Mini LED defect positioning and repairing method and system based on photo-thermal monitoring

Abstract

The invention relates to microelectronic device detection and repair, in particular to a Mini LED defect positioning and repair method and system based on photo-thermal monitoring, and the method comprises the steps: obtaining a display circuit board, a high-resolution camera, a modulatable laser source, a thermal infrared imager and a repair tool head, and determining a plurality of brightness uniformity indexes and a rough position coordinate set based on an initial optical image set; performing temperature monitoring on the irradiated LED by using an infrared thermal imager to obtain a transient thermal response data set, performing thermal parameter extraction on the transient thermal response data set to obtain a peak temperature and response time, and determining a defect score based on the rough position coordinates, the plurality of brightness uniformity indexes, the initial optical image set, the peak temperature and the response time, and determining a plurality of repaired LEDs based on the display circuit board, the plurality of defect scores, the defect label set and the repair tool head, and completing Mini LED defect positioning and repair. According to the invention, the accuracy of positioning the Mini LED with the defect can be improved, and the repair efficiency is further improved.

Description

Technical Field

[0001] This invention relates to the inspection and repair of microelectronic devices, and more particularly to a method and system for locating and repairing defects in Mini LEDs based on photothermal monitoring. Background Technology

[0002] With the development of modern display technology, Mini LED, as a new type of display technology, has advantages such as high brightness, high contrast and long lifespan, and has been widely used in televisions, laptops, tablets and automotive displays.

[0003] Currently, traditional detection methods mainly rely on manual microscopic observation or single-light source imaging. Existing machine vision-based detection methods mostly focus on single-band image processing or using infrared images to determine thermal distribution.

[0004] While the above methods can detect Mini LEDs, they often only identify some defects and cannot simultaneously address comprehensive issues such as abnormal brightness, color imbalance, and abnormal infrared reflection. This results in insufficient accuracy in defect identification, low detection efficiency, and the detection results are easily affected by subjective factors, making it difficult to achieve large-scale, high-precision detection. Therefore, how to improve the accuracy of locating defective Mini LEDs and thus improve rework efficiency has become an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a method for locating and repairing defects in Mini LEDs based on photothermal monitoring, and a computer-readable storage medium. Its main purpose is to improve the accuracy of locating defective Mini LEDs, thereby improving repair efficiency.

[0006] To achieve the above objectives, this invention provides a method for Mini LED defect location and repair based on photothermal monitoring, comprising: The following items were obtained: a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board included multiple suspected Mini LEDs. A high-resolution camera is used to perform a global scan of the display circuit board to obtain an initial set of optical images. Based on the initial optical image set, multiple brightness uniformity indices and a set of coarse position coordinates were identified. The set of coarse position coordinates includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. For each of the multiple coarse position coordinates, perform the following operation: A modulated laser source is used to illuminate a suspected Mini LED corresponding to a rough position coordinate, thus obtaining the illuminated LED; The temperature of the irradiated LED was monitored using an infrared thermal imager to obtain a transient thermal response dataset; Thermal parameters were extracted from the transient thermal response dataset to obtain the peak temperature and response time; Defect scores were determined based on rough location coordinates, multiple brightness uniformity indices, initial optical image set, peak temperature, and response time. Summarize the defect scores to obtain multiple defect scores; By summarizing the transient thermal response datasets, multiple transient thermal response datasets are obtained; A defect analysis model was identified based on multiple defect scores and multiple transient thermal response datasets. Defect analysis was performed on multiple transient thermal response datasets using a defect analysis model to obtain a defect label set; Based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads, multiple reworkable LEDs were identified, completing the Mini LED defect location and rework.

[0007] Optionally, the step of using a high-resolution camera to perform a global scan of the display circuit board to obtain an initial optical image set includes: Obtain a workbench, which includes a camera bracket and a circuit board placement area, wherein the camera bracket is located directly above the circuit board placement area; The display circuit board is fixed on the circuit board placement area of ​​the worktable to obtain the circuit board to be photographed; A high-resolution camera is fixed to a camera mount to obtain a fixed camera; Set the working mode of the circuit board to be photographed to the preset first color mode to obtain the working circuit board; A fixed camera was used to photograph the working circuit board to obtain a red light image; Based on the circuit board to be photographed, the preset second color mode, and the fixed camera, a green light image was confirmed. The blue light image was confirmed based on the circuit board to be photographed, the preset third color mode, and the fixed camera. By combining the red light images, green light images, and blue light images, an initial optical image set is obtained.

[0008] Optionally, the determination of multiple brightness uniformity indices and a coarse set of position coordinates based on the initial optical image set includes: The green light image in the initial optical image set is converted to grayscale to obtain a grayscale green light image; The vertices, length, and width of the circuit board were determined based on the grayscale green light image. The first and second adjacent edges are identified based on the vertices of the circuit board. The first neighboring point is determined based on the vertex of the circuit board and the first adjacent edge, wherein the distance between the first neighboring point and the vertex of the circuit board is the length of the board and the first neighboring point is located on the first adjacent edge; The second neighboring point is determined based on the vertex of the circuit board and the second neighboring edge, wherein the distance between the second neighboring point and the vertex of the circuit board is the width of the board and the second neighboring point is located on the second neighboring edge; A coordinate system is established based on the circuit board vertex, the first neighboring point, and the second neighboring point. The circuit board vertex is used as the origin of the coordinate system, the direction from the circuit board vertex to the first neighboring point is used as the positive x-axis of the coordinate system, and the direction from the circuit board vertex to the second neighboring point is used as the positive y-axis of the coordinate system. The image to be segmented is identified based on the coordinate system and grayscale green light image. The image to be segmented includes: the center coordinates of multiple LEDs, including: the center x coordinate and the center y coordinate. Based on the preset segmentation window and the image to be segmented, multiple brightness uniformity indices and rough position coordinate sets are identified.

[0009] Optionally, the step of identifying the image to be segmented based on the coordinate system and grayscale green light image includes: The grayscale green light image is binarized to obtain a binary green light image; Multiple LED emitting areas were identified based on binary green light images and a pre-built contour detection model; Perform the following operation for each of the multiple LED emitting areas: The coordinates of the LED center were determined based on the LED's luminous area. By summing the center coordinates of the LEDs, we obtain the center coordinates of multiple LEDs. The center coordinates of multiple LEDs are mapped onto a grayscale green light image to obtain the image to be segmented.

[0010] Optionally, the determination of multiple brightness uniformity indices and rough position coordinate sets based on a preset segmentation window and the image to be segmented includes: For each LED center coordinate in the image to be segmented, perform the following operation: Identify the center of the split window, align the center of the window with the center coordinates of the LED, and obtain the clipping window; The image to be segmented is cropped using a cropping window to obtain a segmented image; Summarize the segmented images to obtain multiple segmented images; Number the multiple segmented images to obtain multiple numbered images; Perform the following operation on each of the multiple numbered images: The window grayscale value and brightness uniformity index were determined based on the numbered image. Summarize the grayscale values ​​of the windows to obtain grayscale values ​​for multiple windows; By summing the brightness uniformity indices, multiple brightness uniformity indices are obtained. A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows.

[0011] Optionally, the step of determining the window grayscale value and brightness uniformity index based on the numbered image includes: The image grayscale value set is determined based on the numbered image, wherein the image grayscale value set includes: multiple grayscale values; Calculate the window gray value based on multiple gray values ​​in the image gray value set; Multiple exposures are performed on the numbered image to obtain multiple exposed images; Perform the following operation on each of the multiple exposed images: Multiple grayscale values ​​were identified based on the exposed image; The window brightness is determined based on multiple processed grayscale values, where the window brightness is the average of the multiple processed grayscale values; The window brightness is summarized to obtain multiple window brightness values, where each window brightness corresponds one-to-one with the exposure image; The average window brightness is determined based on the brightness of multiple windows, where the average window brightness is the average of the brightness of multiple windows; The standard deviation of window brightness was determined based on the brightness of multiple windows, where the standard deviation of window brightness is the standard deviation of the brightness of multiple windows; The brightness uniformity index is calculated based on the average window brightness and the standard deviation of window brightness.

