OLED substrate pixel slot positioning method, system and device and storage medium

Abstract

The invention relates to the technical field of ink-jet printing, and discloses an OLED substrate pixel slot positioning method, system and device and a storage medium, and the OLED substrate pixel slot positioning method comprises the following steps: obtaining temperature data of all sensors and an image of a glass substrate, calculating to obtain a two-dimensional temperature field function and the actual displacement of a reference mark point, and calculating the actual displacement of the two-dimensional temperature field function and the actual displacement of the reference mark point; constructing a substrate stage simulation model; according to the simulation model, temperature prediction data and first displacement prediction data of the multiple point locations are obtained through calculation, a preset convolutional neural network model is trained to obtain an OLED substrate pixel slot positioning model, and coordinates of the reference mark point at the next moment are obtained through prediction and calculation of the OLED substrate pixel slot positioning model. According to the method, thermally induced deformation errors are compensated through the temperature field and the convolutional neural network model, noise and delay caused by dependence on real-time visual detection are reduced, and the method is suitable for high-precision pixel slot positioning in the machining process of the large-size glass substrate.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of inkjet printing technology, and in particular to an OLED substrate pixel groove positioning method, system, device and storage medium. BACKGROUND

[0002] The existing inkjet printing alignment method can only measure the result of deformation after the deformation has occurred through optical images, which is a passive reactive detection. The root cause of deformation is often thermal stress. In the process, the substrate will produce a temperature gradient due to uneven heating, leading to uneven thermal expansion and thus causing deformation. As the size of the OLED substrate increases, it is more likely to produce complex deformation due to temperature changes (which may cause thermal expansion and contraction) or mechanical stress during transmission and printing. Relying solely on a few discrete alignment marks for position calculation is like guessing the overall distortion of a large sheet of paper with a few points. It cannot perceive and compensate for the complex distortion between the mark points, resulting in inaccurate alignment in local areas. Error compensation is lagging, and for high-speed continuous printing, especially when the system has a large inertia or mechanical delay, this lagging compensation may not be able to fully keep up with the speed of error generation, resulting in printing deviation. SUMMARY

[0003] The present application aims to improve at least one technical problem in the background art.

[0004] The first aspect of the present application provides an OLED substrate pixel groove positioning method applied to an OLED substrate pixel groove positioning system, the OLED substrate pixel groove positioning system comprising a control device, a carrier and a plurality of temperature sensors, the carrier being used to carry a glass substrate, a plurality of temperature sensors being installed on the carrier, the control device being electrically connected with the plurality of temperature sensors; the OLED substrate pixel groove positioning method comprising the following steps: obtaining temperature data of all sensors and obtaining an image of the glass substrate; interpolating all the temperature data to calculate a two-dimensional temperature field function; determining the coordinates of the reference mark points according to the image of the glass substrate; calculating the actual displacement of the reference mark points according to the coordinates of the reference mark points; constructing a substrate carrier simulation model according to the actual displacement of the reference mark points and the two-dimensional temperature field function; calculating temperature prediction data and first displacement prediction data of a plurality of points according to the substrate carrier simulation model, training a preset convolutional neural network model using the temperature prediction data and the first displacement prediction data to obtain an OLED substrate pixel groove positioning model; inputting the two-dimensional temperature field function into the OLED substrate pixel groove positioning model to output the predicted displacement of the reference mark points; According to the coordinates of the reference mark point and the predicted displacement, the coordinates of the reference mark point at the next moment are calculated.

[0005] Optionally, in the first implementation manner of the first aspect, the substrate stage simulation model is constructed according to the actual displacement of the reference mark point and the two-dimensional temperature field function, and the construction includes: a thermal-mechanical coupling finite element model is built according to the glass substrate and the stage; thermal properties, mechanical properties and thermal expansion coefficients are given to the thermal-mechanical coupling finite element model to obtain a first model; boundary conditions and loads are applied to the first model to obtain a second model; the thermal-mechanical coupling analysis of the second model is solved in a sequential coupling manner to calculate second displacement prediction data of the reference mark point; the second model is iteratively optimized according to the second displacement prediction data and the actual displacement until a preset condition is met to obtain the substrate stage simulation model.

[0006] Optionally, in the second implementation manner of the first aspect, the applying of the boundary conditions and the loads to the first model includes: the two-dimensional temperature field function is applied as a load to the bottom surface of the glass substrate; convection heat transfer and radiation heat transfer are applied as boundary conditions to the top surface and the side surface of the glass substrate and the surface of the stage; contact thermal conductance and contact stiffness are applied as boundary conditions to the interface between the glass substrate and the stage.

[0007] Optionally, in the third implementation manner of the first aspect, the solving of the thermal-mechanical coupling analysis of the second model in a sequential coupling manner to calculate the second displacement prediction data of the reference mark point includes: steady-state thermal analysis is performed on the second model to calculate the temperature distribution of the second model; the temperature distribution is input as a body load into static structure analysis to calculate the deformation of the glass substrate; the second displacement prediction data of the reference mark point is obtained according to the deformation of the glass substrate.

