A quality inspection system for liquid crystal glass based on warpage deformation

Abstract

This invention discloses a liquid crystal glass quality inspection system based on warpage deformation, relating to the field of glass substrate processing technology. The system collects glass substrate size-related data through a data acquisition module, then preprocesses and labels the data using a data processing module, calculates the warpage curvature, and obtains the warpage curvature coefficient. A deformation analysis module then retrieves a set of warpage curvature values ​​stored in the control center. The warpage curvature coefficient is matched with the warpage curvature set, and the corresponding glass substrates are marked. The number of standard glass substrates is counted, and the batch's quality is determined based on a set standard. Based on the inspection result, a corresponding signal is sent to the execution module for alarm notification. This system enables the calculation of warpage for a batch of glass substrates and the determination of their quality.

Description

Technical Field

[0001] This invention belongs to the field of glass substrate processing technology, and relates to a liquid crystal glass quality inspection system, specifically a liquid crystal glass quality inspection system based on warpage deformation. Background Technology

[0002] The detection of glass substrate warpage is an essential part of monitoring product warpage quality. Poor warpage quality can lead to multiple defects at the user end, resulting in significant economic losses. Therefore, performing warpage and dimensional verification checks on the glass substrate during the LCD glass substrate production process is both necessary and crucial. Summary of the Invention

[0003] To address the shortcomings mentioned in the background art, the present invention aims to provide a liquid crystal glass quality inspection system based on warpage deformation, which can calculate the warpage of a batch of substrate glass and determine whether the quality of this batch of substrate glass is qualified.

[0004] Firstly, the objective of this invention can be achieved through the following technical solution: a liquid crystal glass quality inspection system based on warpage deformation, comprising:

[0005] Data acquisition module: used to acquire glass substrate size-related data and send the glass substrate size-related data to the data processing module. The glass substrate size-related data includes: glass substrate thickness, glass substrate maximum height and glass substrate minimum height.

[0006] Data processing module: used to preprocess the glass substrate size-related data, label the preprocessed glass substrate size-related data, calculate the warpage bending degree using the labeled glass substrate size-related data, obtain the warpage bending coefficient, and send the warpage bending coefficient to the deformation analysis module.

[0007] Deformation Analysis Module: This module acquires the warp curvature set stored in the control center, matches the received warp curvature coefficient with the warp curvature set, determines the degree of warp curvature of the glass substrate based on the matching result, and marks the corresponding glass substrates. The marking categories include: glass substrates with too little warp, glass substrates with too much warp, and standard glass substrates. The module counts the number of standard glass substrates, glass substrates with too little warp, and glass substrates with too much warp, and sets a quantity standard to determine whether this batch of glass substrates is qualified. If qualified, a qualified test result signal is sent to the execution module; if unqualified, an unqualified test result signal is sent to the execution module.

[0008] Control Center: Used to acquire and store sets of warp curvature.

[0009] Execution module: Used to alert the batch of glass substrates to be qualified upon receiving a qualified test result signal, and to alert the batch of glass substrates to be unqualified upon receiving a unqualified test result signal.

[0010] In conjunction with the first aspect, in some implementations of the first aspect, the system further includes: the data identification process of the data processing module includes: marking the thickness of the glass substrate as Ti, marking the height of the highest point of the glass substrate as Lgi, and marking the height of the lowest point of the glass substrate as Ldi, where i is the number of times the glass substrate size-related data is collected by the data acquisition module, and i = 1, 2, 3, ..., n, where n is the total number of times the glass substrate size-related data is collected by the data acquisition module.

[0011] In conjunction with the first aspect, in some implementations of the first aspect, the system further includes: the calculation formula for the warpage curvature of the data processing module is as follows:

[0012]

[0013] In the formula, Qqi is the warping coefficient, k1 is the influence coefficient of the highest point height of the glass substrate, k2 is the influence coefficient of the lowest point height of the glass substrate, k3 is the influence coefficient of the thickness of the glass substrate, K is the measurement correlation coefficient, and exp() represents an exponential function with the natural constant e as the base.

[0014] In conjunction with the first aspect, in some implementations of the first aspect, the system further includes: the analysis process of the deformation analysis module:

[0015] Obtain the warp curvature set {Qq0} stored in the control center, wherein the minimum value in the warp curvature set is Qqmin, and the maximum value in the warp curvature set is Qqmax;

[0016] If Qqi < Qqmin, then the glass substrate corresponding to the warp bending coefficient is marked as a glass substrate with too little warp.

[0017] If Qqi > Qqmax, then the glass substrate corresponding to the warp bending coefficient is marked as a glass substrate with excessive warp.

