Tgv laser drilling position optimization method, device, equipment and medium

Abstract

The TGV laser drilling position optimization method, device, equipment and medium provided by the embodiments of the present disclosure comprise: obtaining a white sheet detection image, a positioning point image and a CAD design file of a glass substrate to be processed; determining defect data of the glass substrate to be processed according to the white sheet detection image; determining target defect positions of each defect point in the defect data in a target coordinate system according to the positioning point image; determining an extended risk area according to the through hole information of each through hole, and determining an interference risk value between each through hole and each defect point in the defect data according to the target defect positions of each defect point in the defect data in the target coordinate system and the extended risk area of each through hole; when the interference risk value between a target through hole and a target defect point is greater than or equal to a preset interference risk value, optimizing the hole position of the target through hole according to the hole position allowable offset range constraint condition, the hole spacing constraint condition and the forbidden entry area constraint condition. Improve the utilization rate of the glass substrate to be processed.

Description

Technical Field

[0001] This invention relates to the field of TVG processing technology and related technical fields, specifically to a method, apparatus, equipment and medium for optimizing the position of TGV laser drilling. Background Technology

[0002] Through-Glass Via (TGV) processes typically use glass substrates as the carrier to form vertical interconnect structures through laser induction, etching, cleaning, hole metallization, or conductive paste filling. Due to the low dielectric loss, high dimensional stability, good insulation, and suitability for high-frequency packaging, TGV is increasingly used in advanced packaging, RF devices, optoelectronic integration, sensor packaging, and high-density interconnects. In the TGV process, the glass substrate may already have defects such as blistering, foreign matter, scratches, microcracks, edge chipping, contamination, or localized stress anomalies before entering the laser induction process. Some defects do not directly lead to scrapping at the blank wafer stage, but if they are located near subsequent TGV via locations, laser induction areas, via wall formation areas, or interconnection areas, they may be magnified into serious defects such as blind vias, rough via walls, cracks, filled voids, high resistance, or open circuits during laser induction, etching, via wall formation, conductive paste filling, or electrical testing.

[0003] Existing AOI equipment is typically used for defect detection and classification of images from a specific workstation, with the results primarily used for post-processing sorting or manual review. For defects in the TGV wafer feeding stage, current solutions usually only determine whether the defect exceeds the feeding standard, lacking a mechanism to link the wafer defect coordinates to subsequent CAD hole positions, equipment positioning errors, and process constraints. This results in a large number of glass substrates that could be salvaged through feedforward avoidance being directly intercepted, or conversely, some potentially problematic defects located near critical hole positions being allowed through, causing higher value losses in subsequent processes. Summary of the Invention

[0004] In view of this, the embodiments described herein provide a method for optimizing the drilling position of TGV lasers to improve the utilization rate of the glass substrate to be processed.

[0005] Firstly, based on the content of this disclosure, a method for optimizing the position of TGV laser drilling is provided, including: Acquire the blank inspection image, positioning point image, and CAD design file of the glass substrate to be processed. The CAD design file includes the through hole information, the allowable offset range constraint of the hole position, the hole spacing constraint, and the no-entry area constraint. The through hole information includes the hole center, hole diameter, circuit connection relationship, and the hole position process influence area. Based on the white film inspection image, the defect data of the glass substrate to be processed is determined, wherein the defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level and defect severity corresponding to each defect point; Based on the positioning point image, determine the target defect position of each defect point in the defect data in the target coordinate system; Based on the through hole information of each through hole, the extended risk area is determined, and based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole, the interference risk value between each through hole and each defect point in the defect data is determined. When the interference risk value between the target through hole and the target defect point is greater than or equal to the preset interference risk value, the position of the target through hole is optimized according to the allowable offset range constraint of the target through hole, the hole spacing constraint, and the forbidden area constraint.

[0006] In some embodiments of this disclosure, determining the defect data of the glass substrate to be processed based on the blank film inspection image includes: After preprocessing the white film detection image, the preprocessed white film detection image is further processed based on image segmentation and contour extraction to determine the defect contour of each defect point in the white film detection image. Based on the defect contours of each defect point in the white film detection image, determine the defect type, defect center coordinates, defect size, and defect confidence level of each defect point in the white film detection image; The severity of each defect point is determined based on the defect type and size of each defect point in the white film detection image.

[0007] In some embodiments of this disclosure, determining the target defect position in the target coordinate system based on the positioning point image includes: Based on the positioning point image, determine the transformation relationship between the target coordinate system and the image coordinate system; Based on the defect locations corresponding to each defect point in the defect data and the transformation relationship between the target coordinate system and the image coordinate system, the target defect location in the target coordinate system of each defect point in the defect data is determined.

