PCB detection method, control equipment, medium, product and equipment

Abstract

The invention discloses a PCB detection method, a control device, a medium, a product and a device, and the method comprises the steps: controlling a light source device to emit at least two kinds of light rays to a PCB; a camera device is controlled to shoot the PCB, and a light source image corresponding to each kind of light is obtained; aligning each light source image, and acquiring an alignment image corresponding to each light source image; and performing defect detection on the alignment images corresponding to the at least two light source images to obtain a PCB detection result. According to the technical scheme, defect detection is performed by combining the alignment images corresponding to the light source images of different light rays, so that the camera shooting equipment can shoot the light source images including different defect information under different light rays through different light ray effects, and the defect detection accuracy is improved. Therefore, the control equipment can carry out defect detection through the light source images including different defect information, and the accuracy of PCB defect detection is ensured.

Description

Technical Field

[0001] This invention relates to the field of PCB technology, and in particular to a PCB inspection method, control equipment, medium, product, and equipment. Background Technology

[0002] With the increasing prevalence of Automatic Visual Inspection (AVI) equipment for PCB boards in China, higher requirements are being placed on the inspection capabilities of AVI equipment. However, current AVI equipment can only detect some common defects on the surface of PCB boards, which can no longer meet market demands. For example, for the detection of defects under the ink on PCB boards, such as minor scratches or foreign objects, the existing AVI equipment performs poorly, either failing to detect true defects or introducing a large number of false spots. Summary of the Invention

[0003] This invention provides a PCB inspection method, control device, medium, product, and equipment to solve the problem of poor defect detection performance in existing PCBs.

[0004] A PCB inspection method, comprising:

[0005] Control the light source device to emit at least two types of light onto the PCB board;

[0006] Control the camera device to capture images of the PCB board and obtain light source images corresponding to each type of light;

[0007] Align each of the light source images to obtain the alignment image corresponding to each of the light source images;

[0008] Defect detection is performed on the alignment images corresponding to at least two of the light source images to obtain PCB inspection results.

[0009] Optionally, the control of the light source device to emit at least two types of light onto the PCB board includes:

[0010] Determine the flicker frequency, and control the light source device to alternately emit at least two types of light onto the PCB board according to the flicker frequency;

[0011] The controlled camera device captures images of the PCB board to obtain light source images corresponding to each type of light, including:

[0012] The camera device is controlled to sequentially acquire pixel images corresponding to each pixel row on the PCB board for each light ray according to the first direction.

[0013] Based on the pixel image corresponding to each pixel row on the PCB board for each ray, obtain the light source image corresponding to each ray.

[0014] Optionally, determining the flicker frequency includes:

[0015] Determine the moving speed of the PCB board and the shooting frequency of the camera device in each pixel row of the PCB board;

[0016] The strobe frequency is determined based on the moving speed and the shooting frequency.

[0017] Optionally, the step of sequentially acquiring pixel images corresponding to each pixel row of each light ray on the PCB board includes:

[0018] The camera device is controlled to take at least two pictures of the PCB board in each pixel row, and each picture captures a pixel image corresponding to a certain light in a pixel row.

[0019] Optionally, the emission time of each type of light is less than the exposure time of each of the photographs.

[0020] Optionally, the step of aligning each of the light source images to obtain an alignment image corresponding to each of the light source images includes:

[0021] Based on the Gerber image, each of the light source images is aligned to obtain the first affine transformation matrix corresponding to each of the light source images.

[0022] Based on the first affine transformation matrix corresponding to each of the light source images, obtain the alignment image corresponding to each of the light source images.

[0023] Optionally, the step of performing defect detection on the alignment images corresponding to at least two of the light source images to obtain PCB inspection results includes:

[0024] A defect detection algorithm corresponding to the target defect type is used to perform defect detection on the alignment image corresponding to each light source image, and the PCB detection result corresponding to the target defect type is obtained.

[0025] A control device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the PCB inspection method described above.

[0026] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described PCB inspection method.

[0027] A computer program product includes a computer program that, when executed by a processor, implements the aforementioned PCB inspection method.

[0028] A PCB inspection device, the PCB inspection device comprising a light source device, a camera device, a conveying device, and the aforementioned control device;

[0029] The conveying device is used to convey PCB boards;

[0030] The light source device and the camera device are arranged opposite to the transmission device;

[0031] The control device is connected to the transmission device, the light source device, and the camera device.

[0032] Optionally, the light source device includes RGB lights and infrared lights.