[0012] Optionally, determining the approximate location coordinate set based on multiple window grayscale values ​​includes: The average window gray value is determined based on the gray values ​​of multiple windows, where the average window gray value is the average of the gray values ​​of multiple windows; The standard deviation of grayscale values ​​is calculated based on the grayscale values ​​of multiple windows and the average grayscale value of the window. The calculation formula is as follows: in, This represents the standard deviation of grayscale values. This represents the average window grayscale value. This represents the number of grayscale values ​​in a window among multiple window grayscale values. Represents the grayscale value of multiple windows. Each window's grayscale value; The grayscale threshold is calculated based on the average window grayscale value and the standard deviation of the grayscale value. A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows and the grayscale threshold.

[0013] Optionally, the defect score determination based on coarse location coordinates, multiple brightness uniformity indices, an initial optical image set, peak temperature, and response time includes: Based on the red light image and blue light image in the initial optical image set, as well as the rough position coordinates, the red window image and blue window image were identified. The red component set is identified based on the red window image, wherein the red component set includes multiple red pixel values; the blue component set is identified based on the blue window image, wherein the blue component set includes multiple blue pixel values. The window redness value is calculated based on multiple red pixel values ​​in the red component set; The window blue value is calculated based on multiple blue pixel values ​​in the blue component set; The red-blue difference index is calculated based on the redness and blueness values ​​of the window. The target brightness uniformity index was determined based on the approximate location coordinates and multiple brightness uniformity indices. The defect score is calculated based on the target brightness uniformity index, red-blue difference index, peak temperature, and response time. The calculation formula is as follows: in, Indicates defect score. This represents the red-blue difference index. The preset red and blue standard index, Indicates peak temperature. Indicates response time. Indicates the uniformity index of target brightness. Represents the natural constant. The preset standard response time, is the hyperbolic tangent function, referring to taking the absolute value.

[0014] Optionally, the identification of multiple reworkable LEDs based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads includes: For each defect score in a set of multiple defect scores, perform the following operation: Compare the defect score with the preset score threshold. If the defect score is greater than or equal to the score threshold, the rough location coordinates corresponding to the defect score are used as the precise location coordinates. By summing the precise location coordinates, multiple precise location coordinates are obtained; For each of the multiple precise location coordinates, perform the following operation: The LED to be repaired was identified based on the display circuit board and its precise location coordinates. The target label was identified based on the defect label set and precise location coordinates; The target label is read to obtain the defect type, which includes: poor solder joint, chip crack, or material aging. If the defect type is a cold solder joint, the working mode of the repair tool head is set to the preset first mode to obtain the target tool head; Otherwise, set the working mode of the rework tool head to the preset second mode to obtain the target tool head; The target tool head is used to rework the LED to be repaired, and the repaired LED is obtained. The returned LEDs were compiled, resulting in multiple returned LEDs.

[0015] To achieve the above objectives, the present invention also provides a Mini LED defect location and repair system based on photothermal monitoring, comprising: The basic image acquisition module is used to acquire images of the display circuit board, high-resolution camera, modulated laser source, infrared thermal imager, and repair tool head. The display circuit board includes multiple suspected Mini LEDs. The high-resolution camera performs a global scan of the display circuit board to obtain an initial optical image set. The coarse position confirmation module is used to confirm multiple brightness uniformity indices and a coarse position coordinate set based on the initial optical image set. The coarse position coordinate set includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. The defect scoring calculation module performs the following operations for each of the multiple coarse location coordinates: irradiating the suspected Mini LED corresponding to the coarse location coordinate using a modulated laser source to obtain the irradiated LED; monitoring the temperature of the irradiated LED using an infrared thermal imager to obtain a transient thermal response dataset; extracting thermal parameters from the transient thermal response dataset to obtain the peak temperature and response time; confirming the defect score based on the coarse location coordinates, multiple brightness uniformity indices, the initial optical image set, the peak temperature, and the response time; and summarizing the defect scores to obtain multiple defect scores. The rework processing and repair module is used to summarize transient thermal response datasets, obtain multiple transient thermal response datasets, identify a defect analysis model based on multiple defect scores and multiple transient thermal response datasets, perform defect analysis on multiple transient thermal response datasets using the defect analysis model, obtain a defect label set, identify multiple reworkable LEDs based on the display circuit board, multiple defect scores, defect label set, and rework tool head, and complete the Mini LED defect location and rework.

[0016] To address the above problems, the present invention also provides an electronic device, the electronic device comprising: Memory, storing at least one instruction; and The processor executes the instructions stored in the memory to implement the aforementioned method for MiniLED defect location and repair based on photothermal monitoring.

[0017] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the aforementioned method for Mini LED defect location and rework based on photothermal monitoring.

[0018] To address the problems described in the background section, this invention acquires a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board includes multiple suspected Mini LEDs. This invention facilitates the acquisition of initial optical images of the display circuit board using the high-resolution camera, providing a basis for subsequent analysis to determine a coarse set of positional coordinates. The high-resolution camera then performs a global scan of the display circuit board to obtain the initial optical image set. This initial image set provides a foundation for subsequent analysis, identifying multiple brightness uniformity indices and a coarse set of positional coordinates. These coarse coordinates correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. This invention reduces the amount of subsequent analysis and improves the accuracy of identifying defective Mini LEDs by first analyzing the initial optical images. To improve the accuracy of LED positioning, the following operations are performed for each of the multiple coarse position coordinates: The suspected MiniLED corresponding to the coarse position coordinate is illuminated using a modulated laser source, thus illuminating the LED. This allows the suspected MiniLED to heat up, facilitating the subsequent screening of defective MiniLEDs. The temperature of the illuminated LED is monitored using an infrared thermal imager to obtain a transient thermal response dataset. Thermal parameters are extracted from the transient thermal response dataset to obtain the peak temperature and response time. This provides a basis for calculating defect scores by acquiring the thermal parameters of the MiniLED during heating. Based on the coarse position coordinates, multiple brightness uniformity indices, an initial optical image set, peak temperature, and response time, defect scores are confirmed. Multiple defect scores are then summarized, and multiple transient thermal response datasets are obtained. This demonstrates that by calculating a defect score for each MiniLED corresponding to a coarse position coordinate, this invention provides a data foundation for identifying circuit boards to be repaired based on the defect scores, improving the accuracy of identifying defective MiniLEDs. To improve the accuracy of LED positioning and thus rework efficiency, a defect analysis model is established based on multiple defect scores and transient thermal response datasets. This embodiment of the invention trains a defect analysis model using multiple defect scores and transient thermal response datasets, providing a tool for subsequent defect type analysis. The defect analysis model is then used to analyze defects in multiple transient thermal response datasets to obtain a defect label set.As can be seen, this embodiment of the invention analyzes transient thermal response data using a defect analysis model to determine the defect type, providing support for subsequent LED rework based on the defect type. Based on the display circuit board, multiple defect scores, defect tag sets, and rework toolheads, multiple reworkable LEDs are identified, completing the Mini LED defect location and rework. This embodiment of the invention achieves precise rework by applying different rework strategies to different LEDs, improving the accuracy of locating defective Mini LEDs and thus increasing rework efficiency. Therefore, this invention can improve the accuracy of locating defective Mini LEDs, thereby improving rework efficiency. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating a method for locating and repairing Mini LED defects based on photothermal monitoring, provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a Mini LED defect location and repair system based on photothermal monitoring provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device that implements the Mini LED defect location and repair method based on photothermal monitoring, according to an embodiment of the present invention.

[0020] Explanation of reference numerals in the attached figures: 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0023] This application provides a method for locating and repairing Mini LED defects based on photothermal monitoring. The executing entity of this method includes, but is not limited to, at least one electronic device configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0024] Reference Figure 1The diagram shown is a flowchart illustrating a method for locating and repairing Mini LED defects based on photothermal monitoring, according to an embodiment of the present invention. In this embodiment, the method for locating and repairing Mini LED defects based on photothermal monitoring includes: S1. Acquire the display circuit board, high-resolution camera, modulated laser source, infrared thermal imager, and repair tool head, wherein the display circuit board includes: multiple suspected Mini LEDs.

[0025] For example, Xiao Zhang is a worker at a circuit board manufacturing plant. He needs to assess the installation quality of MiniLEDs already installed on the circuit board, and then locate and rework problematic LEDs. So Xiao Zhang obtains a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a rework tool head. He then uses the high-resolution camera to inspect the display circuit board, uses the modulated laser source and infrared thermal imager to further analyze the detected suspicious LEDs, and finally uses the rework tool head to rework the confirmed problematic LEDs.