[0008] In some embodiments of this disclosure, determining the expansion risk area based on the through-hole information of each through-hole includes: Acquire the positioning error information of the defect detection algorithm, the registration error information of the positioning point image, and the motion error information of the motion platform carrying the glass substrate to be processed; Based on the positioning error information, the registration error information, and the motion error information, determine the safety margin information; Based on the process influence zone of each through hole and the safety margin information, the extended risk area is determined.

[0009] In some embodiments of this disclosure, determining the interference risk value between each through-hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through-hole includes: Based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through hole in the defect data, determine the overlapping area of ​​the defect area of ​​each defect point and the expansion risk area of ​​each through hole. Based on the target defect position of each defect point in the target coordinate system and the through hole information of each through hole in the defect data, determine the distance information between the center point of each defect point and the center point of each through hole. Based on the overlapping area of ​​the extended risk areas of each defect point and each via, the distance information between the center point of the defect point and the center point of each via, the defect type, defect confidence, and defect severity of each defect point, the interference risk value between each via and each defect point in the defect data is determined.

[0010] In some embodiments of this disclosure, optimizing the position of the target through-hole based on the allowable offset range constraint, the hole spacing constraint, and the no-entry zone constraint includes: With the goal of reducing the interference risk between the target through hole and each defect point in the defect data, the hole position of the target through hole is optimized by using the allowable offset range constraint of the target through hole, the hole spacing constraint, and the forbidden area constraint.

[0011] In some embodiments of this disclosure, it also includes: Based on the optimization results, the target hole position information for each through hole is determined, and a target CAD design file executable by the laser drilling equipment is generated.

[0012] Secondly, according to this disclosure, a TGV laser drilling position optimization device is provided, comprising: The information acquisition module is used to acquire the blank inspection image, positioning point image and CAD design file of the glass substrate to be processed. The CAD design file includes the through hole information, the allowable offset range constraint of the hole position, the hole spacing constraint and the no-entry area constraint. The through hole information includes the hole center, hole diameter, line connection relationship and hole position process influence area. The defect data determination module is used to determine the defect data of the glass substrate to be processed based on the white film inspection image. The defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level, and defect severity corresponding to each defect point. The defect coordinate determination module is used to determine the target defect position of each defect point in the defect data in the target coordinate system based on the positioning point image. The interference risk value determination module is used to determine the extended risk area based on the through hole information of each through hole, and to determine the interference risk value between each through hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole. The through-hole position optimization module is used to optimize the position of the target through-hole according to the allowable offset range constraint of the target through-hole, the hole spacing constraint, and the forbidden area constraint when the interference risk value between the target through-hole and the target defect point is greater than or equal to a preset interference risk value.

[0013] Thirdly, according to this disclosure, a computer device is provided, comprising: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors perform the method as described in any of the first aspects.

[0014] Fourthly, according to this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the methods described in any of the first aspects.

[0015] The TGV laser drilling position optimization method provided in this embodiment first acquires a blank inspection image, a positioning point image, and a CAD design file of the glass substrate to be processed; then, based on the blank inspection image, it determines the defect data of the glass substrate to be processed; and based on the positioning point image, it determines the target defect position of each defect point in the defect data in the target coordinate system; further, based on the through-hole information of each through-hole, it determines the expansion risk area, and based on the target defect position of each defect point in the defect data in the target coordinate system and the expansion risk area of ​​each through-hole, it determines the interference risk value between each through-hole and each defect point in the defect data; finally, when there is an interference risk value between the target through-hole and the target defect point that is greater than or equal to a preset interference risk value, the hole position of the target through-hole is optimized according to the hole position allowable offset range constraint, hole spacing constraint, and forbidden area constraint. In the glass substrate feeding stage, defect data is first identified, and the defect point positions in the defect data are unified to the global coordinate system of the glass through positioning point images. Then, based on the defect severity of each defect point, the interference ratio between the defect and the process influence area of ​​the hole position, the defect type, and the defect confidence level, the interference risk value of the through hole is calculated. Finally, with the goal of reducing the interference risk value, under the conditions of meeting the design, process, equipment, and safety margin constraints, the position of the through hole is adaptively optimized. This realizes the transformation of the defect detection results of the glass substrate in the blank stage from "post-sorting information" to "forward process decision information". It can actively avoid fatal defects before laser induction or drilling, improve the utilization rate of the glass substrate to be processed, and avoid uncontrollable blind processing.

[0016] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of the embodiments of this application and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, specific implementation methods of this application are described below. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments will be briefly described below. It should be understood that the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure, wherein: Figure 1 This is a flowchart illustrating a method for optimizing the position of TGV laser drilling provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a TGV laser drilling position optimization device provided in an embodiment of this disclosure; Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this disclosure.

[0018] In the accompanying diagram, markers with the same last two digits correspond to the same elements. It should be noted that the elements in the diagram are schematic and not drawn to scale. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are also within the scope of protection of this disclosure.