[0033] The aforementioned PCB inspection method, control equipment, medium, product, and equipment involve controlling a light source device to emit at least two types of light onto the PCB board, controlling a camera device to capture images of the PCB board, acquiring light source images corresponding to each type of light to ensure the clarity of the light source images, aligning each light source image to acquire an alignment image corresponding to each light source image, performing defect detection on the alignment images corresponding to each light source image, and obtaining PCB inspection results. By combining the alignment images corresponding to light source images of different light sources for defect detection, the camera device can capture light source images containing different defect information under different lighting conditions through different lighting effects. This enables the control equipment to perform defect detection through light source images containing different defect information, ensuring the accuracy of PCB defect detection. Attached Figure Description

[0034] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is a flowchart of a PCB inspection method according to an embodiment of the present invention;

[0036] Figure 2 This is another flowchart of a PCB inspection method in one embodiment of the present invention;

[0037] Figure 3 This is another flowchart of a PCB inspection method in one embodiment of the present invention;

[0038] Figure 4This is another flowchart of a PCB inspection method in one embodiment of the present invention;

[0039] Figure 5 This is a schematic diagram of a pulse signal in one embodiment of the present invention;

[0040] Figure 6 This is a schematic diagram of a PCB inspection device according to an embodiment of the present invention;

[0041] Figure 7 This is a schematic diagram of a control device in one embodiment of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention 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 the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] This invention provides a PCB inspection method, which can be applied to, for example... Figure 6 The application environment is shown. Specifically, this PCB inspection method is applied in a PCB inspection device, which includes, as shown in the example, [details of the example]. Figure 1 The diagram shows a light source device, a camera device, a conveying device, and a control device. The conveying device is used to place and convey PCB boards. The light source device and the camera device are arranged opposite to the conveying device. Exemplarily, the light source device and the camera device may be positioned above the conveying device to detect the front side of the PCB board on the conveying device, or the light source device and the camera device may be positioned below the conveying device to detect the back side of the PCB board on the conveying device. Alternatively, the light source device and the camera device may be positioned above or below the conveying device to simultaneously detect both the front and back sides of the PCB board. 该 The light source device provides at least two types of light to the PCB board. The camera device is used to photograph the PCB board. The control device is connected to the conveyor, the light source device, and the camera device to implement the PCB inspection method.

[0044] As an example, the conveying device includes a conveyor belt and a PCB sensor. The conveyor belt is used to place and convey PCB boards. The PCB sensor is positioned opposite the conveyor belt and connected to a control device. When the PCB board on the conveyor belt is conveyed to the target detection position, the sensor generates a sensing signal to the control device, which then executes the PCB inspection method to automatically detect defects in the PCB board.

[0045] This embodiment provides a PCB inspection method, such as... Figure 1 As shown, it includes:

[0046] S101: Controls the light source device to emit at least two types of light onto the PCB board.

[0047] S102: Control the camera device to take pictures of the PCB board and obtain the light source image corresponding to each type of light.

[0048] S103: Align each light source image to obtain the alignment image corresponding to each light source image.

[0049] S104: Perform defect detection on the alignment images corresponding to at least two light source images to obtain PCB inspection results.

[0050] The at least two types of light can include visible light and infrared light, or other light that can be captured by a camera. Preferably, the visible light is white light, which facilitates the camera capturing images of the PCB surface. As an example, the light source device includes a light source for generating at least two types of light. Exemplarily, the at least two light sources include RGB lights and infrared lights. By adjusting the intensity of the red, green, and blue primary colors in the RGB lights, the RGB lights can generate white light.

[0051] Here, a light source image refers to an image captured by a camera device on a PCB board under corresponding lighting conditions. Examples include light source images corresponding to white light and light source images corresponding to infrared light. An alignment image is an image obtained after aligning the light source image.

[0052] As an example, in step S101, when the control device receives the sensing signal output by the PCB sensor, indicating that the PCB board has been moved to the target detection position, the control device controls the light source device to emit at least two types of light onto the PCB board. The target detection position refers to the location where defect detection is performed on the PCB board. In this example, the target detection position can be located below the light source device and the camera device, so that the camera device can capture images of the PCB board after the light source device emits at least two types of light, thereby obtaining a light source image corresponding to each type of light.

[0053] As an example, in step S102, after the control device controls the light source device to emit at least two types of light onto the PCB board, or simultaneously controls the light source device to emit at least two types of light onto the PCB board, the control device controls the camera device to capture images of the PCB board, obtaining light source images corresponding to each type of light to ensure the clarity of the light source images. Furthermore, since different types of light have different effects, acquiring light source images corresponding to at least two types of light enables the control device to perform a more comprehensive and reliable analysis of PCB board defects based on these images. For example, light source images acquired using white light can be used to detect common defects on the PCB board surface, while light source images acquired using infrared light can be used to detect internal defects under the ink on the PCB board, such as minor scratches, foreign objects, and broken circuits, thereby improving the accuracy of PCB defect detection.

[0054] As an example, in step S103, the control device aligns each light source image based on the PCB file to obtain an alignment image corresponding to each light source image. Exemplarily, the PCB file is a file used for PCB design and manufacturing. Exemplarily, the PCB file includes a Gerber file, such as a Gerber diagram. In this embodiment, by aligning each light source image with the PCB file, the positioning information of the PCB lines and PCB components on the PCB board corresponding to each light source image is determined. Based on the positioning information, alignment processing is performed on the image areas where the PCB lines and PCB components are located in each light source image to obtain an alignment image corresponding to the PCB lines and PCB components in each light source image, thereby further ensuring the accuracy of subsequent PCB defect detection.