[0018] If Qqmin≤Qqi≤Qqmin, then the glass substrate corresponding to the warpage coefficient is marked as a standard glass substrate.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the system further includes: the determination process of the deformation analysis module:

[0020] The number of standard glass substrates, the number of glass substrates with insufficient warping, and the number of glass substrates with excessive warping are counted and labeled as R1, R2, and R3, respectively. If R1≥2(R2+R3), the batch of glass substrates is judged to be qualified glass substrates, and the deformation analysis module sends the qualified test result signal to the execution module.

[0021] If R1 < 2(R2 + R3), then this batch of glass substrates is determined to be unqualified glass substrates, and the deformation analysis module sends the unqualified detection result signal to the execution module; where R1 + R2 + R3 = n.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the system further includes: the process of obtaining the set of warp curvature within the control center includes the following steps:

[0023] The glass substrate size data is collected using a server in the control center. The glass substrate size data includes glass substrate thickness data, glass substrate maximum height data, and glass substrate minimum height data.

[0024] By combining the standard warp bending determination model with the glass substrate size data in the video, warp bending degree determination coefficients are obtained. All obtained warp bending degree determination coefficients are integrated to generate a warp bending degree set. The standard warp bending determination model is based on artificial intelligence model training.

[0025] The beneficial effects of this invention are:

[0026] This invention collects glass substrate size-related data through a data acquisition module, then preprocesses and labels the data using a data processing module, calculates the warpage and curvature, and obtains the warpage and curvature coefficient. Next, a deformation analysis module retrieves the warpage and curvature set stored in the control center. The warpage and curvature coefficient are matched with the warpage and curvature set to identify the corresponding glass substrates, and the number of standard glass substrates is counted. Based on the set quantity standard, the quality of this batch of glass substrates is determined. Based on the quality test result, a corresponding signal is sent to the execution module for alarm notification. This invention enables the calculation of the warpage of a batch of glass substrates and the determination of the quality of this batch of glass substrates. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Example 1:

[0031] The following is a description of the relevant terms used in the embodiments of this application:

[0032] Warpage is a spatial measurement used to describe the degree of curvature of a plane in space.

[0033] Warpage (or warp) describes the degree of curvature of a plane in space. Numerically, it is defined as the distance between the two points furthest apart in the height direction of the warped plane. The warpage of an absolute plane is 0.

[0034] Warpage deformation is one of the important indicators for evaluating product quality. In existing evaluation systems, warpage deformation is evaluated using the amount of warpage, generally the maximum warpage deformation or the warpage deformation of a specific part. When using injection molding CAE for design quality prediction, the evaluation of warpage deformation simulation results is generally done directly using the maximum warpage deformation. Sometimes, statistical quantities such as the total average warpage deformation or the average warpage deformation of the 10% maximum warpage deformation nodes are also used as indicators for evaluating warpage deformation.

[0035] For the same product with the same warpage influence pattern, these indicators can describe the magnitude of warpage deformation under different designs. However, factors such as different materials and mold structures can alter the influence pattern of warpage deformation, thus changing the severity of warpage deformation in different designs. In such cases, using maximum warpage deformation or other relative statistical measures to evaluate warpage deformation has significant limitations and cannot adequately reflect user satisfaction with product warpage deformation under different designs. This is particularly true for LCD glass, where using maximum warpage deformation or other statistical measures to characterize the warpage deformation of the product presents significant limitations.

[0036] like Figure 1 As shown, a liquid crystal glass quality inspection system based on warpage deformation includes:

[0037] The system includes a data acquisition module, a data processing module, a deformation analysis module, a control center, and an execution module.

[0038] The data acquisition module is used to collect data related to the size of the glass substrate and send the collected data to the data processing module for processing. Specifically, the data related to the size of the glass substrate includes: the thickness of the glass substrate, the height of the highest point of the glass substrate, and the height of the lowest point of the glass substrate.

[0039] It should be noted that the height of the highest point of the glass substrate is the height of the highest point of the glass substrate from the horizontal plane, and the height of the lowest point of the glass substrate is the height of the lowest point of the glass substrate from the horizontal plane; the thickness of the glass substrate is measured by using vernier calipers, and the thickness of the glass substrate can be measured more accurately by clamping both ends of the glass substrate with the vernier calipers; the height of the highest point and the height of the lowest point of the glass substrate are measured by using a measuring tape.

[0040] After receiving the glass substrate size-related data sent by the data acquisition module, the data processing module performs data processing. Specifically, the data processing module's processing procedure includes the following steps:

[0041] Preprocessing is performed on the glass substrate size-related data, wherein the preprocessing mainly includes:

[0042] Data cleaning, data integration, data transformation, and data reduction are all techniques used before data mining. These data processing techniques significantly improve the quality of data mining patterns and reduce the time required for actual mining.

