Positioning method and device of circuit board target, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a circuit board target positioning method and device, electronic equipment and storage medium, which can quickly and accurately position the target position of the circuit board to be processed without a target template, thereby improving the production efficiency of the printed circuit board. The positioning method of the circuit board target comprises: receiving a design drawing file of a circuit board to be processed, and parsing a theoretical size and a theoretical centroid coordinate of a target target from the design drawing file; obtaining a pre-set theoretical type and a theoretical shape of the target target; identifying a suspected target in a scanning image corresponding to the circuit board to be processed based on the theoretical centroid coordinate, the theoretical type and the theoretical shape; identifying an actual size of the suspected target; and if the difference between the actual size and the theoretical size is not greater than a set threshold, the suspected target is determined as the target target.

Description

[Technical Field]

[0001] This application relates to the field of laser processing technology, and in particular to a method, apparatus, electronic device, and storage medium for positioning a circuit board target. [Background Technology]

[0002] Currently, with the functional iteration of high-tech electronic products, the demand for and precision requirements of small integrated circuit chips are gradually increasing. Correspondingly, laser processing technology is being adopted in the mass production of printed circuit boards (PCBs) used to process integrated circuit chips to meet the high demand and high precision requirements. Specifically, after drilling holes in the PCB, the laser processing equipment uses its machine vision function to scan and identify the target on the PCB, thereby guiding the laser beam to complete the PCB cutting according to the design drawings.

[0003] In existing technologies, identifying the target location on a PCB mainly relies on manually selecting a target area on the scanned image. The laser processing equipment then performs machine learning on the selected area to generate a target template, enabling rapid target positioning on the PCB during subsequent production. However, due to the time-consuming nature of machine learning, accurate target templates cannot be immediately implemented in production lines before they are trained for the specific PCB model, potentially leading to reduced production efficiency for the PCBs being processed. [Summary of the Invention]

[0004] This application provides a method, apparatus, electronic device, and storage medium for locating targets on printed circuit boards. It enables rapid and accurate positioning of the target position on the circuit board to be processed without the need for a target template, thereby avoiding the time consumption of generating target templates through machine learning and improving the production efficiency of printed circuit boards.

[0005] In a first aspect, embodiments of this application provide a method for locating a target on a circuit board, the method comprising:

[0006] Receive the design drawing file of the circuit board to be processed, and parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file;

[0007] Obtain the pre-defined theoretical type and theoretical shape of the target;

[0008] Based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape, a suspected target is identified in the scanned image corresponding to the circuit board to be processed.

[0009] Identify the actual size of the suspected target;

[0010] If the difference between the actual size and the theoretical size is not greater than a set threshold, then the suspected target is determined as the target target.

[0011] In this embodiment, the theoretical dimensions and centroid coordinates of the target are obtained by analyzing the parameters of the target in the design drawing file. Then, the theoretical type and shape of the target are obtained by human pre-setting. Based on these parameters, a search is performed on the scanned image of the circuit board to be processed to identify suspected targets whose parameters all meet the definition and use them as target targets for application in actual laser processing. This effectively avoids the time-consuming process of machine learning on the target parameters and generating target templates, simplifies the intermediate links from the drawing to the production line of the circuit board to be processed, and improves production efficiency.

[0012] Optionally, identifying suspected targets in the scanned image corresponding to the circuit board to be processed based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape includes:

[0013] Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, the actual centroid coordinates corresponding to the theoretical centroid coordinates are calculated.

[0014] Based on the theoretical type and the theoretical shape, the suspected target is identified at the actual centroid coordinates of the scanned image.

[0015] In this embodiment, by associating the theoretical centroid coordinates of the target with the actual centroid coordinates on the circuit board to be processed, the laser processing machine tool can immediately convert the theoretical centroid coordinates from the design drawings to obtain the corresponding actual centroid coordinates, thereby determining the specific location for identification on the scanned image. Subsequently, the image of the specific location is analyzed based on the theoretical type and theoretical shape to identify the suspected target, thus enabling the laser processing machine tool to achieve automatic target positioning without relying on the target template.

[0016] Optionally, after calculating the actual centroid coordinates corresponding to the theoretical centroid coordinates based on a pre-defined correspondence between the theoretical and actual coordinates, the method further includes:

[0017] If, based on the theoretical type and the theoretical shape, the suspected target cannot be identified at the actual centroid coordinates of the scanned image, a first alarm message is output. The first alarm message is used to remind the user that the suspected target has not been identified.

[0018] In this embodiment, if a suspected target matching the two preset conditions of theoretical type and theoretical shape cannot be found on the circuit board to be processed, a first alarm message is output to inform the user that the identification failed and no suspected target was found, so that the user can be aware of the problem in the circuit board to be processed or the design drawing file in a timely manner and conduct screening.

[0019] Optionally, identifying the actual size of the suspected target includes:

[0020] Identify the imaging size of the suspected target on the scanned image;

[0021] Based on the pre-defined correspondence between the imaging size and the actual size, the actual size corresponding to the imaging size is determined.

[0022] In this embodiment, by associating the imaging size data of the suspected target on the scanned image with the actual size data on the circuit board to be processed, the laser processing machine tool can quickly determine the actual size of the suspected target based on the imaging size after obtaining the scanned image and identifying the outline of the suspected target according to the scanned image, thereby providing accurate comparison data for the judgment process of whether the suspected target corresponds to the target target.

[0023] Optionally, after identifying the actual size of the suspected target, the method further includes:

[0024] If the difference between the actual size and the theoretical size is greater than a set threshold, a second alarm message is output. This second alarm message is used to alert the user that the suspected target is not the target target. In this embodiment, when the difference between the actual size of the suspected target and the theoretical size of the target target is greater than a set threshold, a second alarm message is sent to the user to alert them that a suspected target matching the image features of the target target has been identified, but its size does not match the target target. This allows the user to promptly realize that there may be a target size problem in the circuit board to be processed or the design drawing file, and to conduct targeted screening.

[0025] Optionally, after determining the suspected target as the target target if the difference between the actual size and the theoretical size is not greater than a set threshold, the method further includes:

[0026] Based on the pre-defined correspondence between the machine tool centroid coordinates and the actual centroid coordinates, the machine tool centroid coordinates corresponding to the actual centroid coordinates are determined;

[0027] The target is located on the laser processing machine tool according to the centroid coordinates of the machine tool.