[0026] It should be explained that the display circuit board is an HDI board, and optionally, a Dingji HDI board can be used as the display circuit board. The high-resolution camera is an optical camera, and optionally, a Lingyun Optoelectronics BFS-PGE-50S5C-C can be used as the high-resolution camera. The modulated laser source is a modulated laser, and optionally, a THORLABS-Pigtailed-Laser-Diode-Mount can be used as the modulated laser source. The infrared thermal imager is a thermal imager, and optionally, a FLIR-A50 in-line thermal imager can be used as the infrared thermal imager. The rework tool head is a device used to rework problematic Mini LEDs. Suspicious Mini LEDs refer to Mini LEDs that have been installed on the display circuit board and may have defects. Mini LEDs are sub-millimeter light-emitting diodes, which are LED devices with a chip long side dimension between 100-300 micrometers.

[0027] S2. Use a high-resolution camera to perform a global scan of the display circuit board to obtain an initial optical image set. Based on the initial optical image set, identify multiple brightness uniformity indices and a set of coarse position coordinates. The set of coarse position coordinates includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices in the display circuit board.

[0028] In detail, the process of using a high-resolution camera to perform a global scan of the display circuit board to obtain an initial optical image set includes: Obtain a workbench, which includes a camera bracket and a circuit board placement area, wherein the camera bracket is located directly above the circuit board placement area; The display circuit board is fixed on the circuit board placement area of ​​the worktable to obtain the circuit board to be photographed; A high-resolution camera is fixed to a camera mount to obtain a fixed camera; Set the working mode of the circuit board to be photographed to the preset first color mode to obtain the working circuit board; A fixed camera was used to photograph the working circuit board to obtain a red light image; Based on the circuit board to be photographed, the preset second color mode, and the fixed camera, a green light image was confirmed. The blue light image was confirmed based on the circuit board to be photographed, the preset third color mode, and the fixed camera. By combining the red light images, green light images, and blue light images, an initial optical image set is obtained.

[0029] It should be explained that the workbench is the basic platform for the entire operation. The workbench includes a camera bracket and a circuit board placement area. The camera bracket is the bracket installed on the workbench for fixing the spectral camera, and the circuit board placement area is a specific area on the workbench for placing and fixing the circuit board to be tested.

[0030] It is understood that the circuit board to be photographed refers to the display circuit board placed in the circuit board placement area of ​​the workbench, the fixed camera refers to a high-resolution camera fixed on a camera bracket, the first color mode refers to the mode in which the display circuit board emits red light, the second color mode refers to the mode in which the display circuit board emits green light, and the third color mode refers to the mode in which the display circuit board emits blue light. The act of photographing the working circuit board with a fixed camera means: using a fixed camera to photograph an image of the surface of the working circuit board, which is a red light image. The method of photographing the surface of the working circuit board with a fixed camera is existing technology and will not be described in detail here. The green light image refers to the image of the surface of the working circuit board in the second color mode obtained by using a fixed camera, and the blue light image refers to the image of the surface of the working circuit board in the third color mode obtained by using a fixed camera.

[0031] It should be understood that the method for identifying a green light image based on the circuit board to be photographed, a preset second color mode, and a fixed camera, and the method for identifying a blue light image based on the circuit board to be photographed, a preset third color mode, and a fixed camera, are the same as the method for identifying a red light image based on the circuit board to be photographed, a preset first color mode, and a fixed camera. They will not be described again here. The initial optical image set is a collection of red light images, green light images, and blue light images.

[0032] Specifically, the determination of multiple brightness uniformity indices and a rough set of position coordinates based on the initial optical image set includes: The green light image in the initial optical image set is converted to grayscale to obtain a grayscale green light image; The vertices, length, and width of the circuit board were determined based on the grayscale green light image. The first and second adjacent edges are identified based on the vertices of the circuit board. The first neighboring point is determined based on the vertex of the circuit board and the first adjacent edge, wherein the distance between the first neighboring point and the vertex of the circuit board is the length of the board and the first neighboring point is located on the first adjacent edge; The second neighboring point is determined based on the vertex of the circuit board and the second neighboring edge, wherein the distance between the second neighboring point and the vertex of the circuit board is the width of the board and the second neighboring point is located on the second neighboring edge; A coordinate system is established based on the circuit board vertex, the first neighboring point, and the second neighboring point. The circuit board vertex is used as the origin of the coordinate system, the direction from the circuit board vertex to the first neighboring point is used as the positive x-axis of the coordinate system, and the direction from the circuit board vertex to the second neighboring point is used as the positive y-axis of the coordinate system. The image to be segmented is identified based on the coordinate system and grayscale green light image. The image to be segmented includes: the center coordinates of multiple LEDs, including: the center x coordinate and the center y coordinate. Based on the preset segmentation window and the image to be segmented, multiple brightness uniformity indices and rough position coordinate sets are identified.

[0033] It should be explained that the grayscale processing of the green light image in the initial optical image set refers to converting each pixel in the green light image in the initial optical image set to grayscale. Furthermore, the technique of converting each pixel in the green light image in the initial optical image set to grayscale is existing technology and will not be elaborated upon here. A grayscale green light image refers to a green light image after grayscale processing.

[0034] Understandably, the vertex of the circuit board is any vertex of the rectangle corresponding to the grayscale green light image, the board length refers to the length of the rectangle corresponding to the grayscale green light image, the board width refers to the width of the rectangle corresponding to the grayscale green light image, and the first adjacent side and the second adjacent side are the two sides of the rectangle corresponding to the grayscale green light image that are adjacent to the vertex of the circuit board.

[0035] Specifically, the process of identifying the image to be segmented based on the coordinate system and grayscale green light image includes: The grayscale green light image is binarized to obtain a binary green light image; Multiple LED emitting areas were identified based on binary green light images and a pre-built contour detection model; Perform the following operation for each of the multiple LED emitting areas: The coordinates of the LED center were determined based on the LED's luminous area. By summing the center coordinates of the LEDs, we obtain the center coordinates of multiple LEDs. The center coordinates of multiple LEDs are mapped onto a grayscale green light image to obtain the image to be segmented.

[0036] It should be explained that the binarization processing of the grayscale green image refers to: determining the relationship between the grayscale value of each pixel in the grayscale green image and a preset grayscale threshold, setting all pixels greater than the grayscale threshold to 255 (white), and all pixels less than or equal to the grayscale threshold to 0 (black). This results in a clear black-and-white binary green image. The grayscale threshold is a value manually set by the workers at the circuit board manufacturing plant; optionally, the grayscale threshold is 128. The binary green image refers to the grayscale green image after binarization processing.

[0037] For example, if the grayscale threshold is 128, then the relationship between the grayscale value of each pixel in the grayscale image and 128 is determined. If the grayscale value of the pixel is greater than 128, then the grayscale value of the pixel is set to 255; otherwise, the grayscale value of the pixel is set to 0.

[0038] Understandably, the main operating principle of the contour detection model is as follows: starting from the upper left corner of the binary green light image, scan line by line until an unvisited white pixel (a pixel with a pixel value of 255) is found. This white pixel is taken as the starting point of the contour. Starting from the starting point, check the pixels in its 8 neighboring areas (upper, lower, left, right, upper left, upper right, lower left, lower right). Find the next connected white pixel in a clockwise direction. When the white pixel returns to the starting point, or when no new white pixel can be found, summarize the white pixels to obtain multiple pixels. Connect the multiple pixels into a point sequence to obtain a boundary contour. Use the interior of the boundary contour as the LED light-emitting area. Continue scanning the image to find the next unvisited white pixel starting point. Repeat the above process until the entire image is scanned and multiple LED light-emitting areas are obtained. The above process is a publicly available technical solution and will not be described in detail here.

[0039] It should be explained that determining the LED center coordinates based on the LED emitting area means: identifying the smallest circumcircle of the LED emitting area, and using the center of the smallest circumcircle as the LED center coordinates. Mapping multiple LED center coordinates to a grayscale green image means: labeling the corresponding values ​​of multiple LED center coordinates in the grayscale green image. The grayscale green image containing multiple LED center coordinates is the image to be segmented.

[0040] Specifically, based on the preset segmentation window and the image to be segmented, multiple brightness uniformity indices and a rough set of position coordinates are determined, including: For each LED center coordinate in the image to be segmented, perform the following operation: Identify the center of the split window, align the center of the window with the center coordinates of the LED, and obtain the clipping window; The image to be segmented is cropped using a cropping window to obtain a segmented image; Summarize the segmented images to obtain multiple segmented images; Number the multiple segmented images to obtain multiple numbered images; Perform the following operation on each of the multiple numbered images: The window grayscale value and brightness uniformity index were determined based on the numbered image. Summarize the grayscale values ​​of the windows to obtain grayscale values ​​for multiple windows; By summing the brightness uniformity indices, multiple brightness uniformity indices are obtained. A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows.

