System for measuring warping thickness of liquid crystal glass substrate
Through the design of the warp thickness measurement system of the LCD glass substrate, the data acquisition, processing and analysis modules and combined with artificial intelligence models, the problem of insufficient measurement accuracy of the existing system is solved, the accuracy and reliability of the measurement are improved, and the economy is reduced. and security risks.
Patent Information
- Application Number
- CN202411222865.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-06
AI Technical Summary
The measurement accuracy and accuracy of the existing liquid crystal glass substrate warp thickness measurement system cannot be guaranteed, which affects product quality and production safety and leads to economic losses.
A liquid crystal glass substrate warpage thickness measurement system is designed, including a data acquisition module, a data processing module, a data analysis module and a display module. By collecting the probe motion trajectory data, data preprocessing, marking and comprehensive measurement trajectory determination calculation are carried out. Use artificial intelligence models to judge measurement accuracy and send normal or abnormal signals for display.
It realizes the determination of measurement accuracy based on measurement data and trajectory, prompts staff to measure results, improves the accuracy and reliability of measurement, and reduces economic losses and safety risks.
Smart Images

Figure CN119085569A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of glass substrate production and relates to a measurement system, in particular to a liquid crystal glass substrate warping thickness measurement system. Background Art
[0002] In the glass production process, after the float glass is formed from the molten glass in the tin bath, it enters the annealing kiln for annealing. The glass is cooled down in the annealing kiln for a long enough time through the annealing temperature range or at a slow speed, so as to reduce or eliminate the thermal stress generated in the glass as much as possible. During the annealing process, the glass often has a warping defect due to the large temperature difference between the upper and lower surfaces of the glass plate, or the large lateral temperature difference of the glass plate. The occurrence of glass warping defects not only affects the yield of the glass, but may also cause production safety accidents in the case of severe warping.
[0003] Liquid crystal glass inspection items and inspection methods are also being established and improved. Liquid crystal glass warpage thickness inspection is an important inspection item for monitoring product warpage quality and is essential. Poor quality of liquid crystal glass warpage can cause multiple defects on the user side, causing direct economic losses to the company, and thus may lose customers. The existing liquid crystal glass substrate warpage thickness measurement is carried out by measuring instruments, and the measurement precision and accuracy cannot be guaranteed. Summary of the invention
[0004] In order to solve the deficiencies mentioned in the above background technology, the purpose of the present invention is to provide a liquid crystal glass substrate warpage thickness measurement system, which can determine the measurement accuracy after measurement according to the measurement data and trajectory, and prompt it to the staff.
[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a liquid crystal glass substrate warpage thickness measurement system, comprising:
[0006] Data acquisition module: used to collect probe motion trajectory data and send the probe motion trajectory data to the data processing module, wherein the probe motion trajectory data includes: measurement point coordinate value, distance between the probe and the surface of the measured part, and thickness value of the measured part;
[0007] Data processing module: used for preprocessing the probe motion trajectory data, marking the preprocessed probe motion trajectory data to obtain the marked probe motion trajectory data, performing comprehensive measurement trajectory determination calculation using the marked probe motion trajectory data to obtain the comprehensive measurement trajectory determination coefficient, and sending the comprehensive measurement trajectory determination coefficient to the data analysis module;
[0008] Data analysis module: used to obtain the real-time motion trajectory of the probe, input the comprehensive measurement trajectory determination coefficient and the real-time motion trajectory of the probe into the pre-established motion trajectory accuracy model, obtain the trajectory accuracy matching result, set the trajectory accuracy threshold, compare the trajectory accuracy matching result with the trajectory accuracy threshold, and determine whether there is a problem with the measurement accuracy of the probe based on the comparison result. If there is no problem, a normal signal is sent to the display module, and if there is a problem, an abnormal signal is sent to the display module;
[0009] Display module: after receiving a normal display signal, obtain the measured value and display it, and prompt that the measured value is a normal result; after receiving an abnormal display signal, obtain the measured value and display it, and prompt that the measured value is an abnormal result.
[0010] In combination with the first aspect, in certain implementations of the first aspect, the system also includes: the preprocessing of the data processing module includes: performing data cleaning on the probe motion trajectory data, the data cleaning is achieved by filling in missing values, smoothing noise data, identifying or deleting outliers and resolving inconsistencies.