[0028] The circuit board to be processed is processed based on the located target.

[0029] In this embodiment, based on the pre-established data relationship between the machine tool centroid coordinates and the actual centroid coordinates, when actual processing is required, the laser processing machine tool can automatically locate the target at the corresponding position on the machine tool according to the actual centroid coordinates, thereby avoiding unexpected situations such as workpiece cutting errors during actual processing.

[0030] Optionally, the theoretical types include optical targets and through-hole targets, and the theoretical shapes include circular targets, rectangular targets, and cross targets.

[0031] In this embodiment, by classifying the common types and shapes of targets, the laser processing machine tool can identify the targets of most printed circuit boards on the market without the need for machine learning to generate target templates. This enables the machine tool to accurately grasp and process targets when faced with various printed circuit board design drawings.

[0032] Optionally, before identifying a suspected target in the scanned image corresponding to the circuit board to be processed based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape, the method further includes:

[0033] The circuit board to be processed is placed at a predetermined processing position on a laser processing machine tool, wherein the predetermined endpoint on the circuit board to be processed coincides with the origin of the machine tool coordinate system;

[0034] The control line scan camera performs a global scan of the circuit board to be processed to obtain the scanned image of the circuit board to be processed.

[0035] In this embodiment, before acquiring relevant parameters from the design drawings and searching for the target, the linear scan camera is controlled to perform scanning by placing the circuit board to be processed at a predetermined processing position on the machine tool, i.e., aligning the preset endpoint with the origin of the machine tool coordinate system. This prevents issues such as incomplete scanning of the carrier board image or the scanned image not corresponding to the theoretical centroid coordinates due to placement deviations of the circuit board to be processed, thereby improving the processing accuracy of the circuit board. Simultaneously, a global scanning method is used to acquire scanned images of the circuit board to be processed, allowing all targets to be identified with a single scan. This avoids multiple scans while ensuring processing accuracy, improving the efficiency of target positioning.

[0036] Optionally, the type of the circuit board to be processed is an integrated circuit carrier board.

[0037] In this embodiment, since integrated circuit substrates are more often processed using high-precision small-size processing technology, by limiting the type of circuit board being processed, it can be ensured that the relevant parameters of the integrated circuit substrate can be more specifically adapted when the method is applied to actual processing scenarios.

[0038] Secondly, embodiments of this application provide a positioning device for a circuit board target, the device comprising:

[0039] The processing unit is used to receive the design drawing file of the circuit board to be processed, and to parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file;

[0040] The acquisition unit is used to acquire the theoretical type and theoretical shape of the target object as preset.

[0041] The identification unit is used to identify a suspected target in the scanned image corresponding to the circuit board to be processed, based on the theoretical centroid coordinates, the theoretical type and the theoretical shape.

[0042] The identification unit is also used to identify the actual size of the suspected target;

[0043] The determining unit is configured to determine the suspected target as the target target if the difference between the actual size and the theoretical size is not greater than a set threshold.

[0044] Optionally, the identification unit is specifically used for:

[0045] Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, the actual centroid coordinates corresponding to the theoretical centroid coordinates are calculated.

[0046] Based on the theoretical type and the theoretical shape, the suspected target is identified at the actual centroid coordinates of the scanned image.

[0047] Optionally, the device further includes:

[0048] The first output unit is configured to output a first alarm message if the suspected target cannot be identified at the actual centroid coordinate position of the scanned image according to the theoretical type and the theoretical shape. The first alarm message is used to remind the user that the suspected target has not been identified.

[0049] Optionally, the identification unit is specifically used for:

[0050] Identify the imaging size of the suspected target on the scanned image;

[0051] Based on the pre-defined correspondence between the imaging size and the actual size, the actual size corresponding to the imaging size is determined.

[0052] Optionally, the device further includes:

[0053] The second output unit is used to output a second alarm message if the difference between the actual size and the theoretical size is greater than a set threshold. The second alarm message is used to prompt the user that the suspected target is not the target target.

[0054] Optionally, the device further includes:

[0055] The machining unit is used to determine the machine tool centroid coordinates corresponding to the actual centroid coordinates based on the pre-set correspondence between the machine tool centroid coordinates and the actual centroid coordinates;

[0056] The processing unit is also used to position the target on the laser processing machine tool according to the centroid coordinates of the machine tool;

[0057] The processing unit is also used to process the circuit board to be processed based on the located target.

[0058] Optionally, the theoretical types include optical targets and through-hole targets, and the theoretical shapes include circular targets, rectangular targets, and cross targets.

[0059] Optionally, the device further includes:

[0060] A placement unit is used to place the circuit board to be processed at a predetermined processing position on a laser processing machine tool, wherein the preset endpoint on the circuit board to be processed coincides with the origin of the machine tool coordinate system;

[0061] The scanning unit is used to control the line scan camera to perform a global scan of the circuit board to be processed, and obtain the scanned image of the circuit board to be processed.

[0062] Optionally, the type of the circuit board to be processed is an integrated circuit carrier board.

[0063] Thirdly, embodiments of this application also provide an electronic device, characterized in that the electronic device includes at least one processor and a memory connected to the at least one processor, wherein the at least one processor is used to execute a computer program stored in the memory to implement the steps of the circuit board target positioning method as described in the first aspect.

[0064] Fourthly, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the method described in the first aspect.

[0065] It should be understood that the second to fourth aspects of the embodiments of this application are consistent with the technical solutions of the first aspect of the embodiments of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be described again. [Attached Image Description]

[0066] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0067] Figure 1 A flowchart illustrating a method for locating a circuit board target, provided in an embodiment of this application;

[0068] Figure 2 This is a flowchart illustrating a method for identifying suspected targets from a scanned image of a circuit board to be processed, according to an embodiment of this application.

[0069] Figure 3 This is a flowchart illustrating an alarm method for when a suspected target is not identified, as described in an embodiment of this application.

[0070] Figure 4 This is a flowchart illustrating a method for measuring the actual size of a suspected target in an embodiment of this application.

[0071] Figure 5 This is a flowchart illustrating a method for machining circuit boards based on a machine tool coordinate system, as described in an embodiment of this application.