[0020] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this subject matter pertains. It will be further understood that terms such as those defined in commonly used dictionaries shall be interpreted as having the meaning consistent with their meaning in the context of the specification and in the relevant art, and shall not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, the statement of “connecting” or “coupling” two or more parts together shall mean that these parts are directly joined together or joined through one or more intermediate components.

[0021] The term "embodiment" as used herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of the phrase "embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] In this article, the terms "or" or "or" are merely a way of describing the relationship between related objects, indicating that there can be three kinds of relationships. For example, A or B can mean that only A exists, both A and B exist, or only B exists.

[0023] Furthermore, in all embodiments of this disclosure, terms such as “first” and “second” are used only to distinguish one component (or part of a component) from another component (or another part of a component).

[0024] In the description of this application, unless otherwise stated, "multiple" means two or more (including two), and similarly, "multiple groups" means two or more (including two groups).

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0026] Based on the problems existing in the prior art, this disclosure provides a method for optimizing the position of TGV laser drilling. Figure 1 This is a flowchart illustrating a TGV laser drilling position optimization method provided in an embodiment of this disclosure, as shown below. Figure 1 As shown, the TGV laser drilling position optimization method includes: S110. Obtain the blank inspection image, positioning point image, and CAD design file of the glass substrate to be processed.

[0027] The CAD design files include through-hole information, allowable offset range constraints, hole spacing constraints, and no-entry area constraints for each through-hole. The through-hole information includes hole center, hole diameter, circuit connection relationship, and hole location process influence zone. The hole location process influence zone is determined based on laser spot, heat-affected zone, etching extension range, hole wall formation area, and equipment process.

[0028] Specifically, blank inspection images refer to high-resolution images taken by automated optical inspection (AOI) equipment before the glass substrate to be processed enters processes such as laser drilling. Blank inspection images contain information used to identify various defects on the glass surface, such as bubbles, scratches, foreign objects, and cracks.

[0029] A positioning point image refers to an image of positioning markers on a glass substrate that has been specially photographed. The positioning point image contains specific patterns (such as crosses or circles) that are preset on the glass substrate, serving as a unified reference for coordinate registration between different devices and processes.

[0030] CAD design files are engineering files containing all design information of the glass substrate to be processed. They include key constraints such as the location of all through holes, allowable offset range of hole positions, hole spacing constraints, and no-entry area constraints.

[0031] Furthermore, as a preferred implementation method, when acquiring the blank inspection images, positioning point images, and CAD design files of the glass substrate to be processed, the method also includes acquiring the identification information of the glass substrate to be processed. This identification information is a unique identifier for the glass substrate; it is typically a string of codes containing information such as the production line and batch number. It serves as the core "identity card" for tracking all production data and inspection results of this glass substrate from its initial input to its finished product. By acquiring the identification information of the glass substrate to be processed, it is possible to link all production data and inspection results of this glass substrate from its initial input to its finished product based on this identification information.

[0032] S120. Determine the defect data of the glass substrate to be processed based on the white film inspection image.

[0033] The defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level, and defect severity for each defect point.

[0034] In a specific implementation, the defect data of the glass substrate to be processed is determined based on the blank inspection image, including: after preprocessing the blank inspection image, processing the preprocessed blank inspection image based on image segmentation and contour extraction, and determining the defect contour of each defect point in the blank inspection image; based on the defect contour of each defect point in the blank inspection image, determining the defect type, defect center coordinates, defect size, and defect confidence of each defect point in the blank inspection image; and based on the defect type and defect size of each defect point in the blank inspection image, determining the defect severity of each defect point.

[0035] Since the original unprocessed glass substrate inspection images contain a large amount of noise and background information, preprocessing is performed to suppress interference and highlight defect features, creating optimal conditions for subsequent inspection. Preprocessing includes brightness and illumination correction, image stitching, noise suppression, and background modeling and differencing. Brightness and illumination correction refers to eliminating interference caused by uneven illumination through methods such as flat-field correction and dark-field correction. Image stitching refers to seamlessly stitching multiple local images into a complete image for large-size glass substrates. Noise suppression refers to smoothing the image using algorithms such as Gaussian filtering and mean filtering to reduce sensor noise. Background modeling and differencing involves constructing a defect-free standard inspection image and comparing the unprocessed glass substrate inspection image with the standard inspection image; the difference area represents the possible defect area in the unprocessed glass substrate inspection image, i.e., the defect area corresponding to each defect point.

[0036] After preprocessing the blank film detection image, the image is first divided into defect areas and normal areas through image segmentation. The pixel values ​​included in the defect area are assigned 1, and the pixel values ​​included in the normal area are assigned 0. Then, the precise contour of each defect area is extracted, which is the defect contour of each defect point in the blank film detection image.