[0011] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a marking process of the data processing module:
[0012] The coordinate value of the measuring point is marked as Zi, the distance between the probe and the surface of the measured part is marked as Li, and the thickness value of the measured part is marked as Hi; wherein i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module.
[0013] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a comprehensive measurement trajectory determination calculation process of the data processing module:
[0014] Using the formula The comprehensive measurement trajectory determination coefficient Pgi is calculated;
[0015] Where L0 is the standard spacing coefficient, H0 is the standard part thickness coefficient, k1 is the spacing influence coefficient, k2 is the part thickness influence coefficient, Q is the coordinate conversion numerical coefficient, and exp() is an exponential function with a natural constant as the base.
[0016] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the data analysis module sets a trajectory accuracy threshold, compares the trajectory accuracy matching result with the trajectory accuracy threshold, and if the trajectory accuracy matching result exceeds the trajectory accuracy threshold, it is determined that there is no problem with the measurement accuracy of the probe at this time; the data analysis module sends a display normal signal to the display module;
[0017] If the trajectory accuracy matching result does not exceed the trajectory accuracy threshold, it is determined that there is a problem with the measurement accuracy of the probe at this time, and the data analysis module sends a display abnormality signal to the display module.
[0018] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the pre-established motion trajectory accuracy model of the data analysis module is based on artificial intelligence model training, wherein the process based on artificial intelligence model training is as follows:
[0019] The data acquisition unit in the data analysis module collects standard probe trajectory data and standard motion trajectory; wherein the standard probe trajectory data includes: standard measurement point coordinate data, standard probe and measured part surface distance data and standard measured part thickness data;
[0020] The standard probe trajectory data and the standard motion trajectory are combined to obtain a motion trajectory accuracy data set, which is input into the artificial intelligence model for training, and the motion trajectory accuracy model is output.
[0021] Beneficial effects of the present invention:
[0022] The present invention collects probe motion trajectory data through a data acquisition module, and uses a data processing module to perform comprehensive measurement trajectory determination calculation to obtain a comprehensive measurement trajectory determination coefficient, then uses a data analysis module to obtain the real-time motion trajectory of the probe, and inputs the real-time motion trajectory of the probe and the comprehensive measurement trajectory determination coefficient into a pre-established motion trajectory accuracy model, and determines whether there is a problem with the measurement accuracy of the probe at this time based on the result of trajectory accuracy matching compared with a set threshold, and then displays it through a display module, thereby realizing the function of determining the measurement accuracy after measurement based on the measurement data and trajectory, and prompting the staff. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0024] Figure 1 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION
[0025] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0026] Embodiment 1:
[0027] The following is an introduction to the relevant terms involved in the embodiments of the present application:
[0028] Warpage is the surface distortion of a plastic part that is not formed according to the designed shape. The warpage of a plastic part is caused by the uneven shrinkage of the formed plastic part. If the entire plastic part has a uniform shrinkage rate, the plastic part will not warp when deformed, but will only shrink in size; however, due to the interaction of many factors such as molecular chain / fiber orientation, mold cooling, plastic part design, mold design and molding conditions, it is a very complicated task to achieve low shrinkage or uniform shrinkage.
[0029] Warp is a polysemous word. It can refer to the degree of curvature of an object in space, and can also be used to metaphorically describe the distortion or deviation of something.
[0030] As a spatial measurement method, warpage is used to express the degree of curvature of a plane in space. It is defined as the distance between the two points on the warpage plane that are farthest apart in the height direction. The warpage of an absolute plane is 0. Warpage is one of the important indicators for evaluating product quality, and is usually evaluated by the maximum warpage or the warpage of a specific part. In injection molding CAE design, the evaluation of warpage simulation results is generally carried out directly using the maximum warpage, and sometimes statistics such as the total average warpage, the average warpage of the 10% maximum warpage nodes, etc. are used as indicators for evaluating warpage.
[0031] Convolutional Neural Networks (CNN) are a type of feedforward neural network that includes convolutional calculations and has a deep structure. It is one of the representative algorithms of deep learning. Convolutional neural networks have representation learning capabilities and can perform shift-invariant classification on input information according to their hierarchical structure. Therefore, they are also called "Shift-Invariant Artificial Neural Networks (SIANN)".