[0072] Figure 6 This is a flowchart illustrating an alarm method for when a suspected target is not a target target, as described in an embodiment of this application.

[0073] Figure 7 This application provides a method for scanning an image of a circuit board to be processed.

[0074] Figure 8 A schematic diagram of a circuit board target positioning device provided in an embodiment of this application;

[0075] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

Detailed Implementation Methods

[0076] To better understand the technical solutions in this specification, the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0077] It should be understood that the described embodiments are merely some, not all, of the embodiments in this specification. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without inventive effort are within the scope of protection of this specification.

[0078] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0079] Currently, with the functional iteration of high-tech electronic products, the demand for and precision requirements of small integrated circuit chips are gradually increasing. Correspondingly, laser processing technology is being adopted in the mass production of PCBs used to process integrated circuit chips to meet the high demand and high precision requirements. Specifically, after drilling holes in the PCB, the laser processing equipment scans and identifies the target on the PCB, then guides the laser beam to cut the PCB according to the design drawings.

[0080] The inventors of this application have discovered that in related technologies, the identification of target positions on PCBs mainly relies on the machine vision system built into the laser processing machine tool to scan images. The target's location is then manually outlined on the scanned image. The laser processing equipment then performs machine learning on the image features within the outlined area and generates a target template based on parameters such as the target image's contrast, polarity, and scaling ratio. This allows for rapid target positioning on the PCB during subsequent production. However, to maintain target recognition accuracy, acquiring target image features through machine learning often takes a considerable amount of time. Furthermore, a sufficiently accurate target template cannot be immediately deployed to the production line before it is trained for that particular PCB model, potentially leading to reduced PCB production efficiency.

[0081] In view of this, the present application provides a method for locating targets on circuit boards, which can quickly and accurately identify and locate the target position on the circuit board to be processed based on the relevant data definition of the target in the design drawing file without the need for a target template. This avoids the large amount of time consumed by generating target templates through machine learning and improves the production efficiency of PCBs.

[0082] It should be clarified that the "theoretical coordinate system" used in the embodiments of this application refers to the built-in coordinate system of the design drawing file, while the "actual coordinate system" used is a coordinate system established based on the physical parameters of the PCB to be processed and the target (the method of establishing it will be described in detail below). The terms "theoretical centroid coordinates," "theoretical coordinates," and "theoretical dimensions" used below are all data obtained with the theoretical coordinate system as the reference system; similarly, the terms "actual centroid coordinates," "actual coordinates," "actual dimensions," and "actual position" used below are all coordinate positions or size parameters obtained with the actual coordinate system as the reference system.

[0083] The technical solutions provided in the embodiments of this application will be described below with reference to the accompanying drawings. Please refer to... Figure 1 This application provides a method for locating a target on a circuit board, applied to a laser processing machine tool. The process of this method is described as follows:

[0084] Step 101: Receive the design drawing file of the circuit board to be processed, and parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file.

[0085] The design drawings of the circuit board to be processed are in a conventional CAD format (hereinafter referred to as CAD files). After importing the CAD file into the laser processing machine tool system (hereinafter referred to as the laser processing system), the laser processing system will automatically convert the format of the CAD file to read the theoretical dimensions and theoretical centroid coordinates related to the target. In this embodiment, these data are uniformly stored in the laser processing system in micrometers (μm) for subsequent identification of suspected targets. The unit of measurement was proposed after studying the processing accuracy of commonly used laser processing systems and the recognition accuracy of the matching line scan cameras; however, for laser processing systems with different recognition and processing accuracies, these data can also be expressed using other units (such as pixels or millimeters).

[0086] For example, after converting the format and extracting data from a CAD file, the laser processing system will obtain a code in the form of "FG-1X[arbitrary value]Y[arbitrary value]W[arbitrary value]H[arbitrary value]CO" for a single target. Here, "[arbitrary value]" means that the value may vary depending on the target; PG-1 is the definition statement for a target in the parameters, indicating that the following parameters are only used to search for this target; the values ​​following X and Y are mainly responsible for defining the theoretical centroid coordinates of the target; the values ​​following W and H are mainly responsible for defining the theoretical dimensions (length and width) of the target; C and O are the shape and type definitions of the target, which will be explained below and will not be repeated here.

[0087] It should be understood that, since the processing method in this application embodiment is mainly for the precision processing of small-sized circuit boards, therefore:

[0088] As one possible implementation method, the type of circuit board to be processed is an integrated circuit carrier board.

[0089] In this embodiment, because the framing angle of the line scan camera is limited when scanning the entire image during the extraction of CAD file data and processing of the circuit board, and the scanning object is mainly a small-sized integrated circuit (IC) substrate, the width of the circuit board is limited to within 250mm (based on the maximum framing width of commonly used line scan cameras), and the length is limited to within 45mm-350mm (based on the length limitation of the laser processing machine tool and the recognition accuracy of the machine vision system). However, these data can be appropriately adjusted for different models of laser processing machine tools, and the scanning action of the line scan camera can be configured more flexibly so that this laser processing system can support target positioning and laser processing of more PCB models (such as high-frequency boards, communication interface boards, etc.).

[0090] After completing the format conversion of the CAD file and the data extraction of the target, it is also necessary to obtain the theoretical type and theoretical shape of the target (i.e., the type and shape of the target in the CAD file) so as to match the suspected target on the scanned image more quickly and accurately according to the target characteristics specified in the CAD file.

[0091] Step 102: Obtain the theoretical type and theoretical shape of the pre-defined target.

[0092] After obtaining precise data such as the theoretical dimensions and centroid coordinates of the target, it is still necessary to acquire fuzzy data such as the target type and shape. Since laser processing systems struggle to directly extract these theoretical parameters from CAD files, manually selecting the target type and shape on the laser processing machine's interface is a superior approach. The selectable target types and shapes are all industry-standard, ensuring compatibility with most CAD files. Furthermore, the image feature data (including image area, angles, line vectors, etc.) for each target type and shape are pre-configured in the laser processing system, allowing the machine vision system to retrieve the corresponding image feature data based on the set theoretical target type and shape when identifying the target.

[0093] Regarding how to classify different target types and shapes, a typical classification method is given in the embodiments of this application below.

[0094] As one possible implementation, theoretical types include optical targets and through-hole targets, and theoretical shapes include circular targets, rectangular targets, and cross targets.