[0008] Optionally, in the fourth implementation manner of the first aspect, the temperature prediction data and the first displacement prediction data of a plurality of points are calculated according to the substrate stage simulation model, the preset convolutional neural network model is trained using the temperature prediction data and the first displacement prediction data to obtain an OLED substrate pixel groove positioning model, and the method includes: each temperature prediction data is converted into a first two-dimensional array, and each first displacement prediction data is converted into a second two-dimensional array; Group all the first two-dimensional arrays and the corresponding second two-dimensional arrays into a plurality of data pairs, and randomly divide all the data pairs to obtain a training set; Build a U-Net network structure, input the first two-dimensional array of the training set into the U-Net network structure, and output a predicted two-dimensional array; According to the predicted two-dimensional array and the second two-dimensional array corresponding to the input first two-dimensional array, calculate the loss function; According to the loss function, update the network weight of the U-Net network structure, return to execute the step of calculating the loss function according to the predicted two-dimensional array and the second two-dimensional array corresponding to the input first two-dimensional array, until the training set is traversed, and an OLED substrate pixel groove positioning model is obtained.

[0009] The second aspect of the present application provides an OLED substrate pixel groove positioning system, comprising: a control device, a rack, a carrier and a plurality of temperature sensors, the carrier is installed on the rack, the carrier is used to carry a glass substrate, the temperature sensors are installed on the carrier, the glass substrate is provided with a reference mark point, and the control device is electrically connected with the plurality of temperature sensors;The OLED substrate pixel groove positioning system is used to execute the OLED substrate pixel groove positioning method as described above.

[0010] As a further improvement of the above technical solution, the OLED substrate pixel groove positioning system further comprises an X-axis moving mechanism, a Y-axis moving mechanism and a CCD camera, the fixed part of the Y-axis moving mechanism is installed on the rack, the movable part of the Y-axis moving mechanism is in transmission connection with the carrier, the Y-axis moving mechanism drives the carrier to move along the Y-axis direction, the fixed part of the X-axis moving mechanism is installed on the rack, the CCD camera is installed on the movable part of the X-axis moving mechanism, the X-axis moving mechanism drives the CCD camera to move along the X-axis direction, the CCD camera is located above the glass substrate, the CCD camera is used to shoot the glass substrate, and the control device is electrically connected with the Y-axis moving mechanism, the X-axis moving mechanism and the CCD camera.

[0011] As a further improvement of the above technical solution, the OLED substrate pixel groove positioning system further comprises a first laser interferometer and a second laser interferometer, the first laser interferometer is arranged on the rack, the first laser interferometer is used to measure the distance between the first laser interferometer and the carrier along the Y-axis direction, the second laser interferometer is arranged on the fixed part of the X-axis moving mechanism, the second laser interferometer is used to measure the distance between the second laser interferometer and the CCD camera along the X-axis direction, and the control device is electrically connected with the first laser interferometer and the second laser interferometer.

[0012] The third aspect of the present application provides an OLED substrate pixel slot positioning device, comprising a memory and at least one processor, wherein the memory stores instructions; The at least one processor invokes the instructions in the memory to enable the OLED substrate pixel slot positioning device to perform each step of the OLED substrate pixel slot positioning method described above.

[0013] The fourth aspect of the present application provides a computer readable storage medium, which stores instructions, and the instructions are executed by a processor to implement each step of the OLED substrate pixel slot positioning method described above.

[0014] The present application has the following advantages: by acquiring temperature data of multiple temperature sensors of a carrier and constructing a two-dimensional temperature field function through interpolation, an image of a glass substrate is acquired to determine the coordinates of a reference mark point, the actual displacement of the reference mark point is calculated, and a simulation model of the glass substrate carrier is established based on the actual displacement and the two-dimensional temperature field function, and then an OLED substrate pixel slot positioning model is trained and called to predict the displacement of the reference mark point. The existing inkjet printing positioning method can only measure the result of deformation after the deformation has occurred, and the glass substrate will produce a temperature gradient due to uneven heating, resulting in uneven thermal expansion and thus deformation. The present application can predict the trend and size of deformation before or during deformation by monitoring the temperature at different positions of the substrate in real time, compensate for thermal deformation errors through a temperature field and a convolutional neural network model, significantly improve positioning accuracy, reduce noise and delay caused by relying only on real-time visual detection, improve positioning stability, and be suitable for high-precision pixel slot positioning of large-size glass substrates during processing. In addition, the temperature sensing system is relatively simple, low in cost, and easy to maintain. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and / or additional aspects and advantages of the present application will become apparent and more readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which: Figure 1 A first flowchart of an OLED substrate pixel slot positioning method provided by an embodiment of the present application; Figure 2 A second flowchart of an OLED substrate pixel slot positioning method provided by an embodiment of the present application; Figure 3 A third flowchart of an OLED substrate pixel slot positioning method provided by an embodiment of the present application; Figure 4 A fourth flowchart of an OLED substrate pixel slot positioning method provided by an embodiment of the present application; Figure 5A fifth flowchart of the OLED substrate pixel groove positioning method provided by the embodiment of the present application is provided; Figure 6 A perspective view of the ink supply control system provided by the embodiment of the present application is provided; Figure 7 A schematic diagram of the glass substrate provided by the embodiment of the present application is provided; Figure 8 A structural schematic diagram of the ink supply control device provided by the embodiment of the present application is provided.