[0037] After determining the defect contours of each defect point, it is necessary to analyze the characteristics of the defect contours to determine the defect type and calculate the defect size and center coordinates. Specifically, based on the defect contours of each defect point, the geometric and morphological features of each defect point are determined. Then, based on the pixel information of the corresponding defect region, the grayscale features of each defect point are determined. Finally, based on the geometric, morphological, and grayscale features of each defect point, the defect type is determined. For example, a long and thin defect (with a large aspect ratio) may be classified as a "scratch" type defect.

[0038] Furthermore, after determining the defect profile of each defect point, the defect center coordinates and defect size of each defect point can be directly calculated.

[0039] The confidence level of each defect point is a key indicator for measuring the reliability of the detection results. It can be comprehensively evaluated by analyzing whether the defect features of each extracted defect point are complete and clear. For example, defects with clear outlines and significant features usually have higher confidence levels.

[0040] Defect severity is a physical / process indicator that describes how bad the defect itself is and how destructive it is to subsequent TGV laser drilling and etching. After determining the defect type and size of each defect point, the defect severity of each defect point can be determined based on these factors.

[0041] Finally, all the information is integrated into structured defect data, and each defect data is a data object containing fields such as defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level, and defect severity.

[0042] S130. Based on the positioning point image, determine the target defect position of each defect point in the defect data in the target coordinate system.

[0043] In a specific implementation, determining the target defect position of each defect point in the defect data in the target coordinate system based on the positioning point image includes: determining the transformation relationship between the target coordinate system and the image coordinate system based on the positioning point image; and determining the target defect position of each defect point in the defect data in the target coordinate system based on the defect position corresponding to each defect point included in the defect data and the transformation relationship between the target coordinate system and the image coordinate system.

[0044] Since the through-hole information of each through-hole in the CAD design file is the coordinate information of the target coordinate system (i.e., the global coordinate system of the glass), once the positioning point is determined, the coordinate information of the positioning point in the target coordinate system can be obtained. At this time, based on the positioning point image, the coordinate information of the positioning point in the image coordinate system can be obtained. Therefore, based on the coordinate information of the positioning point in the target coordinate system and the coordinate information of the positioning point in the image coordinate system, the transformation relationship between the target coordinate system and the image coordinate system can be determined. Then, based on the defect position corresponding to each defect point in the defect data and the transformation relationship between the target coordinate system and the image coordinate system, the target defect position of each defect point in the defect data in the target coordinate system can be determined.

[0045] It should be noted that the target coordinate system can be a coordinate system with the plane where the glass substrate is located as the XOY plane and a certain point in the plane where the glass substrate is located as the origin.

[0046] S140. Based on the through hole information of each through hole, determine the extended risk area, and based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole, determine the interference risk value between each through hole and each defect point in the defect data.

[0047] In a specific implementation, determining the extended risk area based on the through-hole information includes: acquiring the positioning error information of the defect detection algorithm, the registration error information of the positioning point image, and the motion error information of the motion platform carrying the glass substrate to be processed; determining the safety margin information based on the positioning error information, registration error information, and motion error information; and determining the extended risk area based on the hole position process influence area and safety margin information of each through-hole.

[0048] The extended risk area is a dynamic safety area corresponding to each via. Its core function is to serve as a quantitative basis for determining whether defects in the glass substrate to be processed will pose a risk to the via.

[0049] On the one hand, the process influence zone of each through hole is determined based on the hole diameter of each through hole designed, the heat influence range generated by the laser beam forming each through hole during the process of forming through holes in the glass substrate to be processed, the range of the hole wall of each through hole being corroded and expanded in the chemical etching step, and the space occupied by the hole wall of each through hole in the final formed.

[0050] On the other hand, safety margin information is determined based on the process error under the current process flow. Specifically, firstly, the positioning error information of the defect detection algorithm, the registration error information of the positioning point image, and the motion error information of the motion platform carrying the glass substrate to be processed are obtained. Then, the safety margin information is determined based on the positioning error information, registration error information, and motion error information.

[0051] Finally, the boundary of the process influence zone of the obtained hole position is uniformly extended outward by the width of a safety margin information, which is the extended risk area corresponding to each through hole.

[0052] In a specific implementation, based on the target defect position of each defect point in the defect data in the target coordinate system and the expansion risk area of ​​each through hole, the interference risk value between each through hole and each defect point in the defect data is determined. This includes: determining the overlapping area of ​​the defect area of ​​each defect point and the expansion risk area of ​​each through hole based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through hole; determining the distance information between the center point of each defect point and the center point of each through hole based on the target defect position of each defect point in the target coordinate system and the through hole information of each through hole; and determining the interference risk value between each through hole and each defect point in the defect data based on the overlapping area of ​​the expansion risk area of ​​each defect point and each through hole, the distance information between the center point of each defect point and the center point of each through hole, the defect type, defect confidence, and defect severity of each defect point.