[0041] Understandably, the window center refers to the intersection of the diagonals of the segmentation window. Aligning the window center with the LED center coordinates means moving the segmentation window so that the points corresponding to the window center and the LED center coordinates coincide. The cropping window refers to the segmentation window after the window center and LED center coordinates are aligned. Cropping the image to be segmented using the cropping window means taking a screenshot of the image within the acquisition window to obtain the segmented image. The method of taking a screenshot of the image within the acquisition window is existing technology and will not be elaborated here. The image within the acquisition window is the segmented image. Optionally, the segmentation window is a 50×50 pixel square.

[0042] For example, if the four segmented images are: image A, image B, image C and image D, then the multiple segmented images are numbered to obtain four numbered images: P1, P2, P3 and P4.

[0043] Specifically, the process of determining the window grayscale value and brightness uniformity index based on the numbered image includes: The image grayscale value set is determined based on the numbered image, wherein the image grayscale value set includes: multiple grayscale values; The window gray value is calculated based on multiple gray values ​​in the image gray value set. The calculation formula is as follows: in, Indicates the grayscale value of the window. The number of gray values ​​in the image's grayscale set. Represents the first of a set of gray values ​​in an image. One grayscale value; Multiple exposures are performed on the numbered image to obtain multiple exposed images; Perform the following operation on each of the multiple exposed images: Multiple grayscale values ​​were identified based on the exposed image; The window brightness is determined based on multiple processed grayscale values, where the window brightness is the average of the multiple processed grayscale values; The window brightness is summarized to obtain multiple window brightness values, where each window brightness corresponds one-to-one with the exposure image; The average window brightness is determined based on the brightness of multiple windows, where the average window brightness is the average of the brightness of multiple windows; The standard deviation of window brightness was determined based on the brightness of multiple windows, where the standard deviation of window brightness is the standard deviation of the brightness of multiple windows; The luminance uniformity index is calculated based on the average window luminance and the standard deviation of window luminance, using the following formula: in, Indicates the brightness uniformity index. Indicates the average window brightness. This represents the standard deviation of window brightness.

[0044] It should be explained that determining the image grayscale value set based on the numbered image means: reading the value of each pixel in the numbered image one by one; the value of each pixel in the numbered image is the image grayscale value, and the image grayscale value set is a collection of multiple image grayscale values. The window grayscale value reflects the brightness of the numbered image; the larger the window grayscale value, the brighter the numbered image.

[0045] It is understood that the multiple exposure processing of the numbered image refers to: sequentially adjusting the exposure value of the numbered image to a plurality of preset exposure adjustment values, and saving the adjusted numbered window image after each adjustment. The method of sequentially adjusting the exposure value of the numbered image to the preset exposure adjustment values ​​is existing technology and will not be described in detail here. The exposed image is the image after exposure processing. Optionally, the plurality of exposure adjustment values ​​are 0.5, 1, 1.5, and 2.0.

[0046] For example, if the preset exposure adjustment values ​​are 0.5, 1, 1.5, and 2.0, the exposure value of the numbered image is first adjusted to 0.5 to obtain the first exposed image. Then the exposure value of the numbered image is adjusted to 1.0 to obtain the second exposed image. This process continues until all exposure values ​​are adjusted and the exposed images are combined to obtain multiple exposed images.

[0047] Understandably, the brightness uniformity index is used to reflect the consistency of grayscale response of the numbered image under multiple exposure conditions. When the brightness uniformity index is high, it means that the target Mini LED has stable brightness performance under different exposure conditions and reliable light emission. When the brightness uniformity index is low, it means that the brightness performance of the Mini LED is unstable and there are potential defects.

[0048] It should be understood that the method for identifying multiple processed grayscale values ​​based on the exposed image is the same as the method for identifying the image grayscale value set based on the numbered image, and will not be repeated here. Processed grayscale values ​​refer to the values ​​of pixels in the exposed image.

[0049] Specifically, the determination of a rough set of location coordinates based on multiple window grayscale values ​​includes: The average window gray value is determined based on the gray values ​​of multiple windows, where the average window gray value is the average of the gray values ​​of multiple windows; The standard deviation of grayscale values ​​is calculated based on the grayscale values ​​of multiple windows and the average grayscale value of the window. The calculation formula is as follows: in, This represents the standard deviation of grayscale values. This represents the average window grayscale value. This represents the number of grayscale values ​​in a window among multiple window grayscale values. Represents the grayscale value of multiple windows. Each window's grayscale value; The grayscale threshold is calculated based on the average window grayscale value and the standard deviation of the grayscale value. The calculation formula is as follows: in, Indicates the grayscale threshold; A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows and the grayscale threshold.

[0050] It should be explained that the standard deviation of grayscale values ​​refers to the standard deviation of grayscale values ​​across multiple windows, and the grayscale threshold is a value calculated based on the average and standard deviation of grayscale values ​​from multiple windows, used as a boundary for judging the grayscale values ​​of a window. Determining a rough position coordinate set based on multiple window grayscale values ​​and the grayscale threshold means: traversing the grayscale values ​​of each window, if the window grayscale value satisfies the condition that the window grayscale value is less than the grayscale threshold, then the center of the corresponding numbered image is used as the rough position coordinate. Finally, the rough position coordinates are summarized to obtain the rough position coordinate set. The center of the numbered image refers to the intersection of the diagonals of the numbered image.

[0051] For example, if the grayscale values ​​of multiple windows are: P1: 90, P2: 95, P3: 102, P4: 110 and P5: 105, and the grayscale threshold is 100, then the suspicious images are numbered P1 and P2. Then the center of P1 and P2 is identified, and two rough position coordinates are obtained.

[0052] S3. For each of the multiple coarse position coordinates, perform the following operations: use a modulated laser source to irradiate the suspected Mini LED corresponding to the coarse position coordinate to obtain the irradiated LED, use an infrared thermal imager to monitor the temperature of the irradiated LED, and obtain a transient thermal response dataset.

[0053] It should be explained that irradiating the suspected Mini LED corresponding to the rough position coordinates using a modulated laser source means: using a modulated laser source to aim at and irradiate the Mini LED corresponding to the rough position coordinates, causing it to heat up. Irradiated LED refers to the suspected Mini LED after being irradiated by the modulated laser source. Monitoring the temperature of the irradiated LED using an infrared thermal imager means: using the high-speed imaging function of an infrared thermal imager to continuously record the dynamic process of the surface temperature change of the irradiated LED over time during and after irradiation by the modulated laser source, thereby generating a temperature change sequence in both time and space dimensions. This temperature change sequence in both time and space dimensions is the transient thermal response dataset.

[0054] S4. Extract thermal parameters from the transient thermal response dataset to obtain the peak temperature and response time.

[0055] It should be explained that the extraction of thermal parameters from the transient thermal response dataset refers to extracting the peak temperature and response time from the dataset. The peak temperature refers to the highest temperature that the surface of the irradiated LED can reach within the irradiation cycle of a single laser modulation pulse. For LEDs with material or structural defects, their heat dissipation capacity is poor, and heat accumulates more easily, resulting in a significantly higher peak temperature than normal LEDs. The response time is a kinetic parameter used to describe the rate of temperature change of the irradiated LED. In this scheme, it can be specifically defined as the time required for the surface temperature of the irradiated LED to rise to its peak temperature from the moment the laser irradiation begins. This time constant directly reflects the heating rate of the LED and is closely related to its heat capacity and heat dissipation conditions. Anomalies in the response time (usually manifested as being too fast or too slow) can effectively indicate whether there are structural defects within the LED that cause changes in its thermal characteristics.

[0056] S5. Based on the rough position coordinates, multiple brightness uniformity indices, initial optical image set, peak temperature and response time, the defect score is confirmed, the defect scores are summarized to obtain multiple defect scores, and the transient thermal response dataset is summarized to obtain multiple transient thermal response datasets.