[0016] In the drawings: 1-Stage; 2-Temperature sensor; 3-CCD camera; 4-Second laser interferometer; 5-First laser interferometer; 6-Y-axis moving mechanism; 7-X-axis moving mechanism; 8-Rack. DETAILED DESCRIPTION

[0017] The embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application.

[0018] The embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application. Figures 1 to 8 The embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar notations represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application.

[0019] Please refer to Figure 1 and Figure 7 One embodiment of the OLED substrate pixel groove positioning method of the present application comprises: an OLED substrate pixel groove positioning system applied to, comprising: a control device, a stage and a plurality of temperature sensors, the stage is used to carry a glass substrate, the glass substrate is provided with a reference mark point, the temperature sensor is installed on the stage, and the control device is electrically connected with the plurality of temperature sensors; the OLED substrate pixel groove positioning method comprises the following steps: 101, acquiring temperature data of all sensors, acquiring images of the glass substrate; In this embodiment, the temperature data of the plurality of temperature sensors arranged on the stage is collected in real time, and the image information of the glass substrate is collected at the same time, which can be collected by setting a CCD camera.

[0020] 102, interpolating all the temperature data to calculate a two-dimensional temperature field function; In this embodiment, the discrete temperature data obtained is subjected to interpolation operation to construct a two-dimensional temperature field function covering the stage and the glass substrate area, which is used to represent the temperature distribution state of the current stage surface. The discrete sensor readings are converted into a continuous two-dimensional temperature field function The interpolation method: the coordinates of each sensor are known , and their temperature readings , representing the sensor, a spatial interpolation algorithm is used to estimate the temperature of any point on the stage surface.

[0021] 103. Determine the coordinates of the fiducial mark points according to the image of the glass substrate; In this embodiment, the image of the glass substrate is processed, the fiducial mark points on the glass substrate are recognized and extracted, and the coordinate information of each fiducial mark point at the current time is obtained. Referring to Figure 7 , the fiducial mark points can be arranged along the ring line.

[0022] 104. Calculate the actual displacement of the fiducial mark points according to the coordinates of the fiducial mark points; In this embodiment, the coordinates of the fiducial mark points at the current time are compared with the coordinates in the reference state, and the actual displacement of the fiducial mark points is calculated.

[0023] 105. Construct a substrate stage simulation model according to the actual displacement of the fiducial mark points and the two-dimensional temperature field function; In this embodiment, a substrate stage simulation model for describing the thermal deformation relationship between the stage and the glass substrate is constructed according to the actual displacement of the fiducial mark points and the two-dimensional temperature field function.

[0024] 106. Calculate the temperature prediction data and the first displacement prediction data of a plurality of points according to the substrate stage simulation model, and use the temperature prediction data and the first displacement prediction data to train a preset convolutional neural network model to obtain an OLED substrate pixel groove positioning model; In this embodiment, the substrate stage simulation model outputs temperature data and corresponding displacement prediction data at a plurality of different spatial points, forming a temperature-displacement prediction data set, which serves as the basis for subsequent model training. The temperature-displacement prediction data is used to train a convolutional neural network model to obtain an OLED substrate pixel groove positioning model.

[0025] 107. Input the two-dimensional temperature field function into the OLED substrate pixel groove positioning model to output the predicted displacement of the fiducial mark points; In this embodiment, the two-dimensional temperature field function currently constructed is input into the OLED substrate pixel groove positioning model to output the predicted displacement of the fiducial mark points.

[0026] 108. Calculate the coordinates of the fiducial mark points at the next time according to the coordinates and the predicted displacement of the fiducial mark points.

[0027] In this embodiment, the coordinates of the reference mark point at the next moment are calculated according to the current coordinates of the reference mark point and the predicted displacement, so as to realize real-time prediction positioning of the pixel groove position of the OLED substrate.

[0028] In the embodiment of the present application, the temperature data of the plurality of temperature sensors of the stage is obtained, and the two-dimensional temperature field function is constructed by interpolation, the glass substrate image is obtained to determine the coordinates of the reference mark point, the actual displacement of the reference mark point is calculated, and the glass substrate stage simulation model is established based on the actual displacement and the two-dimensional temperature field function, and then the OLED substrate pixel groove positioning model is trained and called to predict the displacement of the reference mark point. The existing inkjet printing alignment method can only measure the deformation result after the deformation has occurred through optical image. The glass substrate will produce temperature gradient due to uneven heating, causing uneven thermal expansion and thus deformation. In the embodiment of the present application, the temperature at different positions of the substrate is monitored in real time, the trend and size of the deformation can be predicted before or during the deformation, the thermal deformation error is compensated through the temperature field and the convolutional neural network model, the positioning accuracy is significantly improved, the noise and delay caused by relying on real-time visual detection are reduced, the positioning stability is improved, and the method is suitable for high-precision pixel groove positioning of large-size glass substrates in the processing process. In addition, the temperature sensing system is relatively simple, low in cost, and convenient to maintain.