[0053] First, based on the target defect location of each defect point in the target coordinate system and the expansion risk area of ​​each through hole, calculate the overlap ratio between the defect area of ​​each defect point and the expansion risk area of ​​each through hole. For example, the defect area corresponding to the j-th defect point... and the expansion risk area of ​​the i-th via The overlap ratio between them satisfies:

[0054] Then, based on the target defect position of each defect point in the target coordinate system and the through hole information of each through hole in the defect data, the distance information between the center point of each defect point and the center point of each through hole is determined. For example, the center point of the j-th defect point... The center point of the i-th through hole The distance information satisfies:

[0055] Finally, based on the overlapping area of ​​each defect point and each via's extended risk area, the distance between the center point of the defect point and the center point of each via, the defect type, defect confidence, and defect severity of each defect point, the interference risk value between each via and each defect point in the defect data is determined.

[0056] It should be noted that the specific implementation process for determining the interference risk value between each via and each defect point in the defect data, based on the overlapping area of ​​each defect point and each via's extended risk area, the distance information between the center point of the defect point and the center point of each via, the defect type, defect confidence level, and defect severity of each defect point, is as follows: Based on the overlap ratio, distance information, defect type, defect confidence level, and defect severity of each defect point, their respective proportional scores are determined. Then, based on the overlap ratio, distance information, the proportional scores corresponding to the defect type, defect confidence level, and defect severity of each defect point, as well as their respective weighted values, the interference risk value between each via and each defect point in the defect data is determined.

[0057] S150. When the interference risk value between the target through hole and the target defect point is greater than or equal to the preset interference risk value, the position of the target through hole is optimized according to the constraints of the allowable offset range of the target through hole position, the hole spacing constraints, and the forbidden area constraints.

[0058] As a specific implementation method, with the goal of reducing the interference risk between the target through hole and each defect point in the defect data, the hole position of the target through hole is optimized by using the allowable offset range constraint of the target through hole position, the hole spacing constraint, and the forbidden area constraint.

[0059] The optimization constraints include: 1. Allowable offset range constraint for hole position: ||Δp i || ≤ R i , where R i Wherein is the maximum offset radius allowed by CAD or process. , ( , ) represents the coordinate information of the i-th hole position before optimization. , () represents the optimized coordinates of the i-th hole position; 2. Hole spacing constraint: distance( , The hole spacing constraint condition (≥ d_min) can prevent insufficient hole spacing from causing etched vias, short circuits, or reduced structural strength. The optimized coordinates of the i-th hole position are... The optimized coordinates of the j-th hole adjacent to the i-th hole. 3. Restricted Area Constraints: p' i The coordinate information must not overlap with the coordinate information of the restricted area.

[0060] If multiple feasible solutions are obtained through optimization, the hole position optimization strategy with the lowest interference risk value can be selected; if no feasible solution exists, the reason for unavoidable issues is output. For example, the defect coverage area is too large, the allowable offset range of the hole position is too small, the distance between adjacent holes is too restricted, the prohibited area overlaps with the defect, the equipment accuracy is insufficient, or the risk reduction ratio does not meet the minimum benefit threshold.

[0061] After determining the optimization strategy, the hole position information of each through hole can be optimized according to the optimization strategy to obtain the target hole position information of each through hole. Based on the target hole position information of each through hole, an executable target CAD design file for laser drilling equipment can be generated. This realizes the transformation of the defect detection results of the glass substrate in the blank stage into an executable compensation scheme before subsequent laser drilling, reducing the scrapping of the entire glass substrate or the waste of subsequent high-value processes due to local defects. It has clear industrial application value.

[0062] For example, the glass substrate to be processed has a size of 530 mm × 530 mm. First, a bubbling defect is detected in the glass substrate based on the white film inspection image. The defect location is (X=215.350 mm, Y=318.220 mm), and the projected area is 0.012 mm². The center of a certain through hole is obtained from the CAD design file as (X=215.390 mm, Y=318.240 mm). The radius of the process influence zone of the through hole is 35 μm, and the expansion risk area of ​​the through hole is 50 μm. The interference risk value ρ between the defect point and the expansion risk area is calculated to be 0.42. Since the interference risk value ρ exceeds the preset threshold of 0.25, the through hole is marked as a high-risk through hole. At this point, candidate holes are searched within the allowable offset range of the hole position. It is found that when the hole position is offset in the direction of (+32 μm, -18 μm), the interference risk value decreases from 0.42 to 0.03, and still satisfies the hole spacing constraint, the forbidden area constraint, and the PAD connection constraint. At this point, the target hole position information and interference risk value of the through hole are output.

[0063] If there are adjacent through holes around the through hole and the hole spacing between the through hole and the through hole does not meet the hole spacing constraint condition, the entire group of through holes in the local area where the through hole is located can be shifted as a whole, or the unavoidable reason can be output.