[0057] Specifically, the defect score determined based on coarse location coordinates, multiple brightness uniformity indices, an initial optical image set, peak temperature, and response time includes: Based on the red light image and blue light image in the initial optical image set, as well as the rough position coordinates, the red window image and blue window image were identified. The red component set is identified based on the red window image, wherein the red component set includes multiple red pixel values; the blue component set is identified based on the blue window image, wherein the blue component set includes multiple blue pixel values. The window redness value is calculated based on multiple red pixel values ​​in the red component set; The window blue value is calculated based on multiple blue pixel values ​​in the blue component set; The red-blue difference index is calculated based on the redness and blueness values ​​of the window, using the following formula: in, This represents the red-blue difference index. Indicates the redness value of the window. Indicates the blueness value of the window. This is a preset adjustment coefficient; The target brightness uniformity index was determined based on the approximate location coordinates and multiple brightness uniformity indices. The defect score is calculated based on the target brightness uniformity index, red-blue difference index, peak temperature, and response time. The calculation formula is as follows: in, Indicates defect score. This represents the red-blue difference index. The preset red and blue standard index, Indicates peak temperature. Indicates response time. Indicates the uniformity index of target brightness. Represents the natural constant. The preset standard response time, is the hyperbolic tangent function, referring to taking the absolute value.

[0058] It should be explained that the process of identifying the red and blue window images based on the red and blue light images in the initial optical image set and the coarse position coordinates refers to mapping the coarse position coordinates to the red and blue light images respectively, thereby obtaining the red and blue light images to be segmented. Then, cropping windows are used to crop the red and blue light images to be segmented respectively. The red window image is the image obtained by cropping the red light image to be segmented using the cropping window, and the blue window image is the image obtained by cropping the blue light image to be segmented using the cropping window. The method for identifying the red component set based on the red window image and the method for identifying the blue component set based on the blue window image are the same as the method for identifying the image grayscale value set based on the numbered image, and will not be repeated here. The method for calculating the window red value based on multiple red pixel values ​​in the red component set and the method for calculating the window blue value based on multiple blue pixel values ​​in the blue component set are the same as the method for calculating the window grayscale value based on multiple grayscale values ​​in the image grayscale value set, and will not be repeated here.

[0059] It needs to be explained that the red and blue window images are essentially a single color image. The pixels in a color image include red, blue, and green channels. Therefore, the red pixel value is the brightness value of the red channel within the pixel matrix of the red window image, and the red component set is a collection of multiple red pixel values. Similarly, the blue pixel value is the brightness value of the blue channel within the pixel matrix of the blue window image, and the blue component set is a collection of multiple blue pixel values. The window redness value reflects the intensity of red light in the red window image; the larger the window redness value, the greater the intensity of red light in the red window image. The window blueness value reflects the intensity of blue light in the blue window image; the larger the window blueness value, the greater the intensity of blue light in the blue window image. The red-blue difference index reflects the relative intensity relationship between the red and blue components. The adjustment coefficient is a value manually set by the staff of the circuit board manufacturing plant; optionally, the adjustment coefficient is 1. Determining the target brightness uniformity index based on the coarse position coordinates and multiple brightness uniformity indices means using the brightness uniformity index corresponding to the coarse position coordinates as the target brightness uniformity index. The defect score reflects the severity of a problem with a Mini LED; a higher defect score indicates a more severe problem. Since abnormal response times (typically too fast or too slow) effectively indicate the presence of structural defects that alter thermal characteristics, a greater difference between the response time of a suspected Mini LED and that of a normal Mini LED—i.e., a response time that is too fast or too slow—will increase the calculated defect score. The red-blue standard index is a value manually set by the PCB manufacturing plant staff based on the average red-blue difference index of historically produced, qualified Mini LEDs. For example, if the historical average red-blue difference index of historically produced, qualified Mini LEDs is 1, then the red-blue standard index is 1. The standard response time is a value manually set by the PCB manufacturing plant staff based on the average time it takes for historically produced, qualified Mini LEDs to reach their peak temperature under tunable laser irradiation. For example, if the historical average time it takes for historically produced, qualified Mini LEDs to reach their peak temperature under tunable laser irradiation is 2 seconds, then the standard response time is 2 seconds. It should be noted that in the calculation of defect scores, only the values ​​of peak temperature and response time are substituted, and their dimensions are not considered.

[0060] S6. Based on multiple defect scores and multiple transient thermal response datasets, a defect analysis model is identified. The defect analysis model is then used to perform defect analysis on multiple transient thermal response datasets to obtain a defect label set.

[0061] Specifically, the defect analysis model identified based on multiple defect scores and multiple transient thermal response datasets includes: Multiple transient thermal response datasets are sampled to obtain a training subset, which includes: A dataset of transient thermal responses; A score set was determined based on a training subset and multiple defect scores. The score set includes: Each defect score; Based on the training subset A transient thermal response dataset and a scoring set The training model was confirmed by the defect scores and the pre-built analysis model; The training subset is removed from multiple transient thermal response datasets to obtain an updated transient thermal response dataset; The number of samples to be updated in the transient thermal response dataset is determined, where the number of samples is the number of transient thermal response datasets in the updated transient thermal response dataset; The sample size is compared with a preset threshold. If the sample size is greater than the threshold, the transient thermal response dataset is updated and divided into multiple transient thermal response datasets. The trained model is used as the analysis model. The process of sampling multiple transient thermal response datasets is repeated until the sample size is less than or equal to the threshold. The trained model is then used as the defect analysis model.

[0062] It should be explained that sampling multiple transient thermal response datasets refers to randomly sampling multiple transient thermal response datasets, and the training subset refers to the set obtained after sampling multiple transient thermal response datasets. Determining the score set based on the training subset and multiple defect scores means summarizing the defect scores corresponding to each transient thermal response dataset in the training subset and multiple defect scores to obtain the score set. The phrase "based on the training subset..." A transient thermal response dataset and a scoring set The defect scoring and pre-built analysis model confirm that the training model refers to: utilizing the training subset... A dataset of transient thermal responses and a scoring set A defect scoring training analysis model is used, wherein the analysis model adopts a convolutional neural network structure, the input is a transient thermal response dataset, and the output is the defect type, including: solder joint cold solder joint, chip crack, or material aging. The model utilizes a subset of training data... A dataset of transient thermal responses and a scoring set The method for training and analyzing a defect scoring model is existing technology and will not be elaborated here. Training a model refers to utilizing a subset of... A dataset of transient thermal responses and a scoring set The defect scoring training is used to train the analysis model. The quantity threshold is a value manually set by the staff of the circuit board manufacturing plant. Optional, the quantity threshold is 3. The defect analysis model refers to the training model obtained when the number of samples is less than or equal to the quantity threshold.

[0063] For example, if multiple transient thermal response datasets are P1, P2, P3, P4, and P5, and the training subsets are P2, P3, and P4, then the updated transient thermal response datasets obtained by removing the training subsets from the multiple transient thermal response datasets are P1 and P5.

[0064] It is understood that the defect analysis using the defect analysis model to perform defect analysis on multiple transient thermal response datasets means that each transient response dataset in the multiple transient thermal response datasets is input into the defect analysis model at one time, and the model is used to analyze the defect type. The defect label refers to the defect type analyzed by the model, and the defect label set is a collection of multiple defect labels.

[0065] S7. Based on the display circuit board, multiple defect scores, defect label set, and rework tool head, multiple rework LEDs are identified, and Mini LED defect location and rework are completed.

[0066] Specifically, the identification of multiple reworkable LEDs based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads includes: For each defect score in a set of multiple defect scores, perform the following operation: Compare the defect score with the preset score threshold. If the defect score is greater than or equal to the score threshold, the rough location coordinates corresponding to the defect score are used as the precise location coordinates. By summing the precise location coordinates, multiple precise location coordinates are obtained; For each of the multiple precise location coordinates, perform the following operation: The LED to be repaired was identified based on the display circuit board and its precise location coordinates. The target label was identified based on the defect label set and precise location coordinates; The target label is read to obtain the defect type, which includes: poor solder joint, chip crack, or material aging. If the defect type is a cold solder joint, the working mode of the repair tool head is set to the preset first mode to obtain the target tool head; Otherwise, set the working mode of the rework tool head to the preset second mode to obtain the target tool head; The target tool head is used to rework the LED to be repaired, and the repaired LED is obtained. The returned LEDs were compiled, resulting in multiple returned LEDs.