[0029] Please refer to Figure 2 The second embodiment of the OLED substrate pixel groove positioning method of the present application comprises: According to the actual displacement of the reference mark point and the two-dimensional temperature field function, a substrate stage simulation model is constructed, comprising: 201. Build a thermal coupling finite element model according to the glass substrate and the stage; In this embodiment, a CAD software (such as SolidWorks, CATIA) or a modeling tool built-in finite element software can be used to create a three-dimensional geometric model of the glass substrate and the marble stage. The finite element analysis software can be selected from ANSYS, Abaqus or COMSOL Multiphysics, etc. The glass substrate and the marble stage are meshed, and the hexahedron dominant sweep mesh is used. In the key area, such as the edge of the substrate and the vicinity of the mark point, mesh refinement is needed to accurately capture stress concentration and displacement gradient. The mesh is continuously refined and recalculated until the maximum displacement change is less than the threshold value (1%), ensuring that the calculation result is independent of the grid density.

[0030] 202. Assign thermal properties, mechanical properties and thermal expansion coefficients to the thermal coupling finite element model to obtain a first model; In this embodiment, the properties of the glass substrate and the stage are: Thermal properties: thermal conductivity (k), specific heat capacity (c), and density (p); Mechanical properties: Young's modulus (E), Poisson's ratio (v); Thermal-mechanical coupling properties: thermal expansion coefficient.

[0031] Initial parameter values can come from material handbooks or supplier-provided data, and subsequent models calibrate and adjust these nominal value data.

[0032] 203. Apply boundary conditions and loads to the first model to obtain a second model; In this embodiment, boundary conditions and loads are applied to the first model, two-dimensional temperature field functions, convective heat transfer and radiation heat transfer, etc. can be applied, as well as the boundary conditions of the interface between the glass substrate and the stage, so that the model is more consistent with the real data.

[0033] 204. Use the sequential coupling method to solve the thermal-mechanical coupling analysis of the second model to calculate the second displacement prediction data of the fiducial marker point; In this embodiment, the deformation of the glass substrate has little effect on macroscopic heat conduction, so the sequential coupling method with higher computational efficiency is used. First, steady-state thermal analysis is performed to calculate the temperature distribution of the entire model; then this temperature distribution is input as a body load into the subsequent static structure analysis to calculate the thermal-induced deformation.

[0034] 205. Iteratively optimize the second model according to the second displacement prediction data and the actual displacement until the preset condition is met to obtain the substrate stage simulation model.

[0035] In this embodiment, the uncertain input parameters in the model are adjusted so that the difference between the output (second displacement prediction data) of the model and the actual displacement is minimized.

[0036] The optimization goal is to minimize the residual error between the simulated second displacement prediction data and the actual displacement measured by the CCD camera: wherein, represents the residual error; is the parameter vector to be calibrated; all steady-state experimental data points (different temperature conditions) are traversed, all CCD measurement marker points are traversed; , is the fiducial marker point of the finite element model under temperature conditions and parameters , the second displacement prediction data in the X and Y axis directions; , is the actual displacement of the fiducial marker point under temperature conditions in the X and Y axis directions.

[0037] Parameter vector The candidate parameters in the parameter vector can include the following parameters: P1: Coefficient of thermal expansion (CTE) of the glass substrate: It can be optimized as a constant or a linear or quadratic function of temperature if the temperature difference is large.

[0038] P2: Thermal contact conductance (TCC) of the glass-marble interface: It determines the efficiency of heat transfer from the stage to the glass substrate, thereby affecting the actual temperature distribution inside the glass and indirectly affecting the deformation.

[0039] P3: Contact stiffness of the glass-marble interface: Under vacuum suction, the contact behavior of micro-irregularities affects local displacement.

[0040] P4: Young's modulus (E) of the glass: It affects the ability of the glass substrate material to resist deformation.

[0041] P5: Convective heat transfer coefficient: It affects the heat dissipation on the top and side surfaces of the glass substrate, thereby affecting the overall temperature distribution.

[0042] First, perform a sensitivity analysis to identify the parameters that have the greatest impact on the final displacement results as the main calibration objects, to reduce the dimension and complexity of the optimization problem.

[0043] The parameter optimization algorithm uses a hybrid optimization strategy. First, use the genetic algorithm for global search to find a region close to the global optimum in the entire parameter space. Take the optimal solution obtained by global search as the initial value, and use the Levenberg-Marquardt local optimization algorithm for fine tuning to converge to the final solution.

[0044] The iterative calibration process is as follows: Define the parameter vector to be calibrated and its value range (constraints); select the optimization algorithm and set its parameters (such as the population size, crossover and mutation rate of GA); set the iteration stop condition; set the initial parameters (based on empirical material manuals or data provided by suppliers).

[0045] Start the iteration loop (current iteration step ), generate a new candidate parameter vector based on the historical evaluation results. For each steady-state experimental condition ( ), update the input of the finite element model using the parameters , run the solution to get the predicted displacement field under each condition. From the simulation result file, extract the displacement of all reference markers The second displacement prediction data corresponding to the position is then used. The extracted second displacement prediction data and the corresponding actual displacement are then substituted into the formula to calculate the current parameters. The objective function value .Will The value is returned to the optimization algorithm, which checks whether the preset iteration stopping condition is met. If it is met, the loop ends, and the current optimal value is returned. This is the calibration result; if it does not meet the requirements, then... Then, begin the next iteration.