[0064] The TGV laser drilling position optimization method provided in this embodiment first acquires a blank inspection image, a positioning point image, and a CAD design file of the glass substrate to be processed; then, based on the blank inspection image, it determines the defect data of the glass substrate to be processed; and based on the positioning point image, it determines the target defect position of each defect point in the defect data in the target coordinate system; further, based on the through-hole information of each through-hole, it determines the expansion risk area, and based on the target defect position of each defect point in the defect data in the target coordinate system and the expansion risk area of ​​each through-hole, it determines the interference risk value between each through-hole and each defect point in the defect data; finally, when there is an interference risk value between the target through-hole and the target defect point that is greater than or equal to a preset interference risk value, the hole position of the target through-hole is optimized according to the hole position allowable offset range constraint, hole spacing constraint, and forbidden area constraint. In the glass substrate feeding stage, defect data is first identified using an AOI system, and the defect point positions in the defect data are unified to the global coordinate system of the glass through positioning point images. Then, the through hole information, hole position process influence zone, hole position allowable offset range constraints, hole spacing constraints, and forbidden area constraints of each through hole in the CAD design file are analyzed. Then, based on the defect severity of each defect point, the interference ratio between the defect and the hole position process influence zone, the defect type, and the defect confidence, the interference risk value of the through hole is calculated. Finally, with the goal of reducing the interference risk value, under the condition of meeting the design, process, equipment, and safety margin constraints, the position of the through hole is adaptively optimized. This realizes the transformation of the defect detection results of the glass substrate in the blank stage from "post-sorting information" to "forward process decision information". It can actively avoid fatal defects before laser induction or drilling, improve the utilization rate of the glass substrate to be processed, and avoid uncontrollable blind processing.

[0065] Based on the above embodiments, this disclosure also provides a TGV laser drilling position optimization device. Figure 2 This is a schematic diagram of the structure of a TGV laser drilling position optimization device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, the TGV laser drilling position optimization device includes: The information acquisition module 210 is used to acquire the white film inspection image, positioning point image and CAD design file of the glass substrate to be processed. The CAD design file includes the through hole information, the allowable offset range constraint of the hole position, the hole spacing constraint and the no-entry area constraint. The through hole information includes the hole center, hole diameter, line connection relationship and hole position process influence area. The defect data determination module 220 is used to determine the defect data of the glass substrate to be processed based on the white film inspection image. The defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level and defect severity corresponding to each defect point. The defect coordinate determination module 230 is used to determine the target defect position in the target coordinate system of each defect point in the defect data based on the positioning point image. The interference risk value determination module 240 is used to determine the extended risk area based on the through hole information of each through hole, and to determine the interference risk value between each through hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole. The through-hole position optimization module 250 is used to optimize the position of the target through-hole according to the constraints of the allowable offset range of the target through-hole, the hole spacing constraints, and the forbidden area constraints when the interference risk value between the target through-hole and the target defect point is greater than or equal to the preset interference risk value.

[0066] The TGV laser drilling position optimization device provided in this embodiment first acquires a blank inspection image, a positioning point image, and a CAD design file of the glass substrate to be processed; then, based on the blank inspection image, it determines the defect data of the glass substrate to be processed; and based on the positioning point image, it determines the target defect position of each defect point in the defect data in the target coordinate system; furthermore, based on the through-hole information of each through-hole, it determines the expansion risk area, and based on the target defect position of each defect point in the defect data in the target coordinate system and the expansion risk area of ​​each through-hole, it determines the interference risk value between each through-hole and each defect point in the defect data; finally, when the interference risk value between the target through-hole and the target defect point is greater than or equal to a preset interference risk value, the hole position of the target through-hole is optimized according to the hole position allowable offset range constraint, hole spacing constraint, and forbidden area constraint. In the glass substrate feeding stage, defect data is first identified using an AOI system, and the defect point positions in the defect data are unified to the global coordinate system of the glass through positioning point images. Then, the through hole information, hole position process influence zone, hole position allowable offset range constraints, hole spacing constraints, and forbidden area constraints of each through hole in the CAD design file are analyzed. Then, based on the defect severity of each defect point, the interference ratio between the defect and the hole position process influence zone, the defect type, and the defect confidence, the interference risk value of the through hole is calculated. Finally, with the goal of reducing the interference risk value, under the condition of meeting the design, process, equipment, and safety margin constraints, the position of the through hole is adaptively optimized. This realizes the transformation of the defect detection results of the glass substrate in the blank stage from "post-sorting information" to "forward process decision information". It can actively avoid fatal defects before laser induction or drilling, improve the utilization rate of the glass substrate to be processed, and avoid uncontrollable blind processing.

[0067] In some embodiments of this disclosure, determining the defect data of the glass substrate to be processed based on the blank film inspection image includes: After preprocessing the white film detection image, the preprocessed white film detection image is further processed based on image segmentation and contour extraction to determine the defect contour of each defect point in the white film detection image. Based on the defect contours of each defect point in the white film detection image, determine the defect type, defect center coordinates, defect size, and defect confidence level of each defect point in the white film detection image; The severity of each defect point is determined based on the defect type and size of each defect point in the white film detection image.