[0032] like Figure 1 As shown, a liquid crystal glass substrate warpage thickness measurement system comprises:
[0033] Data acquisition module, data processing module, data analysis module and display module;
[0034] The data acquisition module is used to collect the probe motion trajectory data, and send the collected probe motion trajectory data to the data processing module for processing, wherein the probe motion trajectory data includes: the coordinate value of the measuring point, the distance between the probe and the surface of the measured part, and the thickness value of the measured part;
[0035] After receiving the probe motion trajectory data sent by the data acquisition module, the data processing module performs data processing. Specifically, the processing process of the data processing module includes the following steps:
[0036] The probe motion trajectory data is preprocessed, and the preprocessing mainly includes:
[0037] Data cleaning, data integration, data transformation, data reduction, etc. These data processing technologies are used before data mining, which greatly improves the quality of data mining patterns and reduces the time required for actual mining.
[0038] In this embodiment, data cleaning is mainly performed on the probe motion trajectory 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 goals are to achieve the following: format standardization, abnormal data removal, error correction, and duplicate data removal.
[0039] The preprocessed probe motion trajectory data is marked to obtain the marked probe motion trajectory data, wherein the coordinate value of the measuring point is marked as Zi, the distance between the probe and the surface of the measured part is marked as Li, and the thickness value of the measured part is marked as Hi; wherein i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module;
[0040] The marked probe motion trajectory data is used to perform comprehensive measurement trajectory determination calculation to obtain a comprehensive measurement trajectory determination coefficient. Specifically, the calculation process of the comprehensive measurement trajectory determination calculation of the data processing module includes:
[0041] Using the formula The comprehensive measurement trajectory determination coefficient Pgi is calculated;
[0042] Wherein, L0 is the standard spacing coefficient, H0 is the standard part thickness coefficient, k1 is the spacing influence coefficient, k2 is the part thickness influence coefficient, Q is the coordinate conversion numerical coefficient, and exp() is an exponential function with a natural constant as the base;
[0043] Among them, in this embodiment, the spacing influence coefficient and the part thickness influence coefficient are obtained by the present application through daily acquisition of the spacing between the probe and the surface of the measured part and the thickness of the measured part, and a comprehensive evaluation is performed according to the influence of external factors, wherein the external factors include: human factors, machine detection and environmental factors, etc.; human factors are caused by human operation or improper scanning;
[0044] Furthermore, in the specific implementation process, the preset standard spacing coefficient and standard part thickness coefficient are obtained by multiple simulation calculations and data averages during the daily collection of spacing and thickness;
[0045] The data processing module sends the comprehensive measurement trajectory determination coefficient Pgi to the data analysis module;
[0046] After receiving the comprehensive measurement trajectory determination coefficient Pgi sent by the data processing module, the data analysis module performs data analysis. Specifically, the analysis process of the data analysis module includes the following steps:
[0047] Get the real-time motion trajectory of the probe;
[0048] The calculated comprehensive measurement trajectory determination coefficient Pgi is used to perform precision matching with the real-time motion trajectory of the probe. The measurement accuracy of the probe is determined based on the size of the trajectory accuracy matching result. The specific analysis process is as follows:
[0049] The comprehensive measurement trajectory determination coefficient Pgi and the real-time motion trajectory of the probe are input into the pre-established motion trajectory accuracy model, and the trajectory accuracy matching result is output;
[0050] A trajectory accuracy threshold is set, and the trajectory accuracy matching result is compared with the trajectory accuracy threshold. If the trajectory accuracy matching result exceeds the trajectory accuracy threshold, it is determined that there is no problem with the measurement accuracy of the probe at this time; the data analysis module sends a display normal signal to the display module;
[0051] If the trajectory accuracy matching result does not exceed the trajectory accuracy threshold, it is determined that there is a problem with the measurement accuracy of the probe at this time, and the data analysis module sends a display abnormality signal to the display module;
[0052] It should be noted that the present invention is further described below by way of examples:
[0053] The pre-established motion trajectory accuracy model is based on artificial intelligence model training, wherein the process based on artificial intelligence model training is as follows:
[0054] The data acquisition unit in the data analysis module collects standard probe trajectory data and standard motion trajectory; wherein the standard probe trajectory data includes: standard measurement point coordinate data, standard probe and measured part surface distance data and standard measured part thickness data;
[0055] The standard probe trajectory data and the standard motion trajectory are combined to obtain a motion trajectory accuracy data set, which is input into an artificial intelligence model for training, and a motion trajectory accuracy model is output, wherein the artificial intelligence model includes a deep convolutional neural network model and an RBF neural network model.