[0046] The iteration terminates when any of the following conditions are met: (1) The objective function converges: the relative change in the objective function value is less than a very small threshold in several consecutive steps.

[0047] (2) Parameter convergence: The relative change of the parameter vector is less than a threshold in several consecutive steps.

[0048] (3) Reaching the maximum number of iterations: To prevent the algorithm from failing to converge and taking too long, a maximum number of iterations N_max (200 times) is set.

[0049] In this embodiment of the invention, a thermo-mechanically coupled finite element model of the glass substrate and the stage is established. The model is assigned thermal properties, mechanical properties, and a coefficient of thermal expansion. A two-dimensional temperature field function is applied as a thermal load. The second displacement prediction data of the reference marker points is solved through sequential coupling. Based on the second displacement prediction data and the actual displacement, the model is iteratively optimized to obtain a simulation model of the substrate and stage. The thermo-induced deformation mechanism of the glass substrate and stage is introduced into the positioning process in the form of a finite element model, improving the physical consistency of the model. Iterative optimization makes the simulation model match the actual working conditions, reducing errors caused by model parameter uncertainties. This provides a highly reliable model foundation for subsequent displacement prediction and neural network training, improving the accuracy and repeatability of the temperature-displacement relationship description.

[0050] Please refer to Figure 3 The third embodiment of the OLED substrate pixel slot positioning method of the present invention includes: The application of boundary conditions and loads to the first model includes: 301. Apply a two-dimensional temperature field function as a load to the bottom surface of the glass substrate; In this embodiment, the two-dimensional temperature field function As a thermal load applied to the model, As a specified temperature boundary condition, it is applied to all nodes on the bottom surface of the glass substrate (the surface in contact with the stage).

[0051] 302. Apply convective heat transfer and radiative heat transfer as boundary conditions on the top and side surfaces of the glass substrate, the surface of the table; In this embodiment, the upper surface and side surface of the glass substrate, and the exposed surface of the marble table, are applied with convective heat transfer and radiative heat transfer boundary conditions to simulate heat exchange with the surrounding air, and the ambient temperature, convective heat transfer coefficient and surface emissivity are defined.

[0052] 303. Apply contact thermal conductivity and contact stiffness as boundary conditions at the interface between the glass substrate and the table.

[0053] In this embodiment, the contact thermal conductivity (TCC) of the glass-marble interface determines the efficiency of heat transfer from the table to the glass substrate, thereby affecting the actual temperature distribution inside the glass substrate and indirectly affecting the deformation. The contact stiffness of the glass-marble interface, under vacuum adsorption, the contact behavior of micro-unevenness will affect the local displacement.

[0054] In addition, the structure load can also be given, and the following content can be selected: gravity; vacuum adsorption; contact definition: define a contact pair between the bottom surface of the glass substrate and the top surface of the marble table; normal behavior, set as hard contact, allow separation, do not allow penetration; tangential behavior: can be set as a contact with friction, set the friction coefficient; displacement constraint: to prevent rigid body displacement of the model during solving, proper fixing constraints need to be applied to the bottom or side surface of the marble table.

[0055] In the embodiment of the application, convective heat transfer and radiative heat transfer boundary conditions are applied to the glass substrate and the table in the thermal coupling finite element model, and contact thermal conductivity and contact stiffness are set at the contact interface between the glass substrate and the table. The heat exchange and mechanical constraint state of the glass substrate and the table during actual operation can be more realistically simulated, the calculation deviation of the temperature field and deformation caused by the simplification of the boundary conditions is reduced, the applicability of the simulation model under different environmental temperatures and heat dissipation conditions is improved, and more accurate training data set is provided for the displacement prediction of the reference mark.

[0056] Please refer to Figure 4 The fourth embodiment of the OLED substrate pixel slot positioning method of the application comprises: The second displacement prediction data of the reference mark is calculated by using the sequence coupling method to solve the thermal coupling analysis of the second model, comprising: 401. Perform steady-state thermal analysis on the second model to calculate the temperature distribution of the second model; 402. Input the temperature distribution as a body load into the static structure analysis to calculate the deformation of the glass substrate; In this embodiment, steady-state thermal analysis is first performed to calculate the temperature distribution of the entire model; then the temperature distribution is input into subsequent static structure analysis as a body load to calculate the thermal deformation. The deformation of the glass substrate is in the micron level, and has little effect on macroscopic heat conduction, so the sequential coupling method with higher calculation efficiency is adopted.

[0057] 403、According to the deformation of the glass substrate, second displacement prediction data of the reference mark point is obtained.

[0058] In this embodiment, according to the deformation result of the glass substrate, the second displacement prediction data of the reference mark point is extracted.

[0059] In the embodiment of the present application, the sequential coupling method is used to solve the thermal-mechanical coupled finite element model, the temperature distribution is obtained by first performing steady-state thermal analysis, and then the temperature distribution is input into static structure analysis as a body load to calculate the deformation of the glass substrate, so as to obtain the second displacement prediction data of the reference mark point. On the premise of ensuring the accuracy of thermal-mechanical analysis, the overall calculation complexity is reduced, the numerical instability problem in full coupling analysis is reduced, the model solving reliability is improved, the model parameter adjustment and multiple iteration calculation are facilitated, and the modeling efficiency is improved.