[0067] It should be explained that precise location coordinates refer to the approximate location coordinates corresponding to defect scores greater than or equal to the scoring threshold. The scoring threshold is a value manually set by the staff of the circuit board manufacturing plant; optionally, the scoring threshold is 85. Identifying the LED to be repaired based on the display circuit board and precise location coordinates means: identifying the suspicious Mini LED corresponding to the precise location coordinates on the display circuit board as the LED to be repaired. The suspicious Mini LED corresponding to the precise location coordinates on the display circuit board is the LED to be repaired. Identifying the target label based on the defect label set and precise location coordinates means: filtering out the defect labels corresponding to the transient thermal response data corresponding to the precise location coordinates from the defect label set; the defect label corresponding to the transient thermal response data corresponding to the precise location coordinates is the target label. Reading the target label means: reading the type of defect corresponding to the target label; the type of defect corresponding to the target label is the defect type. The target tool head refers to the rework tool head after mode settings. The first mode refers to the mode for performing heat soldering operations, where heat soldering refers to heating the LED to ensure a firm weld. The second mode refers to the mode for performing LED chip replacement operations. The term "repairing an LED using a target tool head" refers to repairing an LED on a circuit board under inspection using a target tool head. A reworked LED refers to an LED that has undergone rework.

[0068] For example, once the repair circuit board was obtained, Xiao Zhang completed the defect location and repair of the Mini LED.

[0069] Another embodiment of the present invention provides a method for Mini LED defect location and repair based on photothermal monitoring, comprising: In the above Figure 1 Based on the first embodiment shown, the step of obtaining multiple precise location coordinates based on multiple defect scores can also be replaced by the following steps: The defect mean and defect standard deviation are determined based on multiple defect scores, where the defect mean is the average of multiple defect scores and the defect standard deviation is the standard deviation of multiple defect scores. For each defect score in a set of multiple defect scores, perform the following operation: The standard defect score is calculated based on the defect score, the defect mean, and the defect standard deviation, using the following formula: in, Indicates standard defect score, This represents the mean defect value. Indicates the standard deviation of defects; By summing the standard defect scores, multiple standard defect scores are obtained. Cluster analysis was performed on multiple standard defect scores to obtain potential defect clusters, which include multiple standard defect scores. Confirm the number of scores for multiple standard defect scores in the potential defect cluster. If the number of scores is greater than or equal to 5, then multiple original defect scores are identified. The original defect scores are the defect scores corresponding to the standard defect scores. Multiple original defect scores are sorted in ascending order to obtain multiple sorted defect scores; Determine the parity of the number of scores. If the number of scores is even, then identify the first even sorting defect score, the second even sorting defect score, the third even sorting defect score, and the fourth even sorting defect score based on the multiple sorting defect scores. The first quartile is calculated based on the first even-sorted defect score and the second even-sorted defect score, using the following formula: in, Indicates the first quartile. This indicates the first even-ordered defect score. This indicates the second even-ordered defect score; The third quartile was identified based on the third even sort defect score and the fourth even sort defect score. If the number of scores is odd, then the first odd sorting defect score, the second odd sorting defect score, the third odd sorting defect score, and the fourth odd sorting defect score are determined based on the multiple sorting defect scores. The first quartile was identified based on the first odd sort defect score and the second odd sort defect score. The third quartile was identified based on the third odd ordering defect score and the fourth odd ordering defect score. The dynamic threshold is calculated based on the first quartile and the third quartile, using the following formula: in, Indicates dynamic threshold. Indicates the third quartile; For each of the multiple original defect scores, perform the following operation: Compare the original defect score with the dynamic threshold. If the original defect score is greater than or equal to the dynamic threshold, then the rough position coordinates corresponding to the original defect score are used as the precise position coordinates. By summing the precise location coordinates, multiple precise location coordinates are obtained; If the number of scores is less than 5, the rough position coordinates corresponding to multiple standard defect scores in the potential defect cluster will be used as multiple precise position coordinates.

[0070] It should be explained that the standard defect score refers to the defect score after standardization based on the defect mean and defect standard deviation. The cluster analysis of multiple standard defect scores refers to analyzing multiple standard defect scores using a clustering algorithm. The method of using a clustering algorithm to analyze multiple standard defect scores is existing technology and will not be elaborated here. Optionally, the K-means clustering algorithm can be used as the clustering algorithm. A potential defect cluster refers to the cluster obtained after analyzing multiple standard defect scores using a clustering algorithm.

[0071] For example, if the original defect scores are 11, 12, 10, 13, 15, and 14, then the original defect scores are sorted in ascending order to obtain the sorted defect scores as 10, 11, 12, 13, 14, and 15.

[0072] For example, if multiple ranking scores are 10, 11, 12, 13, 14, 15, 16, and 17, and the number of scores is 8 (an even number), then the first even ranking defect score, the second even ranking defect score, the third even ranking defect score, and the fourth even ranking defect score identified based on the multiple ranking defect scores are 11, 12, 15, and 16, respectively. The first even ranking defect score refers to the score among the multiple ranking scores when the number of scores is even. The second even-numbered ranking defect score refers to the score among multiple ranking scores when the number of scores is even. The third even-numbered ranking defect score refers to the score among multiple ranking scores when the number of scores is even. The fourth even-numbered ranking defect score refers to the score among multiple ranking scores when the number of scores is even. Each sorting defect score.

[0073] It should be understood that the methods for determining the third quartile based on the third even sorting defect score and the fourth even sorting defect score, the methods for determining the first quartile based on the first odd sorting defect score and the second odd sorting defect score, and the methods for determining the third quartile based on the third odd sorting defect score and the fourth odd sorting defect score are all the same as the method for calculating the first quartile based on the first even sorting defect score and the second even sorting defect score, and will not be repeated here.

[0074] For example, if multiple ranking scores are 10, 11, 12, 13, 14, 15, 16, 17, and 18, and the number of scores is 9 (an odd number), then the first odd ranking defect score, the second odd ranking defect score, the third odd ranking defect score, and the fourth odd ranking defect score identified based on the multiple ranking defect scores are 11, 12, 16, and 17, respectively. The first odd ranking defect score refers to the score among the multiple ranking scores when the number of scores is odd. The second odd ranking defect score refers to the score among multiple ranking scores when the number of scores is odd. The third odd ranking defect score refers to the score among multiple ranking scores when the number of scores is odd. The fourth odd ranking defect score refers to the score among multiple ranking scores when the number of scores is odd. Each sorting defect score.

[0075] Understandably, the first quartile refers to the ranking defect score at the lower 25% dividing point among multiple ranking defect scores, the third quartile refers to the ranking defect score at the upper 25% dividing point among multiple ranking defect scores, the dynamic threshold is the judgment boundary used to reflect whether there is a defect in the LED, and the precise location coordinates refer to the rough location coordinates corresponding to the original defect score that is greater than or equal to the dynamic threshold.

[0076] To address the problems described in the background section, this invention acquires a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board includes multiple suspected Mini LEDs. This invention facilitates the acquisition of initial optical images of the display circuit board using the high-resolution camera, providing a basis for subsequent analysis to determine a coarse set of positional coordinates. The high-resolution camera then performs a global scan of the display circuit board to obtain the initial optical image set. This initial image set provides a foundation for subsequent analysis, identifying multiple brightness uniformity indices and a coarse set of positional coordinates. These coarse coordinates correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. This invention reduces the amount of subsequent analysis and improves the accuracy of identifying defective Mini LEDs by first analyzing the initial optical images. To improve the accuracy of LED positioning, the following operations are performed for each of the multiple coarse position coordinates: The suspected MiniLED corresponding to the coarse position coordinate is illuminated using a modulated laser source, thus illuminating the LED. This allows the suspected MiniLED to heat up, facilitating the subsequent screening of defective MiniLEDs. The temperature of the illuminated LED is monitored using an infrared thermal imager to obtain a transient thermal response dataset. Thermal parameters are extracted from the transient thermal response dataset to obtain the peak temperature and response time. This provides a basis for calculating defect scores by acquiring the thermal parameters of the MiniLED during heating. Based on the coarse position coordinates, multiple brightness uniformity indices, an initial optical image set, peak temperature, and response time, defect scores are confirmed. Multiple defect scores are then summarized, and multiple transient thermal response datasets are obtained. This demonstrates that by calculating a defect score for each MiniLED corresponding to a coarse position coordinate, this invention provides a data foundation for identifying circuit boards to be repaired based on the defect scores, improving the accuracy of identifying defective MiniLEDs. To improve the accuracy of LED positioning and thus rework efficiency, a defect analysis model is established based on multiple defect scores and transient thermal response datasets. This embodiment of the invention trains a defect analysis model using multiple defect scores and transient thermal response datasets, providing a tool for subsequent defect type analysis. The defect analysis model is then used to analyze defects in multiple transient thermal response datasets to obtain a defect label set.As can be seen, this embodiment of the invention analyzes transient thermal response data using a defect analysis model to determine the defect type, providing support for subsequent LED rework based on the defect type. Based on the display circuit board, multiple defect scores, defect tag sets, and rework toolheads, multiple reworkable LEDs are identified, completing the Mini LED defect location and rework. This embodiment of the invention achieves precise rework by applying different rework strategies to different LEDs, improving the accuracy of locating defective Mini LEDs and thus increasing rework efficiency. Therefore, this invention can improve the accuracy of locating defective Mini LEDs, thereby improving rework efficiency.