[0068] In some embodiments of this disclosure, determining the target defect position in the target coordinate system based on the positioning point image includes: Based on the positioning point image, determine the transformation relationship between the target coordinate system and the image coordinate system; Based on the defect locations corresponding to each defect point in the defect data and the transformation relationship between the target coordinate system and the image coordinate system, the target defect location in the target coordinate system of each defect point in the defect data is determined.

[0069] In some embodiments of this disclosure, determining the expansion risk area based on the through-hole information of each through-hole includes: Acquire the positioning error information of the defect detection algorithm, the registration error information of the positioning point image, and the motion error information of the motion platform carrying the glass substrate to be processed; Based on the positioning error information, the registration error information, and the motion error information, determine the safety margin information; Based on the process influence zone of each through hole and the safety margin information, the extended risk area is determined.

[0070] In some embodiments of this disclosure, determining the interference risk value between each through-hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through-hole includes: Based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through hole in the defect data, determine the overlapping area of ​​the defect area of ​​each defect point and the expansion risk area of ​​each through hole. Based on the target defect position of each defect point in the target coordinate system and the through hole information of each through hole in the defect data, determine the distance information between the center point of each defect point and the center point of each through hole. Based on the overlapping area of ​​the extended risk areas of each defect point and each via, the distance information between the center point of the defect point and the center point of each via, the defect type, defect confidence, and defect severity of each defect point, the interference risk value between each via and each defect point in the defect data is determined.

[0071] In some embodiments of this disclosure, optimizing the position of the target through-hole based on the allowable offset range constraint, the hole spacing constraint, and the no-entry zone constraint includes: With the goal of reducing the interference risk between the target through hole and each defect point in the defect data, the hole position of the target through hole is optimized by using the allowable offset range constraint of the target through hole, the hole spacing constraint, and the forbidden area constraint.

[0072] In some embodiments of this disclosure, it also includes: Based on the optimization results, the target hole position information for each through hole is determined, and a target CAD design file executable by the laser drilling equipment is generated.

[0073] This application also provides a computer device, please refer to the following for details. Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0074] The computer device includes a memory 510 and a processor 520 that are interconnected via a system bus. It should be noted that only a computer device with components 510-520 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components may be implemented alternatively. Those skilled in the art will understand that the computer device described herein is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0075] Computer devices can include desktop computers, laptops, handheld computers, and cloud servers. These devices allow for human-computer interaction with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0076] The memory 510 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. RAM may include static RAM or dynamic RAM. In some embodiments, the memory 510 may be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the memory 510 may also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, or flash card equipped on the computer device. Of course, the memory 510 may include both internal storage units and external storage devices of the computer device. In this embodiment, the memory 510 is typically used to store the operating system and various application software installed on the computer device, such as the program code of the method described above. In addition, the memory 510 may also be used to temporarily store various types of data that have been output or will be output.

[0077] The processor 520 is typically used to perform the overall operation of a computer device. In this embodiment, the memory 510 is used to store program code or instructions, including computer operation instructions. The processor 520 is used to execute the program code or instructions stored in the memory 510 or to process data, such as program code that runs the methods described above.

[0078] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus system can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0079] Another embodiment of this application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method; and to generate means for implementing the functional actions specified in each block or combination of blocks in the block diagram.

[0080] Computer-readable media include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any suitable combination thereof, wherein the memory is used to store program code or instructions, the program code including computer operation instructions, and the processor is used to execute the program code or instructions of the above-described methods stored in the memory.

[0081] The definitions of memory and processor can be found in the description of the foregoing computer device embodiments, and will not be repeated here.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0083] In the various embodiments of this application, the functional units or modules 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 as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] Unless otherwise expressly indicated by the context, the singular form of words used herein and in the appended claims includes the plural form, and vice versa. Thus, when referring to the singular, the plural form of the corresponding term is generally included. Similarly, the terms “comprising” and “including” shall be interpreted as including rather than exclusively. Likewise, the terms “including” and “or” shall be interpreted as including unless such interpretation is expressly prohibited herein. Where the term “example” is used herein, particularly when it follows a set of terms, the “example” is merely exemplary and illustrative and should not be considered exclusive or extensive.

[0086] Further aspects and scope of adaptation become apparent from the description provided herein. It should be understood that various aspects of this application may be implemented individually or in combination with one or more other aspects. It should also be understood that the descriptions and specific embodiments herein are for illustrative purposes only and are not intended to limit the scope of this application.

[0087] Several embodiments of this disclosure have been described in detail above. However, it is obvious that those skilled in the art can make various modifications and variations to the embodiments of this disclosure without departing from the spirit and scope of this disclosure. The scope of protection of this disclosure is defined by the appended claims.