[0060] Please refer to Figure 5 The fifth embodiment of the OLED substrate pixel groove positioning method of the present application comprises: The temperature prediction data and the first displacement prediction data of a plurality of points are calculated according to the substrate stage simulation model, the temperature prediction data and the first displacement prediction data are used to train a preset convolutional neural network model to obtain an OLED substrate pixel groove positioning model, which comprises: 501、Each temperature prediction data is converted into a first two-dimensional array, and each first displacement prediction data is converted into a second two-dimensional array; In this embodiment, for input features, the input temperature field is discretized into an N×M two-dimensional array (image), i.e. the first two-dimensional array, where each pixel value represents the temperature at that position. For output targets: the output deformation field and are also discretized into two N×M two-dimensional arrays (images), i.e. the predicted two-dimensional arrays. The actual displacement in the X and Y directions is discretized into two N×M two-dimensional arrays (images), i.e. the second two-dimensional arrays. Converting input and output into two-dimensional arrays is suitable for convolutional neural network (CNN) processing, and the problem is converted into an image-to-image regression task.

[0061] 502、All the first two-dimensional arrays and the corresponding second two-dimensional arrays are combined into a plurality of data pairs, and all the data pairs are randomly divided to obtain a training set; In this embodiment, all the generated data pairs are randomly divided into training set, validation set and test set in the ratio of 8:1:1. The training set is used to train the model and adjust the weights of the model. The validation set is used to monitor the performance of the model during the training process, optimize the hyperparameters and prevent overfitting. The test set does not participate in the training process and is only used for final evaluation of the generalization ability and performance of the model after the training is completed.

[0062] 503. Build a U-Net network structure, input the first two-dimensional array of the training set into the U-Net network structure, and output a predicted two-dimensional array; 504. Calculate the loss function according to the predicted two-dimensional array and the second two-dimensional array corresponding to the input first two-dimensional array; 505. Update the network weights of the U-Net network structure according to the loss function, and return to execute the step of calculating the loss function according to the predicted two-dimensional array and the second two-dimensional array corresponding to the input first two-dimensional array, until the training set is traversed, and an OLED substrate pixel slot positioning model is obtained.

[0063] In this embodiment, data preprocessing: normalize the input (temperature field) and output (deformation field) data (subtract the mean value and divide by the standard deviation, or scale to the [0, 1] interval) to accelerate model convergence and improve performance.

[0064] Build a U-Net network structure, and use mean square error as the loss function, wherein, the predicted two-dimensional array output by the model, is the second two-dimensional array converted from the input first displacement prediction data. Based on the predicted two-dimensional array, the predicted displacement can be converted.

[0065] Training loop: extract data from the training set in small batches, input the data into the U-Net model, perform forward propagation to obtain the predicted deformation field, and calculate the loss between the predicted displacement and the actual displacement. Then perform backpropagation to calculate the gradient of the loss function with respect to each weight of the network, and use the Adam optimizer to update the network weights based on the gradient. Repeat the above steps until the training set is traversed.

[0066] After each training loop, evaluate the model performance on the validation set. If the loss on the validation set no longer decreases, trigger the early stopping mechanism to stop training to prevent overfitting.

[0067] In the embodiment of the present application, based on the plurality of temperature prediction data and the first displacement prediction data output by the substrate stage simulation model, a data set is constructed and a convolutional neural network model is trained, the convolutional neural network model adopts a U-Net network structure and is used for rapidly predicting the displacement of the reference mark point according to a two-dimensional temperature field. The complex finite element simulation calculation result is mapped to an efficient neural network prediction model, rapid online displacement prediction is realized, the extraction capability of the U-Net network for the spatial features of the two-dimensional temperature field is utilized, the prediction accuracy is improved, the calculation resource consumption in the real-time positioning process is significantly reduced, and the overall response speed of the OLED substrate pixel groove positioning method is improved.

[0068] The OLED substrate pixel groove positioning method of the present application is described above, and the OLED substrate pixel groove positioning system in the embodiment of the present application is described below, with reference to Figure 6 One embodiment of the OLED substrate pixel groove positioning system in the embodiment of the present application comprises: A control device, a rack 8, a stage 1 and a plurality of temperature sensors 2, the stage 1 is installed on the rack 8, the stage 1 is used for carrying a glass substrate, the temperature sensors 2 are installed on the stage 1, the glass substrate is provided with a reference mark point, and the control device is electrically connected with the plurality of temperature sensors 2; the OLED substrate pixel groove positioning system is used for executing the OLED substrate pixel groove positioning method as described above.

[0069] In the embodiment, a plurality of temperature sensors 2 are arranged on the stage 1, which has a simple structure and can stably obtain temperature information of the stage 1, thereby providing reliable data sources for establishing a two-dimensional temperature field function and a simulation model. Specifically, the temperature sensors 2 are embedded in the surface of the stage 1 and arranged at key positions of the stage 1, including the edges, center and key support points of the stage 1, so that the temperature distribution of the entire stage 1 and the glass substrate can be collected in real time and synchronously.