[0056] After receiving the display normal signal sent by the data analysis module, the display module obtains the measurement value and displays it, and prompts that the measurement value is a normal result. After receiving the display abnormal signal sent by the data analysis module, the display module obtains the measurement value and displays it, and prompts that the measurement value is an abnormal result.
[0057] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.
[0058] It needs to be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to execute the above method. The storage medium can adopt 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 device, or any combination of the above. More specific examples (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 of the above. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0059] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.
[0060] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0061] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.
Claims
1. A liquid crystal glass substrate warpage thickness measurement system, It is characterized in that include: Data acquisition module: used to collect probe motion trajectory data and send the probe motion trajectory data to the data processing module, wherein the probe motion trajectory data includes: measurement point coordinate value, distance between the probe and the surface of the measured part, and thickness value of the measured part; Data processing module: used for preprocessing the probe motion trajectory data, marking the preprocessed probe motion trajectory data to obtain the marked probe motion trajectory data, performing comprehensive measurement trajectory determination calculation using the marked probe motion trajectory data to obtain the comprehensive measurement trajectory determination coefficient, and sending the comprehensive measurement trajectory determination coefficient to the data analysis module; Data analysis module: used to obtain the real-time motion trajectory of the probe, input the comprehensive measurement trajectory determination coefficient and the real-time motion trajectory of the probe into the pre-established motion trajectory accuracy model, obtain the trajectory accuracy matching result, set the trajectory accuracy threshold, compare the trajectory accuracy matching result with the trajectory accuracy threshold, and determine whether there is a problem with the measurement accuracy of the probe based on the comparison result. If there is no problem, a normal signal is sent to the display module, and if there is a problem, an abnormal signal is sent to the display module; Display module: after receiving a normal display signal, obtain the measured value and display it, and prompt that the measured value is a normal result; after receiving an abnormal display signal, obtain the measured value and display it, and prompt that the measured value is an abnormal result.
2. A liquid crystal glass substrate warpage thickness measurement system according to claim 1, It is characterized in that The preprocessing of the data processing module includes: cleaning the probe motion trajectory data by filling in missing values, smoothing noise data, identifying or deleting outliers and resolving inconsistencies, thereby cleaning the data.
3. A liquid crystal glass substrate warpage thickness measurement system according to claim 2, It is characterized in that The marking process of the data processing module: The coordinate value of the measuring point is marked as Zi, the distance between the probe and the surface of the measured part is marked as Li, and the thickness value of the measured part is marked as Hi; wherein i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module.
4. A liquid crystal glass substrate warpage thickness measurement system according to claim 3, It is characterized in that The comprehensive measurement trajectory determination calculation process of the data processing module: Using the formula The comprehensive measurement trajectory determination coefficient Pgi is calculated; Where L0 is the standard spacing factor, H0 is the standard part thickness factor, k 1 is the spacing influence coefficient, k 2 is the influence coefficient of part thickness, Q is the numerical coefficient of coordinate transformation, and exp() is an exponential function with a natural constant as the base.
5. The liquid crystal glass substrate warpage thickness measurement system according to claim 1, It is characterized in that The data analysis module sets a trajectory accuracy threshold, compares the trajectory accuracy matching result with the trajectory accuracy threshold, and if the trajectory accuracy matching result exceeds the trajectory accuracy threshold, it is determined that there is no problem with the measurement accuracy of the probe at this time; the data analysis module sends a display normal signal to the display module; If the trajectory accuracy matching result does not exceed the trajectory accuracy threshold, it is determined that there is a problem with the measurement accuracy of the probe at this time, and the data analysis module sends a display abnormality signal to the display module.
6. A liquid crystal glass substrate warpage thickness measurement system according to claim 5, It is characterized in that The pre-established motion trajectory accuracy model of the data analysis module is based on artificial intelligence model training, wherein the process based on artificial intelligence model training is as follows: The data acquisition unit in the data analysis module collects standard probe trajectory data and standard motion trajectory; wherein the standard probe trajectory data includes: standard measurement point coordinate data, standard probe and measured part surface distance data and standard measured part thickness data; The standard probe trajectory data and the standard motion trajectory are combined to obtain a motion trajectory accuracy data set, which is input into the artificial intelligence model for training, and the motion trajectory accuracy model is output.