Claims

1. A method for optimizing the position of TGV laser drilling, characterized in that, include: Acquire the blank inspection image, positioning point image, and CAD design file of the glass substrate to be processed. The CAD design file includes the through hole information, the allowable offset range constraint of the hole position, the hole spacing constraint, and the no-entry area constraint. The through hole information includes the hole center, hole diameter, circuit connection relationship, and the hole position process influence area. Based on the white film inspection image, the defect data of the glass substrate to be processed is determined, wherein the defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level and defect severity corresponding to each defect point; Based on the positioning point image, determine the target defect position of each defect point in the defect data in the target coordinate system; Based on the through hole information of each through hole, the extended risk area is determined, and based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole, the interference risk value between each through hole and each defect point in the defect data is determined. When the interference risk value between the target through hole and the target defect point is greater than or equal to the preset interference risk value, the position of the target through hole is optimized according to the allowable offset range constraint of the target through hole, the hole spacing constraint, and the forbidden area constraint.

2. The method according to claim 1, characterized in that, The step of determining the defect data of the glass substrate to be processed based on the white film inspection image includes: After preprocessing the white film detection image, the preprocessed white film detection image is further processed based on image segmentation and contour extraction to determine the defect contour of each defect point in the white film detection image. Based on the defect contours of each defect point in the white film detection image, determine the defect type, defect center coordinates, defect size, and defect confidence level of each defect point in the white film detection image; The severity of each defect point is determined based on the defect type and size of each defect point in the white film detection image.

3. The method according to claim 1, characterized in that, The step of determining the target defect position in the target coordinate system for each defect point in the defect data based on the positioning point image includes: Based on the positioning point image, determine the transformation relationship between the target coordinate system and the image coordinate system; Based on the defect locations corresponding to each defect point in the defect data and the transformation relationship between the target coordinate system and the image coordinate system, the target defect location in the target coordinate system of each defect point in the defect data is determined.

4. The method according to claim 1, characterized in that, The step of determining the expansion risk area based on the through-hole information of each through-hole includes: Acquire the positioning error information of the defect detection algorithm, the registration error information of the positioning point image, and the motion error information of the motion platform carrying the glass substrate to be processed; Based on the positioning error information, the registration error information, and the motion error information, determine the safety margin information; Based on the process influence zone of each through hole and the safety margin information, the extended risk area is determined.

5. The method according to claim 1, characterized in that, The step of determining the interference risk value between each through-hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through-hole includes: Based on the target defect position of each defect point in the target coordinate system and the expansion risk area of ​​each through hole in the defect data, determine the overlapping area of ​​the defect area of ​​each defect point and the expansion risk area of ​​each through hole. Based on the target defect position of each defect point in the target coordinate system and the through hole information of each through hole in the defect data, determine the distance information between the center point of each defect point and the center point of each through hole. Based on the overlapping area of ​​the extended risk areas of each defect point and each via, the distance information between the center point of the defect point and the center point of each via, the defect type, defect confidence, and defect severity of each defect point, the interference risk value between each via and each defect point in the defect data is determined.

6. The method according to claim 1, characterized in that, The optimization of the hole position of the target through hole based on the allowable offset range constraint, the hole spacing constraint, and the no-entry zone constraint includes: With the goal of reducing the interference risk between the target through hole and each defect point in the defect data, the hole position of the target through hole is optimized by using the allowable offset range constraint of the target through hole, the hole spacing constraint, and the forbidden area constraint.

7. The method according to claim 1, characterized in that, Also includes: Based on the optimization results, the target hole position information for each through hole is determined, and a target CAD design file executable by the laser drilling equipment is generated.

8. A TGV laser drilling position optimization device, characterized in that, include: The information acquisition module is used to acquire the blank inspection image, positioning point image and CAD design file of the glass substrate to be processed. The CAD design file includes the through hole information, the allowable offset range constraint of the hole position, the hole spacing constraint and the no-entry area constraint. The through hole information includes the hole center, hole diameter, line connection relationship and hole position process influence area. The defect data determination module is used to determine the defect data of the glass substrate to be processed based on the white film inspection image. The defect data includes the defect location, defect type, defect outline, defect center coordinates, defect size, defect confidence level, and defect severity corresponding to each defect point. The defect coordinate determination module is used to determine the target defect position of each defect point in the defect data in the target coordinate system based on the positioning point image. The interference risk value determination module is used to determine the extended risk area based on the through hole information of each through hole, and to determine the interference risk value between each through hole and each defect point in the defect data based on the target defect position of each defect point in the target coordinate system and the extended risk area of ​​each through hole. The through-hole position optimization module is used to optimize the position of the target through-hole according to the allowable offset range constraint of the target through-hole, the hole spacing constraint, and the forbidden area constraint when the interference risk value between the target through-hole and the target defect point is greater than or equal to a preset interference risk value.

9. A computer device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 7.

Images