[0070] The second embodiment of the OLED substrate pixel groove positioning system in the embodiment of the present application further comprises an X-axis moving mechanism 7, a Y-axis moving mechanism 6 and a CCD camera 3, the fixed part of the Y-axis moving mechanism 6 is installed on the rack, the movable part of the Y-axis moving mechanism 6 is in transmission connection with the stage 1, the Y-axis moving mechanism 6 drives the stage 1 to move along the Y-axis direction, the fixed part of the X-axis moving mechanism 7 is installed on the rack, the CCD camera 3 is installed on the movable part of the X-axis moving mechanism 7, the X-axis moving mechanism 7 drives the CCD camera 3 to move along the X-axis direction, the CCD camera 3 is located above the glass substrate, the CCD camera 3 is used for shooting the glass substrate, and the control device is electrically connected with the Y-axis moving mechanism 6, the X-axis moving mechanism 7 and the CCD camera 3.

[0071] In this embodiment, an X-axis moving mechanism 7, a Y-axis moving mechanism 6, and a CCD camera 3 are configured to acquire images of the glass substrate and obtain the coordinates of reference marker points, thereby improving the spatial coverage of reference marker point detection, meeting the positioning requirements of large-size glass substrates, and providing image data for reference marker point displacement calculation and model correction. Specifically, the CCD camera 3 identifies reference marker points on the glass substrate and determines the actual positions of these reference marker points in the coordinate systems of the X-axis moving mechanism 7 and the Y-axis moving mechanism 6.

[0072] In a third embodiment of the OLED substrate pixel slot positioning system of the present invention, the OLED substrate pixel slot positioning system further includes a first laser interferometer 5 and a second laser interferometer 4. The first laser interferometer 5 is mounted on the frame 8 and is used to measure the distance between itself and the stage 1 along the Y-axis. The second laser interferometer 4 is mounted on the fixed part of the X-axis moving mechanism 7 and is used to measure the distance between itself and the CCD camera 3 along the X-axis. The control device is electrically connected to the first laser interferometer 5 and the second laser interferometer 4.

[0073] In this embodiment, laser interferometers are respectively set in the movement directions of the stage 1 and the CCD camera 3 to measure the displacement information of the stage 1 and the CCD camera 3 and to link with the control device, thereby further improving the overall positioning accuracy and stability of the system. Specifically, the first laser interferometer 5 measures the movement distance of the stage 1 in the Y-axis direction, and the second laser interferometer 4 and the CCD camera 3 measure the movement distance in the X-axis direction.

[0074] Figure 8 This is a schematic diagram of the structure of an OLED substrate pixel slot positioning device 800 provided in an embodiment of the present invention. The OLED substrate pixel slot positioning device 800 can vary significantly due to different configurations or performance characteristics. It may include one or more central processing units (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) storing application programs 833 or data 832. The memory 820 and storage media 830 can be temporary or persistent storage. The program stored in the storage media 830 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the OLED substrate pixel slot positioning device 800. Furthermore, the processor 810 may be configured to communicate with the storage media 830 and execute the series of instruction operations in the storage media 830 on the OLED substrate pixel slot positioning device 800 to implement the steps of the OLED substrate pixel slot positioning method provided in the above-described method embodiments.

[0075] The OLED substrate pixel groove positioning apparatus 800 can also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input / output interfaces 860, and / or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that, Figure 8 The illustrated OLED substrate pixel groove positioning apparatus structure is not intended to limit the OLED substrate pixel groove positioning apparatus, and can include more or fewer components than illustrated, or can combine certain components, or have a different arrangement of components.

[0076] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, or a volatile computer readable storage medium, and the computer readable storage medium stores instructions, which, when executed on a computer, cause the computer to perform the steps of the OLED substrate pixel groove positioning method.

[0077] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the above-described system or device, unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0078] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art, or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0079] Finally, it should be noted that: the above only describes the preferred embodiments of the present application, and is not intended to limit the present application, although the present application has been described in detail with reference to the foregoing embodiments, and for those skilled in the art, the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced with equivalent ones. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for positioning pixel slots on an OLED substrate, characterized in that, An OLED substrate pixel slot positioning system is applied, comprising: a control device, a stage, and multiple temperature sensors. The stage supports a glass substrate, and the multiple temperature sensors are mounted on the stage. The control device is electrically connected to the multiple temperature sensors. The OLED substrate pixel slot positioning method includes the following steps: Acquire temperature data from all sensors and obtain images of the glass substrate; Interpolate all the temperature data to calculate the two-dimensional temperature field function; Determine the coordinates of the reference marker points based on the image of the glass substrate; The actual displacement of the reference marker point is calculated based on its coordinates. Based on the actual displacement of the reference markers and the two-dimensional temperature field function, a simulation model of the substrate stage is constructed. Based on the substrate stage simulation model, temperature prediction data and first displacement prediction data at multiple points are calculated. The temperature prediction data and first displacement prediction data are used to train a preset convolutional neural network model to obtain the OLED substrate pixel slot positioning model. The two-dimensional temperature field function is input into the OLED substrate pixel slot positioning model, and the predicted displacement of the reference marker point is output. Based on the coordinates of the reference marker and the predicted displacement, the coordinates of the reference marker at the next moment are calculated.