[0095] In this embodiment of the application, when the machine vision system retrieves the theoretical type and theoretical shape of the target, the specific retrieval method is to query the image feature data corresponding to the theoretical type and theoretical shape based on the previously received identification code of the theoretical type and the identification code of the theoretical shape, and then transmit the image feature data to the machine vision system for use.

[0096] Here, we again use the code in the form of "FG-1X[arbitrary value]Y[arbitrary value]W[arbitrary value]H[arbitrary value]CO" as an example. Here, C is the identifier for the theoretical shape, representing that the target is circular (other shape identifiers include: R—square target, S—cross target), and O is the identifier for the theoretical type, representing that the target is an optical target (other type identifiers include: H—through-hole target). If it is necessary to process PCBs with target types and shapes, the type and shape feature data of the target can be extracted beforehand and then imported into the laser processing system for type recognition expansion.

[0097] After acquiring the theoretical dimensions, centroid coordinates, type, and shape of the target, it can be considered that the main feature parameters required for target identification have been obtained. Therefore, the next step is to input these parameters into the laser processing machine tool for image recognition in order to find suspected targets with similar features to the target in the scanned image.

[0098] Step 103: Based on the theoretical centroid coordinates, theoretical type and theoretical shape, identify the suspected target in the scanned image corresponding to the circuit board to be processed.

[0099] In this embodiment, when a machine vision system equipped with a charge-coupled device (CCD) on a laser processing machine tool finds the coordinate point to be searched on the scanned image based on the theoretical centroid coordinates of the target, it compares the image features around the coordinate point with the previously acquired parameters of the target to determine whether the target that the laser processing system expects to capture exists near the selected coordinate point. Specifically, after generating a recognizable scanned image, the machine vision system identifies the pixels around the theoretical centroid coordinates, counts pixels with the same or similar chromaticity values, and forms a graphic contour. Then, the machine vision system matches the obtained graphic contour with the theoretical type and theoretical shape, labels graphic contours similar to the target's features, and stores them as suspected targets.

[0100] It should be understood that after the scanned image is acquired and stitched together by a line scan camera, it needs to be binarized. That is, according to the preset maximum and minimum chromaticity thresholds, the set value of each pixel on the scanned image is judged. Pixels with chromaticity values ​​lower than the minimum chromaticity threshold or higher than the maximum chromaticity threshold will be colored black, while pixels with chromaticity values ​​between the minimum and maximum chromaticity thresholds will be marked white to obtain a grayscale image of the scanned image (the minimum and maximum chromaticity thresholds need to be adjusted according to the object to be extracted from the scanned image - such as the target to be identified and located in the embodiment of this application).

[0101] After the grayscale image is generated, it needs to undergo convolution processing to improve both the signal-to-noise ratio and contrast, thereby increasing the accuracy of pattern recognition. Once convolution is complete, the machine vision system can perform chromaticity recognition and connected component analysis (selecting adjacent pixels with similar chromaticity) on the pixels surrounding the desired coordinate point (such as the reference point mentioned above) based on the required coordinate point. It then extracts image feature data such as angles, line vectors, and areas from the analyzed connected components. Based on the similarity between these feature data and pre-stored image feature data contained in theoretical shapes and types, the machine vision system can determine whether the CCD image data of the identified object (such as the suspected target mentioned above) matches the data of the target object (such as the target object mentioned above) within a certain confidence interval. This confidence interval can be adjusted according to different requirements for image recognition accuracy.

[0102] After the scanned image is processed, when statistically analyzing the connected components of the grayscale image to find suspected targets, it is also necessary to extract the theoretical centroid coordinates of the target and convert them into the actual centroid coordinates for identifying suspected targets, so as to inform the machine vision system of the specific location for local image recognition. The method will be described in detail below.

[0103] Figure 2 This is a flowchart illustrating a method for identifying suspected targets from a scanned image of a circuit board to be processed, as described in an embodiment of this application. In one possible implementation, step 103 is achieved by executing sub-steps 1031 to 1032.

[0104] Step 1031: Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, calculate the actual centroid coordinates corresponding to the theoretical centroid coordinates.

[0105] Step 1032: Based on the theoretical type and theoretical shape, identify the suspected target at the actual centroid coordinates of the scanned image.

[0106] Because the laser processing system locates the target using a target template by manually selecting the target area, allowing the system to learn the location and image features of that area, other methods must be used to inform the laser processing system of the target's location when a target template is unavailable. This saves search time and reduces recognition errors. Therefore, this embodiment uses the method of reading the theoretical centroid coordinates of the target from the CAD file to find the actual centroid coordinates of the suspected target. The prerequisite for this method is establishing a data correlation between the theoretical and actual coordinate systems.

[0107] It should be understood that the scanning precision of common industrial cameras can support the acquisition of images measured in micrometers (μm); therefore, in this embodiment, the coordinate unit of the actual coordinate system is also expressed in μm. Since the coordinate unit of both the theoretical and actual coordinate systems is micrometer, based on this characteristic, a transformation relationship between the theoretical centroid coordinates and the actual centroid coordinates can be directly established, and according to this data transformation relationship, the theoretical centroid coordinates can be converted into the actual centroid coordinates on the scanned image (i.e., the position where the centroid of the aforementioned suspected target should exist in the scanned image).

[0108] However, when establishing the correspondence between the theoretical and actual coordinate systems in a laser processing system, image distortion caused by a line scan camera and errors in the machine's own parameters can often prevent the theoretical coordinates from being accurately converted into actual coordinates. Therefore, this application employs two existing methods to compensate for coordinate transformation errors caused by image distortion and machine parameter errors before the laser processing machine tool is put into circuit board production:

[0109] 1. Use general cutting files to compensate for coordinate transformation errors.

[0110] First, a general cutting drawing file (i.e., a generic CAD drawing file used for calibration) is loaded into the laser processing system, and the black calibration plate is placed on the laser processing machine. Then, a laser beam is used to print on the black calibration plate. The printed graphic includes: 40 hollow circles with a spacing of 40mm and a diameter of 2mm, distributed in a 5*8 pattern; and four solid circles with a diameter of 2mm located at the four corners of the calibration plate, used to assist the machine vision system in positioning during subsequent steps. In addition, the printed graphic may also include: a DataMatrix code (DM code, a small-sized matrix-style QR code commonly used as a physical identifier for small parts) to record information such as the circuit board model, so that the machine vision system can read the relevant information of the current circuit board after scanning.