[0077] like Figure 2 The diagram shown is a functional block diagram of a Mini LED defect location and repair system based on photothermal monitoring provided in an embodiment of the present invention.

[0078] The Mini LED defect location and repair system 100 based on photothermal monitoring described in this invention can be installed in electronic devices. Depending on the functions implemented, the Mini LED defect location and repair system 100 may include a basic image acquisition module 101, a coarse location confirmation module 102, a defect scoring calculation module 103, and a repair processing module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0079] The basic image acquisition module 101 is used to acquire the display circuit board, high-resolution camera, modulated laser source, infrared thermal imager and repair tool head. The display circuit board includes multiple suspected Mini LEDs. The high-resolution camera is used to perform a global scan of the display circuit board to obtain an initial optical image set. The coarse position confirmation module 102 is used to confirm multiple brightness uniformity indices and a coarse position coordinate set based on the initial optical image set. The coarse position coordinate set includes multiple coarse position coordinates, wherein the coarse position coordinates correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices in the display circuit board. The defect scoring calculation module 103 is used to perform the following operations for each of the multiple coarse position coordinates: irradiate the suspected Mini LED corresponding to the coarse position coordinate using a modulated laser source to obtain the irradiated LED; monitor the temperature of the irradiated LED using an infrared thermal imager to obtain a transient thermal response dataset; extract thermal parameters from the transient thermal response dataset to obtain the peak temperature and response time; confirm the defect score based on the coarse position coordinate, multiple brightness uniformity indices, the initial optical image set, the peak temperature, and the response time; and summarize the defect scores to obtain multiple defect scores. The rework processing and repair module 104 is used to summarize transient thermal response datasets to obtain multiple transient thermal response datasets. Based on multiple defect scores and multiple transient thermal response datasets, a defect analysis model is identified. The defect analysis model is used to perform defect analysis on multiple transient thermal response datasets to obtain a defect label set. Based on the display circuit board, multiple defect scores, defect label set, and rework tool head, multiple reworkable LEDs are identified, thus completing the Mini LED defect location and rework.

[0080] In detail, the modules in the Mini LED defect location and repair system 100 based on photothermal monitoring described in this embodiment of the invention employ the same methods as described above. Figure 1 The method for locating and repairing Mini LED defects based on photothermal monitoring described herein is the same as the method described above and can produce the same technical effect, so it will not be repeated here.

[0081] like Figure 3 The diagram shown is a structural schematic of an electronic device that implements a method for locating and repairing Mini LED defects based on photothermal monitoring, according to an embodiment of the present invention.

[0082] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a method program for Mini LED defect location and repair based on photothermal monitoring.

[0083] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a Mini LED defect location and repair method program based on photothermal monitoring, but also to temporarily store data that has been output or will be output.

[0084] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a method for locating and repairing Mini LED defects based on photothermal monitoring) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0085] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0086] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0087] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0088] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0089] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0090] The Mini LED defect location and repair method program based on photothermal monitoring, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following: The following items were obtained: a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board included multiple suspected Mini LEDs. A high-resolution camera is used to perform a global scan of the display circuit board to obtain an initial set of optical images. Based on the initial optical image set, multiple brightness uniformity indices and a set of coarse position coordinates were identified. The set of coarse position coordinates includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. For each of the multiple coarse position coordinates, perform the following operation: A modulated laser source is used to illuminate a suspected Mini LED corresponding to a rough position coordinate, thus obtaining the illuminated LED; The temperature of the irradiated LED was monitored using an infrared thermal imager to obtain a transient thermal response dataset; Thermal parameters were extracted from the transient thermal response dataset to obtain the peak temperature and response time; Defect scores were determined based on rough location coordinates, multiple brightness uniformity indices, initial optical image set, peak temperature, and response time. Summarize the defect scores to obtain multiple defect scores; By summarizing the transient thermal response datasets, multiple transient thermal response datasets are obtained; A defect analysis model was identified based on multiple defect scores and multiple transient thermal response datasets. Defect analysis was performed on multiple transient thermal response datasets using a defect analysis model to obtain a defect label set; Based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads, multiple reworkable LEDs were identified, completing the Mini LED defect location and rework.

[0091] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0092] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0093] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following: The following items were obtained: a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board included multiple suspected Mini LEDs. A high-resolution camera is used to perform a global scan of the display circuit board to obtain an initial set of optical images. Based on the initial optical image set, multiple brightness uniformity indices and a set of coarse position coordinates were identified. The set of coarse position coordinates includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. For each of the multiple coarse position coordinates, perform the following operation: A modulated laser source is used to illuminate a suspected Mini LED corresponding to a rough position coordinate, thus obtaining the illuminated LED; The temperature of the irradiated LED was monitored using an infrared thermal imager to obtain a transient thermal response dataset; Thermal parameters were extracted from the transient thermal response dataset to obtain the peak temperature and response time; Defect scores were determined based on rough location coordinates, multiple brightness uniformity indices, initial optical image set, peak temperature, and response time. Summarize the defect scores to obtain multiple defect scores; By summarizing the transient thermal response datasets, multiple transient thermal response datasets are obtained; A defect analysis model was identified based on multiple defect scores and multiple transient thermal response datasets. Defect analysis was performed on multiple transient thermal response datasets using a defect analysis model to obtain a defect label set; Based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads, multiple reworkable LEDs were identified, completing the Mini LED defect location and rework.

[0094] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0095] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0097] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for defect location and repair of Mini LEDs based on photothermal monitoring, characterized in that, The method includes: The following items were obtained: a display circuit board, a high-resolution camera, a modulated laser source, an infrared thermal imager, and a repair tool head. The display circuit board included multiple suspected Mini LEDs. A high-resolution camera is used to perform a global scan of the display circuit board to obtain an initial set of optical images. Based on the initial optical image set, multiple brightness uniformity indices and a set of coarse position coordinates were identified. The set of coarse position coordinates includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. For each of the multiple coarse position coordinates, perform the following operation: A modulated laser source is used to illuminate a suspected Mini LED corresponding to a rough position coordinate, thus obtaining the illuminated LED; The temperature of the irradiated LED was monitored using an infrared thermal imager to obtain a transient thermal response dataset; Thermal parameters were extracted from the transient thermal response dataset to obtain the peak temperature and response time; Defect scores were determined based on rough location coordinates, multiple brightness uniformity indices, initial optical image set, peak temperature, and response time. Summarize the defect scores to obtain multiple defect scores; By summarizing the transient thermal response datasets, multiple transient thermal response datasets are obtained; A defect analysis model was identified based on multiple defect scores and multiple transient thermal response datasets. Defect analysis was performed on multiple transient thermal response datasets using a defect analysis model to obtain a defect label set; Based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads, multiple reworkable LEDs were identified, completing the Mini LED defect location and rework.

2. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 1, characterized in that, The process of using a high-resolution camera to perform a global scan of the display circuit board to obtain an initial optical image set includes: Obtain a workbench, which includes a camera bracket and a circuit board placement area, wherein the camera bracket is located directly above the circuit board placement area; The display circuit board is fixed on the circuit board placement area of ​​the worktable to obtain the circuit board to be photographed; A high-resolution camera is fixed to a camera mount to obtain a fixed camera; Set the working mode of the circuit board to be photographed to the preset first color mode to obtain the working circuit board; A fixed camera was used to photograph the working circuit board to obtain a red light image; Based on the circuit board to be photographed, the preset second color mode, and the fixed camera, a green light image was confirmed. The blue light image was confirmed based on the circuit board to be photographed, the preset third color mode, and the fixed camera. By combining the red light images, green light images, and blue light images, an initial optical image set is obtained.

3. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 2, characterized in that, The initial optical image set identifies multiple brightness uniformity indices and a rough set of position coordinates, including: The green light image in the initial optical image set is converted to grayscale to obtain a grayscale green light image; The vertices, length, and width of the circuit board were determined based on the grayscale green light image. The first and second adjacent edges are identified based on the vertices of the circuit board. The first neighboring point is determined based on the vertex of the circuit board and the first adjacent edge, wherein the distance between the first neighboring point and the vertex of the circuit board is the length of the board and the first neighboring point is located on the first adjacent edge; The second neighboring point is determined based on the vertex of the circuit board and the second neighboring edge, wherein the distance between the second neighboring point and the vertex of the circuit board is the width of the board and the second neighboring point is located on the second neighboring edge; A coordinate system is established based on the circuit board vertex, the first neighboring point, and the second neighboring point. The circuit board vertex is used as the origin of the coordinate system, the direction from the circuit board vertex to the first neighboring point is used as the positive x-axis of the coordinate system, and the direction from the circuit board vertex to the second neighboring point is used as the positive y-axis of the coordinate system. The image to be segmented is identified based on the coordinate system and grayscale green light image. The image to be segmented includes: the center coordinates of multiple LEDs, wherein the center coordinates of the LEDs include: the center x coordinate and the center y coordinate. Based on the preset segmentation window and the image to be segmented, multiple brightness uniformity indices and rough position coordinate sets are identified.

4. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 3, characterized in that, The process of identifying the image to be segmented based on the coordinate system and grayscale green light image includes: The grayscale green light image is binarized to obtain a binary green light image; Multiple LED emitting areas were identified based on binary green light images and a pre-built contour detection model; Perform the following operation for each of the multiple LED emitting areas: The coordinates of the LED center were determined based on the LED's luminous area. By summing the center coordinates of the LEDs, we obtain the center coordinates of multiple LEDs. The center coordinates of multiple LEDs are mapped onto a grayscale green light image to obtain the image to be segmented.

5. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 4, characterized in that, The process, based on a preset segmentation window and the image to be segmented, identifies multiple brightness uniformity indices and a set of approximate position coordinates, including: For each LED center coordinate in the image to be segmented, perform the following operation: Identify the center of the split window, align the center of the window with the center coordinates of the LED, and obtain the clipping window; The image to be segmented is cropped using a cropping window to obtain a segmented image; Summarize the segmented images to obtain multiple segmented images; Number the multiple segmented images to obtain multiple numbered images; Perform the following operation on each of the multiple numbered images: The window grayscale value and brightness uniformity index were determined based on the numbered image. Summarize the grayscale values ​​of the windows to obtain grayscale values ​​for multiple windows; By summing the brightness uniformity indices, multiple brightness uniformity indices are obtained. A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows.

6. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 5, characterized in that, The process of determining the window grayscale value and brightness uniformity index based on the numbered image includes: The image grayscale value set is determined based on the numbered image, wherein the image grayscale value set includes: multiple grayscale values; Calculate the window gray value based on multiple gray values ​​in the image gray value set; Multiple exposures are performed on the numbered image to obtain multiple exposed images; Perform the following operation on each of the multiple exposed images: Multiple grayscale values ​​were identified based on the exposed image; The window brightness is determined based on multiple processed grayscale values, where the window brightness is the average of the multiple processed grayscale values; The window brightness is summarized to obtain multiple window brightness values, where each window brightness corresponds one-to-one with the exposure image; The average window brightness is determined based on the brightness of multiple windows, where the average window brightness is the average of the brightness of multiple windows; The standard deviation of window brightness was determined based on the brightness of multiple windows, where the standard deviation of window brightness is the standard deviation of the brightness of multiple windows; The brightness uniformity index is calculated based on the average window brightness and the standard deviation of window brightness.

7. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 6, characterized in that, The process of determining a rough set of location coordinates based on multiple window grayscale values ​​includes: The average window gray value is determined based on the gray values ​​of multiple windows, where the average window gray value is the average of the gray values ​​of multiple windows; The standard deviation of grayscale values ​​is calculated based on the grayscale values ​​of multiple windows and the average grayscale value of the window. The calculation formula is as follows: in, This represents the standard deviation of grayscale values. This represents the average window grayscale value. This represents the number of grayscale values ​​in a window among multiple window grayscale values. Represents the grayscale value of multiple windows. Each window's grayscale value; The grayscale threshold is calculated based on the average window grayscale value and the standard deviation of the grayscale value. A rough set of location coordinates was determined based on the grayscale values ​​of multiple windows and the grayscale threshold.

8. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 7, characterized in that, The defect score, determined based on rough location coordinates, multiple brightness uniformity indices, an initial optical image set, peak temperature, and response time, includes: Based on the red light image and blue light image in the initial optical image set, as well as the rough position coordinates, the red window image and blue window image were identified. The red component set is identified based on the red window image, wherein the red component set includes multiple red pixel values; the blue component set is identified based on the blue window image, wherein the blue component set includes multiple blue pixel values. The window redness value is calculated based on multiple red pixel values ​​in the red component set; The window blue value is calculated based on multiple blue pixel values ​​in the blue component set; The red-blue difference index is calculated based on the redness and blueness values ​​of the window. The target brightness uniformity index was determined based on the approximate location coordinates and multiple brightness uniformity indices. The defect score is calculated based on the target brightness uniformity index, red-blue difference index, peak temperature, and response time. The calculation formula is as follows: in, Indicates defect score. This represents the red-blue difference index. The preset red and blue standard index, Indicates peak temperature. Indicates response time. Indicates the uniformity index of target brightness. Represents the natural constant. The preset standard response time, Let be the hyperbolic tangent function, and let be the absolute value.

9. The method for Mini LED defect location and repair based on photothermal monitoring as described in claim 8, characterized in that, The method identifies multiple LEDs requiring rework based on the display circuit board, multiple defect scores, defect tag sets, and rework tool heads, including: For each defect score in a set of multiple defect scores, perform the following operation: Compare the defect score with the preset score threshold. If the defect score is greater than or equal to the score threshold, the rough location coordinates corresponding to the defect score are used as the precise location coordinates. By summing the precise location coordinates, multiple precise location coordinates are obtained; For each of the multiple precise location coordinates, perform the following operation: The LED to be repaired was identified based on the display circuit board and its precise location coordinates. The target label was identified based on the defect label set and precise location coordinates; The target label is read to obtain the defect type, which includes: poor solder joint, chip crack, or material aging. If the defect type is a cold solder joint, the working mode of the rework tool head is set to the preset first mode to obtain the target tool head; Otherwise, set the working mode of the rework tool head to the preset second mode to obtain the target tool head; The target tool head is used to rework the LED to be repaired, and the repaired LED is obtained. The returned LEDs were compiled, resulting in multiple returned LEDs.

10. A Mini LED defect location and repair system based on photothermal monitoring, characterized in that, The system includes: The basic image acquisition module is used to acquire images of the display circuit board, high-resolution camera, modulated laser source, infrared thermal imager, and repair tool head. The display circuit board includes multiple suspected Mini LEDs. The high-resolution camera performs a global scan of the display circuit board to obtain an initial optical image set. The coarse position confirmation module is used to confirm multiple brightness uniformity indices and a coarse position coordinate set based on the initial optical image set. The coarse position coordinate set includes multiple coarse position coordinates, which correspond one-to-one with the suspected Mini LEDs and brightness uniformity indices on the display circuit board. The defect scoring calculation module performs the following operations for each of the multiple coarse location coordinates: irradiating the suspected Mini LED corresponding to the coarse location coordinate using a modulated laser source to obtain the irradiated LED; monitoring the temperature of the irradiated LED using an infrared thermal imager to obtain a transient thermal response dataset; extracting thermal parameters from the transient thermal response dataset to obtain the peak temperature and response time; confirming the defect score based on the coarse location coordinates, multiple brightness uniformity indices, the initial optical image set, the peak temperature, and the response time; and summarizing the defect scores to obtain multiple defect scores. The rework processing and repair module is used to summarize transient thermal response datasets, obtain multiple transient thermal response datasets, identify a defect analysis model based on multiple defect scores and multiple transient thermal response datasets, perform defect analysis on multiple transient thermal response datasets using the defect analysis model, obtain a defect label set, identify multiple reworkable LEDs based on the display circuit board, multiple defect scores, defect label set, and rework tool head, and complete the Mini LED defect location and rework.

Images