, chip position simulation path, and dispensing thickness simulation path; The chip offset angle simulation path, chip position simulation path and glue dispensing thickness simulation path are supervisedly trained, verified and tested using training data, verification data and test data. After the convergence conditions are met, a completed LED chip fixing simulator is obtained by combining them.

5. The backlight packaging process optimization control method according to claim 1, characterized in that: The illumination impact calculation is performed according to the LED chip offset angle to obtain the illumination impact coefficient, including: Get the preset illumination angle of the LED chip; The illumination influence coefficient is calculated based on the LED chip offset angle and the preset illumination angle.

6. The backlight packaging process optimization control method according to claim 1, characterized in that: The influence of the welding wire is calculated according to the actual fixing position and the dispensing thickness to obtain the influence coefficient of the welding wire, including: Get the preset wire length of the LED chip; According to the actual fixed position and the dispensing thickness, the actual welding wire distance is calculated as follows: Among them, x j and j are the x-axis coordinate value and y-axis coordinate value of the fixed coordinate of the welding wire on the substrate, x r and r are the x-axis and y-axis coordinate values ​​of the actual fixed position, h s is the preset dispensing thickness, h r is the dispensing thickness; The deviation between the actual welding wire distance and the preset welding wire length is calculated as the welding wire influence coefficient.

7. The backlight packaging process optimization control method according to claim 1, characterized in that: According to the illumination influence coefficient and the welding wire influence coefficient, the packaging score of the LED fixed parameters is calculated, and the LED fixed parameters are optimized and adjusted to obtain the optimal LED fixed parameters, including: Calculate the light source performance influence coefficient according to the illumination influence coefficient and the welding wire influence coefficient; According to the light source performance influence coefficient, a packaging score of the LED fixed parameters is calculated, wherein the size of the packaging score is negatively correlated with the size of the light source performance influence coefficient; Continue to randomly adjust and configure the LED fixed parameters, process and obtain the package score, optimize the LED fixed parameters until convergence, output the LED fixed parameters with the largest package score, and obtain the optimal LED fixed parameters; The optimal LED fixing parameters are used to fix the LED chip and control the backlight source packaging.

8. A backlight packaging process optimization control system, characterized in that: The system comprises: A fixed parameter configuration module, used to randomly configure LED fixed parameters of LED chips during backlight packaging, wherein the LED fixed parameters include a fixed position, a dispensing position, and a dispensing amount; A fixing simulation module, used to perform LED chip fixing simulation according to the LED fixing parameters, and obtain the LED chip offset angle, actual fixing position and dispensing thickness; An impact analysis module, used to calculate the illumination impact according to the LED chip offset angle to obtain the illumination impact coefficient, and to calculate the welding wire impact according to the actual fixing position and the glue dispensing thickness to obtain the welding wire impact coefficient; The optimization control module is used to calculate the packaging score of the LED fixed parameters according to the illumination influence coefficient and the welding wire influence coefficient, optimize and adjust the LED fixed parameters, obtain the optimal LED fixed parameters, and perform backlight source packaging control.

Images