[0111] Then, the CAD file of the current circuit board is loaded, and the black calibration plate is scanned using a machine vision system. At least three 2mm diameter solid circles are identified as calibration targets to assist in positioning, establishing the transformation relationship between the theoretical coordinate system in the CAD file and the actual coordinate system in the scanned image. Several 1mm diameter solid circles have been added to the CAD file to determine the coordinate transformation error. These circles are used to determine the error compensation value after setting parameters such as the target position, barcode position, and material border in the scanned image.

[0112] Finally, based on the scanned image from the machine vision system, the laser beam is controlled for secondary printing. The printed graphic includes a 1mm diameter solid circle from the CAD file. After printing, it is measured whether the 1mm diameter solid circle and the 2mm diameter hollow circle are concentric. If the distance between the centers of the two circles is large to the naked eye, the coordinate transformation error is considered to be greater than 70μm; alternatively, a two-dimensional measuring device can be used to confirm the center distance to obtain a precise coordinate transformation error value.

[0113] 2. Use nine-circle calibration and cross calibration to compensate for coordinate transformation errors.

[0114] First, a black calibration plate is placed on a laser processing machine tool, and a laser beam is controlled on the black calibration plate to print nine solid circles with a diameter of 2mm and equal theoretical spacing. The machine vision system is then used to scan and identify these nine solid circles. Subsequently, the actual distance between the solid circle in the center and the other eight solid circles is calculated, as well as eight sets of ratios between the actual distance and the theoretical distance. The average value of the eight sets of ratios is then calculated to obtain the first compensation value for compensating for coordinate transformation errors.

[0115] Then, the laser beam is controlled to print 1035 cross-shaped patterns with a spacing of 6mm and a size of 2mm on the black calibration plate (enough to cover the entire line scan range of 250mm*315mm). The actual coordinate values ​​of these 1035 cross-shaped patterns are counted by the machine vision system. The coordinates used when the laser beam is printing are taken as theoretical values. The difference between the actual values ​​and the theoretical values ​​is calculated as a secondary compensation value to compensate for coordinate transformation errors.

[0116] Finally, the coordinate transformation error is compensated in reverse overall based on the primary and secondary compensation values. That is, a fixed value is added to the coordinate values ​​of the theoretical X-axis and Y-axis (this value is obtained by weighted calculation of the primary and secondary compensation values) so as to obtain accurate actual coordinate values ​​under the current equipment conditions.

[0117] After adjusting the transformation error between the theoretical and actual coordinate systems of the laser processing system using the two methods described above, the grayscale image of the scanned image near the centroid of the suspected target can be identified based on the image feature data corresponding to the theoretical type and shape. This allows for the search for an image contour that matches the image feature data, which is the suspected target that the laser processing system hopes to find on the PCB. It should be understood that the coordinate transformation error between the theoretical and actual coordinate systems is only necessary to compensate for using the two methods described above when the equipment conditions of the laser processing machine tool change to a certain extent or when there are significant accuracy problems in the circuit board processing.

[0118] Furthermore, when searching for suspected targets in scanned images, there may be situations where suspected targets matching the characteristics of the target cannot be identified. If this occurs, an additional alarm logic needs to be set up to alert the user that a suspected target cannot be identified.

[0119] Figure 3 This is a flowchart illustrating an alarm method for when a suspected target is not identified, as described in an embodiment of this application. As a possible implementation, after step 1031, step 1033 can be further executed:

[0120] Step 1033: If, based on the theoretical type and theoretical shape, a suspected target cannot be identified at the actual centroid coordinates of the scanned image, output the first alarm message. The first alarm message is used to remind the user that no suspected target has been identified.

[0121] In this embodiment, there are three prerequisites for identifying a suspected target: (1) the type of the suspected target matches the theoretical type; (2) the shape of the suspected target matches the theoretical shape; and (3) the actual centroid coordinates of the suspected target match the theoretical centroid coordinates. That is, when any of the prerequisites is not met, the alarm logic of the laser processing system is triggered, promptly alerting the user to the failure to identify the suspected target, so that the user can promptly screen for problems in the PCB or CAD file to be processed. If the user needs to obtain more detailed alarm reasons, this embodiment can also extend its functionality to output specific reasons for identification failure, showing the user image contours that have some similar features but still cannot match the target, as well as the prerequisite feature conditions that the image contours do not meet.

[0122] Similarly, after identifying a suspected target and the machine vision system has completed the size measurement of the suspected target, it is also necessary to consider the possibility that the actual size of the suspected target is too different from the theoretical target, and to output an alarm message to the user based on this situation.

[0123] Step 104: Identify the actual size of the suspected target.

[0124] In this embodiment of the application, since an actual coordinate system has been established in advance in the machine vision system, after identifying the outline of the suspected target on the scanned image, the actual size of the suspected target can be obtained simply by measuring the length and width of its pattern outline.

[0125] Specifically, since the basic unit of measurement for scanned images is pixels, if a machine vision system is required to directly identify the actual size based on pixel size, the correspondence between the image size and the actual size of the object must be established beforehand. This correspondence also needs to be pre-set based on physical parameters. Only after the correspondence is determined can the technical principle of "statistical connectivity of the grayscale image of the scanned image" mentioned above be used to measure the actual size of the suspected target. This method will be explained in detail below.

[0126] Figure 4 This is a flowchart illustrating a method for measuring the actual size of a suspected target according to an embodiment of this application; as one possible implementation, step 104 is achieved by executing steps 1041-1042:

[0127] Step 1041: Identify the imaging size of the suspected target on the scanned image.

[0128] Step 1042: Based on the pre-defined correspondence between the imaging size and the actual size, determine the actual size corresponding to the imaging size.

[0129] In this embodiment, after the machine vision system identifies the connected components of the grayscale image to form an image of a suspected target, it is necessary to measure the actual size of the image. However, since the length and width (i.e., the imaging size) of any graphic in the obtained scanned image are represented in pixels, it is necessary to first measure the imaging size of the suspected target and obtain the actual size of the suspected target based on the pre-established conversion relationship between the actual size and the imaging size.