[0043] In this embodiment, data cleaning is mainly performed on glass substrate size-related data. The data cleaning routine "cleans" the data by filling in missing values, smoothing noisy data, identifying or deleting outliers, and resolving inconsistencies. The main objectives are: format standardization, removal of abnormal data, error correction, and removal of duplicate data.

[0044] The pre-processed glass substrate dimensional data are labeled, with the glass substrate thickness labeled as Ti, the highest point height of the glass substrate labeled as Lgi, and the lowest point height of the glass substrate labeled as Ldi. In the formula, i represents the number of times the glass substrate dimensional data was collected by the data acquisition module, and i = 1, 2, 3, ..., n, where n is the total number of times the glass substrate dimensional data was collected by the data acquisition module. It should be noted that n represents the total number of glass substrates to be inspected in this batch.

[0045] Using the dimensional data of the labeled glass substrate, the warpage is calculated to obtain the warpage coefficient. The calculation formula for the warpage in the data processing module is as follows:

[0046] Using formula

[0047] The warping coefficient Qqi was calculated.

[0048] In the formula, k1 is the influence coefficient of the highest point height of the glass substrate, k2 is the influence coefficient of the lowest point height of the glass substrate, k3 is the influence coefficient of the thickness of the glass substrate, K is the measurement correlation coefficient, and exp() represents an exponential function with the natural constant e as the base.

[0049] In this embodiment, the influence coefficients of the highest point height, the lowest point height, and the thickness of the glass substrate are calculated by comprehensively evaluating the influence of external factors when the thickness, the highest point height, and the lowest point height of the glass substrate are obtained routinely. These factors include human factors, machine inspection, and environmental factors. Human factors refer to those caused by improper human operation or scanning. The measurement correlation coefficient is obtained by analyzing relevant data from routine measurements, including those caused by errors in the glass substrate material and measurement accuracy.

[0050] The calculated warpage coefficient Qqi is sent to the deformation analysis module for analysis.

[0051] Obtain the warp curvature set {Qq0} stored in the control center, wherein the minimum value in the warp curvature set is Qqmin, and the maximum value in the warp curvature set is Qqmax;

[0052] The received warpage coefficient Qqi is matched with the warpage set {Qq0}, and the degree of warpage of the glass substrate is determined based on the matching result.

[0053] If Qqi < Qqmin, then it is determined that the degree of warpage is less than the minimum value in the stored set of warpage degrees, and the glass substrate corresponding to the corresponding warpage coefficient is marked as a glass substrate with too little warpage.

[0054] If Qqi > Qqmax, then it is determined that the degree of warping is greater than the maximum value in the stored set of warping degrees, and the glass substrate corresponding to the corresponding warping coefficient is marked as a glass substrate with excessive warping.

[0055] If Qqmin≤Qqi≤Qqmin, then it is determined that the degree of warping is within the set of warping degrees, and the glass substrate corresponding to the warping coefficient is marked as a standard glass substrate.

[0056] The number of standard glass substrates, the number of glass substrates with insufficient warping, and the number of glass substrates with excessive warping are counted and labeled as R1, R2, and R3, respectively. If R1≥2(R2+R3), the batch of glass substrates is judged to be qualified glass substrates, and the deformation analysis module sends the qualified test result signal to the execution module.

[0057] If R1 < 2(R2 + R3), then this batch of glass substrates is determined to be unqualified glass substrates, and the deformation analysis module sends the unqualified detection result signal to the execution module; where R1 + R2 + R3 = n;

[0058] The control center is used to acquire and store the warp curvature set {Qq0}, wherein the process of acquiring the warp curvature set includes the following steps:

[0059] The glass substrate size data is collected using a server in the control center. The glass substrate size data includes glass substrate thickness data, glass substrate maximum height data, and glass substrate minimum height data.

[0060] By combining the standard warp bending determination model with the glass substrate size data in the video, warp bending degree determination coefficients are obtained. All obtained warp bending degree determination coefficients are integrated to generate a warp bending degree set. The standard warp bending determination model is based on artificial intelligence model training.

[0061] The process of training a standard warp and bending determination model based on an artificial intelligence model:

[0062] The standard glass substrate size coefficient is obtained through the server, wherein the standard glass substrate size coefficient includes the standard glass substrate thickness coefficient, the standard glass substrate maximum height coefficient, and the standard glass substrate minimum height coefficient.

[0063] The artificial intelligence model is trained using standard glass substrate size factors to obtain and store a standard warping and bending determination model; wherein, the artificial intelligence model includes a deep convolutional neural network model and an RBF neural network model.

[0064] After receiving a qualified test result signal from the deformation analysis module, the execution module will issue an alarm indicating that the batch of glass substrates is qualified. After receiving a failed test result signal from the deformation analysis module, the execution module will issue an alarm indicating that the batch of glass substrates is unqualified.