2. The OLED substrate pixel slot positioning method according to claim 1, characterized in that, Based on the actual displacement of the reference marker points and the two-dimensional temperature field function, a simulation model of the substrate stage is constructed, including: A thermo-coupled finite element model was constructed based on the glass substrate and the stage. The thermo-coupled finite element model is given thermal properties, mechanical properties, and coefficient of thermal expansion to obtain the first model; By applying boundary conditions and loads to the first model, the second model is obtained. The second model was solved by sequential coupling analysis to obtain the second displacement prediction data of the reference marker point. Based on the second displacement prediction data and the actual displacement, the second model is iteratively optimized until it meets the preset conditions, thus obtaining the simulation model of the substrate stage.

3. The OLED substrate pixel slot positioning method according to claim 2, characterized in that, The application of boundary conditions and loads to the first model includes: A two-dimensional temperature field function is applied as a load to the bottom surface of the glass substrate; Convection and radiation heat transfer are applied as boundary conditions to the top and side surfaces of the glass substrate and the surface of the stage. Contact thermal conductivity and contact stiffness are applied as boundary conditions to the interface between the glass substrate and the stage.

4. The OLED substrate pixel slot positioning method according to claim 2, characterized in that, The method of solving the thermo-mechanical coupling analysis of the second model using sequential coupling to calculate the second displacement prediction data of the reference marker points includes: Steady-state thermal analysis was performed on the second model to calculate its temperature distribution. Temperature distribution is used as a volume load input for static structural analysis to calculate the deformation of the glass substrate. Based on the deformation of the glass substrate, the second displacement prediction data of the reference mark point is obtained.

5. The OLED substrate pixel slot positioning method according to claim 1, characterized in that: Based on the substrate stage simulation model, temperature prediction data and first displacement prediction data for multiple points are calculated. A pre-set convolutional neural network model is trained using the temperature prediction data and the first displacement prediction data to obtain the OLED substrate pixel slot positioning model, including: Each temperature prediction data is converted into a first two-dimensional array, and each first displacement prediction data is converted into a second two-dimensional array; All the first two-dimensional arrays and their corresponding second two-dimensional arrays are combined into multiple data pairs, and all data pairs are randomly divided to obtain the training set. Construct a U-Net network structure, input the first two-dimensional array of the training set into the U-Net network structure, and output a predicted two-dimensional array; Calculate the loss function based on the predicted two-dimensional array and the second two-dimensional array corresponding to the first input two-dimensional array; Based on the loss function, update the network weights of the U-Net network structure, and return to the step of calculating the loss function based on the predicted two-dimensional array and the second two-dimensional array corresponding to the first two-dimensional array of input, until the training set is traversed to obtain the OLED substrate pixel slot localization model.

6. A pixel slot positioning system for an OLED substrate, characterized in that, include: The system comprises a control device, a frame (8), a stage (1), and multiple temperature sensors (2). The stage (1) is mounted on the frame (8) and is used to support a glass substrate. The temperature sensors (2) are mounted on the stage (1). The glass substrate has reference markings. The control device is electrically connected to the multiple temperature sensors (2). The OLED substrate pixel slot positioning system is used to perform the OLED substrate pixel slot positioning method as described in any one of claims 1-5.

7. The OLED substrate pixel slot positioning system according to claim 6, characterized in that, The OLED substrate pixel slot positioning system further includes an X-axis moving mechanism (7), a Y-axis moving mechanism (6), and a CCD camera (3). The fixed part of the Y-axis moving mechanism (6) is mounted on the frame (8), and the movable part of the Y-axis moving mechanism (6) is connected to the stage (1) for transmission. The Y-axis moving mechanism (6) drives the stage (1) to move along the Y-axis direction. The fixed part of the X-axis moving mechanism (7) is mounted on the frame (8), and the CCD camera (3) is mounted on the movable part of the X-axis moving mechanism (7). The X-axis moving mechanism (7) drives the CCD camera (3) to move along the X-axis direction. The CCD camera (3) is located above the glass substrate and is used to photograph the glass substrate. The control device is electrically connected to the Y-axis moving mechanism (6), the X-axis moving mechanism (7), and the CCD camera (3).

8. The OLED substrate pixel slot positioning system according to claim 7, characterized in that: The OLED substrate pixel slot positioning system further includes a first laser interferometer (5) and a second laser interferometer (4). The first laser interferometer (5) is mounted on the frame (8) and is used to measure the distance between it and the stage (1) along the Y-axis. The second laser interferometer (4) is mounted on the fixed part of the X-axis moving mechanism (7) and is used to measure the distance between it and the CCD camera (3) along the X-axis. The control device is electrically connected to the first laser interferometer (5) and the second laser interferometer (4).

9. A pixel slot positioning device for an OLED substrate, characterized in that, The OLED substrate pixel slot positioning device includes: a memory and at least one processor, wherein the memory stores instructions; At least one of the processors invokes the instructions in the memory to cause the OLED substrate pixel slot positioning device to perform the steps of the OLED substrate pixel slot positioning method as described in any one of claims 1-5.

10. A computer-readable storage medium storing instructions thereon, characterized in that, When the instructions are executed by the processor, they implement each step of the OLED substrate pixel slot positioning method as described in any one of claims 1-5.

Images