[0130] First, the specific method for measuring the imaging size is to mark the edge of the pixels occupied by the suspected target image on the scanned image using a machine vision system, and retrieve two directions that are pre-set in the machine vision system and are parallel to the horizontal and vertical axes in the actual coordinate system (these two directions must be perpendicular to each other). The maximum pixel length of the suspected target image in these two directions is then counted to obtain the imaging size of the suspected target on the scanned image.

[0131] After measuring the image size of the suspected target, to obtain its actual size based on its pixel size in the scanned image, a method similar to the one described above, linking the actual coordinate system with the theoretical coordinate system, can be used to correlate the pixel position of the scanned image with the actual position of the target on the PCB to derive a specific data conversion relationship. As one way to achieve this correlation, after installing the laser processing system, the machine vision system needs to be manually controlled to acquire one or more PCB images containing the target, and the relative physical distance and relative pixel distance between the target's centroid and any point on the PCB are measured. The data conversion relationship between the two is then derived. Once this relationship is established, the machine vision system can directly read the image and calculate the actual size of the suspected target in the image using the aforementioned data conversion relationship.

[0132] After measuring the actual size of the suspected target indirectly, it is also necessary to determine the difference between the actual size and the theoretical size to confirm whether the suspected target fully conforms to the characteristics of the target.

[0133] Step 105: If the difference between the actual size and the theoretical size is not greater than the set threshold, then the suspected target is identified as the target target.

[0134] In this embodiment of the application, when adding a target on the PCB, the size of the target may be different from the target size specified in the CAD file due to processing deviations and other reasons. This error may be amplified in the subsequent processing process as an abnormality in the overall processing and positioning of the PCB, which may lead to the scrapping of the entire batch of products.

[0135] Therefore, unlike the comparison process of characteristic parameters such as the type and shape of suspected targets, the identification of target size does not need to be as precise as possible. Instead, it requires setting a range that can tolerate processing deviations. This tolerance range is established through the aforementioned threshold setting. In this embodiment, the threshold setting is determined to be 0.2mm based on empirical data. That is, when the size error of the suspected target is within this range, it will not be ignored due to accidental errors, nor will it lead to unexpected situations where a large error is still identified as a target, thus ensuring a certain level of accuracy. However, depending on different PCB models and different laser processing systems (such as laser processing machine tools with higher precision machine vision), this threshold setting can also be flexibly adjusted (e.g., increasing the threshold setting to 0.25mm) to adapt to more PCB processing scenarios.

[0136] When the actual size of the suspected target is calculated to be greater than the theoretical size of the target, if the difference is greater than a set threshold, the error between the suspected target and the target is considered to be too large, and the suspected target is not the target that the laser processing system wants to find on the PCB image. When the difference is less than or equal to the set threshold, the size parameters of the suspected target are considered to match the target target, and the suspected target can be identified as the target target. The actual position of the suspected target on the PCB is used as the positioning result for subsequent processing.

[0137] Furthermore, as a preferred implementation, this application also summarizes several target size grades commonly encountered in PCB manufacturing: 1 mm, 1.5 mm, 2 mm, 2.5 mm, 3 mm, 3.5 mm, and 4 mm. To reduce the difficulty of target fabrication on PCBs, the recognition ranges for different target size grades are defined sequentially as [0.8 mm, 1.2 mm], [1.3 mm, 1.7 mm], [1.8 mm, 2.2 mm], [2.3 mm, 2.7 mm], [2.8 mm, 3.2 mm], [3.3 mm, 3.7 mm], and [3.8 mm, 4.2 mm]. When the size of a suspected target approaches these preset recognition ranges, the suspected target is categorized according to its corresponding size grade, and it is determined whether the size grade of the suspected target is the same as that of the target target. Comparing the sizes of suspected and target targets in this way simplifies the comparison logic of the machine vision system and improves its operating speed.

[0138] It should be noted that, in order to meet more diverse processing needs, the method for identifying suspected targets can be adjusted in this embodiment. For example, an additional target size level of 0.5mm can be added, and the recognition range of this size level can be limited to [0, 0.7mm], so that the machine vision system can capture targets with smaller sizes; or the recognition range of the 4mm size level can be widened to [3.8mm, Xmm], where X is an arbitrary set value, so that the machine vision system can identify targets with larger errors, but which the user still expects to capture. In a similar way, other target size levels can be added, or the recognition range of existing target size levels can be adjusted, so as to increase or decrease the error tolerance within a specific range according to specific processing needs and the actual recognition accuracy of the machine vision system.

[0139] After comparing the actual and theoretical dimensions, if the suspected target still matches the target target in this feature, it can be considered that the target target has been located on the PCB, and laser processing of the PCB can begin. However, simply knowing the actual position of the target target on the PCB is obviously not enough to meet all the conditions for laser processing. It is also necessary to establish a connection between the overall position of the PCB to be processed and the machine tool coordinate system so that the laser processing machine tool knows which path to guide the laser beam to process the PCB.

[0140] Figure 5 This is a flowchart illustrating a method for machining circuit boards based on a machine tool coordinate system according to an embodiment of this application; as a possible implementation, after step 105, steps 106 to 108 can be further executed:

[0141] Step 106: Determine the machine tool centroid coordinates corresponding to the actual centroid coordinates based on the pre-set correspondence between the machine tool centroid coordinates and the actual centroid coordinates.

[0142] Step 107: Locate the target on the laser processing machine tool according to the centroid coordinates of the machine tool.

[0143] Step 108: Process the circuit board to be processed based on the located target.

[0144] Before the laser processing machine tool unfolds and processes the PCB, a correspondence between the actual coordinates and the machine tool coordinates is configured in the database of the laser processing system, similar to storing the correspondence between the theoretical coordinate system and the actual coordinate system. This correspondence also uses the measurable physical data of the target and the PCB as a reference. Since the machine tool coordinate system is a known coordinate system that is set before the laser processing machine tool leaves the factory, there is no need to set its coordinate origin separately; only the data conversion relationship between this coordinate system and the actual coordinate system needs to be configured. Once the actual centroid coordinates of the target on the PCB to be processed are identified, the machine tool coordinates of the target can be quickly obtained based on the correspondence between the actual coordinate system and the machine tool coordinate system, and the PCB processing begins according to the obtained machine tool coordinates.