[0065] Based on the same inventive concept, this invention also provides a computer device, comprising: one or more processors, and a memory for storing one or more computer programs; the programs include program instructions, and the processor executes the program instructions stored in the memory. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, used to implement one or more instructions, specifically for loading and executing one or more instructions stored in a computer storage medium to implement the above-described method.

[0066] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium having a computer program stored thereon, which executes the above method when executed by a processor. The storage medium can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: 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 thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0067] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0068] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0069] The foregoing has shown and described the basic principles, main features, and advantages of this disclosure. Those skilled in the art should understand that this disclosure is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of this disclosure. Various changes and modifications can be made to this disclosure without departing from its spirit and scope, and all such changes and modifications fall within the scope of this disclosure as claimed.

Claims

1. A liquid crystal glass quality inspection system based on warpage deformation, characterized in that, include: Data acquisition module: used to acquire glass substrate size-related data and send the glass substrate size-related data to the data processing module. The glass substrate size-related data includes: glass substrate thickness, glass substrate maximum height and glass substrate minimum height. Data processing module: used to preprocess the glass substrate size-related data, label the preprocessed glass substrate size-related data, calculate the warpage bending degree using the labeled glass substrate size-related data, obtain the warpage bending coefficient, and send the warpage bending coefficient to the deformation analysis module. The data identification process of the data processing module includes: marking the thickness of the glass substrate as Ti, marking the height of the highest point of the glass substrate as Lgi, and marking the height of the lowest point of the glass substrate as Ldi, where i is the number of times the glass substrate size-related data is collected by the data acquisition module, and i = 1, 2, 3, ..., n, where n is the total number of times the glass substrate size-related data is collected by the data acquisition module. The calculation formula for the warpage curvature of the data processing module is as follows: In the formula, Qqi is the warping coefficient, k1 is the influence coefficient of the highest point height of the glass substrate, k2 is the influence coefficient of the lowest point height of the glass substrate, k3 is the influence coefficient of the thickness of the glass substrate, K is the measurement correlation coefficient, and exp() represents an exponential function with the natural constant e as the base. Deformation Analysis Module: This module acquires the warp curvature set stored in the control center, matches the received warp curvature coefficient with the warp curvature set, determines the degree of warp curvature of the glass substrate based on the matching result, and marks the corresponding glass substrates. The marking categories include: glass substrates with too little warp, glass substrates with too much warp, and standard glass substrates. The module counts the number of standard glass substrates, glass substrates with too little warp, and glass substrates with too much warp, and sets a quantity standard to determine whether this batch of glass substrates is qualified. If qualified, a qualified test result signal is sent to the execution module; if unqualified, an unqualified test result signal is sent to the execution module. Control Center: Used to acquire and store sets of warp curvature. Execution module: Used to alert the batch of glass substrates to be qualified upon receiving a qualified test result signal, and to alert the batch of glass substrates to be unqualified upon receiving a unqualified test result signal.

2. The liquid crystal glass quality inspection system based on warpage deformation according to claim 1, characterized in that, The analysis process of the deformation analysis module is as follows: obtain the warp curvature set {Qq0} stored in the control center, wherein the minimum value in the warp curvature set is Qqmin, and the maximum value in the warp curvature set is Qqmax; If Qqi < Qqmin, then the glass substrate corresponding to the warp bending coefficient is marked as a glass substrate with too little warp. If Qqi > Qqmax, then the glass substrate corresponding to the warp bending coefficient is marked as a glass substrate with excessive warp. If Qqmin≤Qqi≤Qqmin, then the glass substrate corresponding to the warpage coefficient is marked as a standard glass substrate.

3. The liquid crystal glass quality inspection system based on warpage deformation according to claim 2, characterized in that, The determination process of the deformation analysis module is as follows: count the number of standard glass substrates, the number of glass substrates with too little warping, and the number of glass substrates with too much warping, and mark them as R1, R2, and R3 respectively. If R1≥2(R2+R3), then this batch of glass substrates is determined to be qualified glass substrates, and the deformation analysis module sends the qualified test result signal to the execution module. If R1 < 2(R2 + R3), then this batch of glass substrates is determined to be unqualified glass substrates, and the deformation analysis module sends the unqualified detection result signal to the execution module; where R1 + R2 + R3 = n.

4. The liquid crystal glass quality inspection system based on warpage deformation according to claim 1, characterized in that, The process of obtaining the warp curvature set in the control center includes the following steps: collecting glass substrate size data using a server in the control center, wherein the glass substrate size data includes glass substrate thickness data, glass substrate maximum height data, and glass substrate minimum height data. By combining the standard warp bending determination model with the glass substrate size data in the video, warp bending degree determination coefficients are obtained. All obtained warp bending degree determination coefficients are integrated to generate a warp bending degree set. The standard warp bending determination model is based on artificial intelligence model training.

Images