[0145] Figure 6 This is a flowchart illustrating an alarm method for when a suspected target is not a target target, as described in an embodiment of this application. As a possible implementation, after step 104, step 109 can be further executed:

[0146] Step 109: If the difference between the actual size and the theoretical size is greater than the set threshold, output the second alarm information. The second alarm information is used to prompt the user that the suspected target is not the target.

[0147] In this embodiment of the application, when the difference between the actual size and the theoretical size is too large (i.e. greater than the set threshold), regardless of whether the reason is that the theoretical centroid coordinates were entered incorrectly, resulting in a suspected target positioning error, or that the theoretical type or theoretical shape was incorrectly set during manual setting, causing it to be identified as other shapes near the coordinates, the user needs to be immediately alerted to the situation so that the user can screen the possible causes of the situation.

[0148] Before identifying and searching for suspected targets in the scanned images, it is necessary to scan the PCB using relevant hardware equipment that is compatible with the machine vision system to obtain scanned images for identification purposes.

[0149] Figure 7 This application provides a scanning method for an image of a circuit board to be processed. As a possible implementation, steps 110 to 111 can be further performed before step 103:

[0150] Step 110: Place the circuit board to be processed at the predetermined processing position of the laser processing machine tool, wherein the preset endpoints on the circuit board to be processed coincide with the origin of the machine tool coordinate system.

[0151] Step 111: Control the linear scan camera to perform a global scan of the circuit board to be processed, and obtain a scanned image of the circuit board to be processed.

[0152] In this embodiment, the circuit board to be processed is placed at a predetermined processing position, that is, the pre-set endpoint of the circuit board is placed at a position coinciding with the origin of the machine tool coordinate system, and the two sets of opposite sides of the circuit board to be processed are parallel to the horizontal and vertical axes of the machine tool coordinate system, respectively. This ensures that the scanned image of the circuit board to be processed can meet the pre-set transformation relationship between the theoretical coordinate system and the actual coordinate system, thereby ensuring that the laser processing system can accurately complete the subsequent processing steps. This preset endpoint can be any endpoint of the circuit board to be processed, as long as it is ensured that after selecting the endpoint and placing it as required, the image of the entire circuit board to be processed can be scanned into the machine vision system without any missing images of the carrier board. The placement process of the circuit board can be carried out automatically by machinery or manually adjusted to adapt to different processing requirements.

[0153] After performing step 110 above, to ensure that the circuit board to be processed is accurately placed in the predetermined processing position without any offset before acquiring the scanned image of the circuit board to be processed, it is also necessary to verify the position of the circuit board to be processed. Specifically, to complete this verification step, it is necessary to extract the endpoint data of the circuit board to be processed in the CAD file based on the theoretical coordinate system in the CAD file. This extraction action should extract the theoretical coordinates of at least two endpoints located on the same diagonal in a single operation. Subsequently, the acquired endpoint data is compared with the endpoint data identified by the machine vision system from the scanned image to verify whether the transformation relationship between the theoretical coordinate system and the actual coordinate system is strictly satisfied, and to eliminate the interference of placement offset of the circuit board to be processed due to unexpected circumstances.

[0154] For example, after extracting the theoretical coordinates of two endpoints, the output parameter format can be "RP X[arbitrary value] Y[arbitrary value]", where RP stands for Rectangular Position, indicating that the two endpoints are used to assist the laser processing system in data conversion. The "[arbitrary value]" following X and Y is similar to the theoretical coordinate data of the target mentioned earlier, representing the theoretical coordinates of the endpoints on the horizontal and vertical axes. By recognizing the grayscale image of the scanned image through a machine vision system, the edges of the circuit board to be processed can be identified, and the corresponding actual coordinates of the two endpoints can be extracted. By comparing the theoretical coordinates and actual coordinates of the two endpoints, it can be confirmed whether there is any misalignment in the placement of the circuit board to be processed, and the conversion relationship between theoretical and actual coordinates can be calibrated.

[0155] It is important to note that conventional machine vision systems use industrial cameras, including line scan cameras and area scan cameras, and their scanning method involves partially scanning the object to be identified and generating a local image. However, this embodiment uses a line scan camera, which is responsible for acquiring image data of the entire circuit board to be processed. The purpose is to quickly identify the edges and all target objects of the circuit board based on the complete scan image.

[0156] Please see Figure 8 Based on the same inventive concept, embodiments of this application also provide a circuit board target positioning device, the device comprising:

[0157] The processing unit 201 is used to receive the design drawing file of the circuit board to be processed, and to parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file;

[0158] Acquisition unit 202 is used to acquire the theoretical type and theoretical shape of a pre-set target.

[0159] The identification unit 203 is used to identify suspected targets in the scanned image corresponding to the circuit board to be processed based on theoretical centroid coordinates, theoretical type and theoretical shape.

[0160] The identification unit 203 is also used to identify the actual size of the suspected target;

[0161] The determination unit 204 is used to determine the suspected target as the target target if the difference between the actual size and the theoretical size is not greater than a set threshold.

[0162] Optionally, the identification unit 203 is specifically used for:

[0163] Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, the actual centroid coordinates corresponding to the theoretical centroid coordinates are calculated.

[0164] Based on the theoretical type and shape, the suspected target was identified at the actual centroid coordinates of the scanned image.

[0165] Optionally, the device may also include:

[0166] The first output unit is used to output a first alarm message if, based on the theoretical type and theoretical shape, a suspected target cannot be identified at the actual centroid coordinates of the scanned image. The first alarm message is used to remind the user that no suspected target has been identified.

[0167] Optionally, the identification unit 203 is specifically used for:

[0168] Identify the imaging size of suspected targets in the scanned image;

[0169] Based on the pre-defined correspondence between the imaging size and the actual size, the actual size corresponding to the imaging size is determined.

[0170] Optionally, the device may also include:

[0171] The second output unit is used to output a second alarm message if the difference between the actual size and the theoretical size is greater than a set threshold. The second alarm message is used to prompt the user that the suspected target is not the target.

[0172] Optionally, the device may also include:

[0173] The machining unit is used to determine the machine tool centroid coordinates corresponding to the actual centroid coordinates based on the pre-set correspondence between the machine tool centroid coordinates and the actual centroid coordinates.

[0174] The processing unit is also used to locate the target on the laser processing machine tool according to the centroid coordinates of the machine tool;

[0175] The processing unit is also used to process the circuit board to be processed based on the located target.

[0176] Optional theoretical types include optical targets and through-hole targets, and theoretical shapes include circular targets, rectangular targets, and cross targets.

[0177] Optionally, the device may also include:

[0178] The placement unit is used to place the circuit board to be processed at the predetermined processing position of the laser processing machine tool, wherein the preset endpoints on the circuit board to be processed coincide with the origin of the machine tool coordinate system;

[0179] The scanning unit is used to control the linear scan camera to perform a global scan of the circuit board to be processed, thereby obtaining a scanned image of the circuit board.

[0180] Optionally, the type of circuit board to be processed is an integrated circuit carrier board.

[0181] Please see Figure 9 Based on the same inventive concept, embodiments of this application also provide an electronic device 300, which may include at least one processor for executing a computer program stored in a memory to implement the functions provided in embodiments of this application. Figures 1-7 The steps of the circuit board target positioning method are shown.

[0182] Optionally, the processor mentioned above may be a central processing unit, a specific ASIC, or one or more integrated circuits used to control program execution.

[0183] Optionally, the electronic device may further include a memory 302 connected to at least one processor 301. The memory 302 may include ROM, RAM, and disk storage. The memory 302 stores data required for the processor 301 to run, i.e., it stores instructions executable by at least one processor 301. The at least one processor 301 executes instructions stored in the memory 302 to perform tasks such as... Figures 1-7 The method is shown. The number of memories 302 is one or more.

[0184] The physical devices corresponding to the processing unit 201, the identification unit 203, and the determination unit 204 can all be the aforementioned processor 301. This electronic device can be used to execute... Figures 1-7 The method provided in the illustrated embodiment. Therefore, regarding the functions that each functional unit in this electronic device can achieve, please refer to... Figures 1-7 The corresponding descriptions in the illustrated embodiments will not be repeated here.

[0185] Furthermore, embodiments of this application also provide a computer storage medium, wherein the computer storage medium stores computer instructions, which, when executed on a computer, cause the computer to perform... Figures 1-7 The method described.

[0186] The above description is merely a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of protection of this specification.

Claims

1. A method for locating a target on a circuit board, characterized in that, The method includes: Receive the design drawing file of the circuit board to be processed, and parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file; Obtain the pre-defined theoretical type and theoretical shape of the target; Based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape, a suspected target is identified in the scanned image corresponding to the circuit board to be processed. Identify the actual size of the suspected target; If the difference between the actual size and the theoretical size is not greater than a set threshold, then the suspected target is determined as the target target; The process of identifying suspected targets in the scanned image corresponding to the circuit board to be processed based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape includes: Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, the actual centroid coordinates corresponding to the theoretical centroid coordinates are calculated. Based on the theoretical type and the theoretical shape, the suspected target is identified at the actual centroid coordinates of the scanned image.

2. The method according to claim 1, after calculating the actual centroid coordinates corresponding to the theoretical centroid coordinates based on a pre-defined correspondence between theoretical and actual centroid coordinates, the method further includes: If the suspected target cannot be identified at the actual centroid coordinates of the scanned image based on the theoretical type and the theoretical shape, a first alarm message is output. The first alarm message is used to remind the user that the suspected target has not been identified.

3. The method according to claim 1, characterized in that, The identification of the actual size of the suspected target includes: Identify the imaging size of the suspected target on the scanned image; Based on the pre-defined correspondence between the imaging size and the actual size, the actual size corresponding to the imaging size is determined.

4. The method according to claim 1, characterized in that, After identifying the actual size of the suspected target, the method further includes: If the difference between the actual size and the theoretical size is greater than a set threshold, a second alarm message is output. The second alarm message is used to prompt the user that the suspected target is not the target target.

5. The method according to claim 1, characterized in that, If the difference between the actual size and the theoretical size is not greater than a set threshold, and the suspected target is then identified as the target target, the method further includes: Based on the pre-defined correspondence between the machine tool centroid coordinates and the actual centroid coordinates, the machine tool centroid coordinates corresponding to the actual centroid coordinates are determined; The target is located on the laser processing machine tool based on the centroid coordinates of the machine tool. The circuit board to be processed is processed based on the located target.

6. The method according to claim 1, characterized in that, The theoretical types include optical targets and through-hole targets, and the theoretical shapes include circular targets, rectangular targets, and cross targets.

7. The method according to claim 1, characterized in that, Before identifying the suspected target in the scanned image corresponding to the circuit board to be processed based on the theoretical centroid coordinates, the theoretical type, and the theoretical shape, the method further includes: The circuit board to be processed is placed at a predetermined processing position on a laser processing machine tool, wherein the predetermined endpoint on the circuit board to be processed coincides with the origin of the machine tool coordinate system; The control line scan camera performs a global scan of the circuit board to be processed to obtain the scanned image of the circuit board to be processed.

8. The method according to any one of claims 1-7, characterized in that, The type of circuit board to be processed is an integrated circuit carrier board.

9. A positioning device for a circuit board target, characterized in that, The device includes: The processing unit is used to receive the design drawing file of the circuit board to be processed, and to parse the theoretical dimensions and theoretical centroid coordinates of the target from the design drawing file; The acquisition unit is used to acquire the theoretical type and theoretical shape of the target object as preset. The identification unit is used to identify a suspected target in the scanned image corresponding to the circuit board to be processed, based on the theoretical centroid coordinates, the theoretical type and the theoretical shape. The identification unit is also used to identify the actual size of the suspected target; The determining unit is configured to determine the suspected target as the target target if the difference between the actual size and the theoretical size is not greater than a set threshold. The identification unit is specifically used for: Based on the pre-defined correspondence between theoretical centroid coordinates and actual centroid coordinates, the actual centroid coordinates corresponding to the theoretical centroid coordinates are calculated. Based on the theoretical type and the theoretical shape, the suspected target is identified at the actual centroid coordinates of the scanned image.

10. An electronic device, characterized in that, The electronic device includes at least one processor and a memory connected to the at least one processor, the at least one processor being configured to implement the steps of the method as described in any one of claims 1-8 when executing a computer program stored in the memory.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-8.

Images