[0055] As an example, in step S104, the control device performs defect detection on the alignment images corresponding to at least two light source images to obtain PCB inspection results. Exemplarily, the control device employs a preset defect detection strategy to perform defect detection on the alignment images corresponding to at least two light source images to obtain PCB inspection results. This preset defect detection strategy is a custom-defined detection algorithm used to detect defects in the alignment images. Exemplarily, this detection algorithm can employ blob analysis algorithms, template matching methods, deep learning methods, image segmentation algorithms, and image feature extraction algorithms, etc. Exemplarily, defect features in the alignment images are extracted using the above detection algorithm, and cluster analysis is performed based on these defect features to output PCB inspection results. By combining alignment images corresponding to light source images with different lighting conditions for defect detection, the camera device can capture light source images containing different defect information under different lighting conditions, thereby enabling the control device to perform defect detection on light source images containing different defect information, ensuring the accuracy of PCB defect detection.

[0056] For example, in one application scenario, after a PCB board is placed into the conveying device of a PCB inspection equipment, the PCB board is conveyed to the target inspection position. When the PCB sensor in the conveying device outputs a sensing signal to the control device when the PCB board is conveyed to the target inspection position, the control device controls the light source device to emit white light and infrared light to the PCB board, and controls the camera device to capture images of the PCB board, acquiring the light source image corresponding to the white light and the light source image corresponding to the infrared light. Based on the PCB file, the light source images corresponding to the white light and infrared light are aligned, and the alignment images corresponding to the white light and infrared light light are acquired respectively. Defect detection is performed on the alignment images corresponding to the white light light and the alignment images corresponding to the infrared light light, obtaining the PCB inspection result. In this example, white light enables the camera device to capture defect information on the surface of the PCB board, and infrared light enables the camera device to capture defect information inside the PCB board. Thus, the defect information on the surface and inside the PCB board is combined for defect detection, improving the accuracy of PCB defect detection. For example, the defect information includes information such as short circuit, open circuit, bent circuit, missing pad, oxidation and / or scratches.

[0057] In this embodiment, the control light source device emits at least two types of light onto the PCB board, and the control camera device captures images of the PCB board to obtain light source images corresponding to each type of light, ensuring the clarity of the light source images. Based on the PCB file, each light source image is aligned to obtain an alignment image corresponding to each light source image. Defect detection is performed on the alignment images corresponding to each light source image to obtain PCB inspection results. By combining the alignment images corresponding to light source images of different light sources for defect detection, the camera device can capture light source images containing different defect information under different lighting conditions through different lighting effects. This enables the control device to perform defect detection on light source images containing different defect information, ensuring the accuracy of PCB defect detection.

[0058] In one embodiment, such as Figure 2 As shown, in step S101, controlling the light source device to emit at least two types of light onto the PCB board includes:

[0059] S201: Based on the flicker frequency, control the light source device to alternately emit at least two types of light onto the PCB board.

[0060] In step S102, the camera device is controlled to capture images of the PCB board, obtaining light source images corresponding to each type of light, including:

[0061] S202: Control the camera device to sequentially acquire pixel images corresponding to each pixel row on the PCB board for each light ray according to the first direction.

[0062] S203: Obtain the light source image corresponding to each ray based on the pixel image corresponding to each pixel row on the PCB board for each ray.

[0063] Here, strobe frequency refers to the frequency at which at least two types of light alternate. A pixel row refers to the row of pixels located when a camera captures an image of a PCB board. The first direction refers to the shooting direction of the camera when capturing the PCB board.

[0064] As an example, in step S201, the control device, based on the flicker frequency, controls the light source device to alternately emit at least two types of light onto the PCB board. This allows the camera device to capture pixel images corresponding to each light in each pixel row, thus forming a light source image corresponding to each light after the camera device has captured images of the PCB board. In this way, at least two light source images can be captured at a single workstation, reducing the number of inspection stations and shooting times, and improving the efficiency and cost of PCB defect detection. Optionally, the flicker frequency can be determined by directly obtaining the flicker frequency input by the user, or by determining the flicker frequency based on the flicker parameters input by the user and a preset frequency calculation strategy.

[0065] As an example, in step S202, the control device controls the camera device to sequentially acquire pixel images corresponding to each pixel row on the PCB board for each light ray according to the first direction. For instance, if the camera device's shooting range is 300*500 pixels and the PCB board is within this shooting range, the control device directly or indirectly determines the flicker frequency based on user input information, and controls the light source device to alternately emit at least two types of light rays to the PCB board based on the flicker frequency. Simultaneously, it sequentially captures each pixel row from bottom to top with a width of 300 pixels until a height of 500 pixels is reached. This flicker frequency is the frequency at which white light and infrared light are emitted once and once respectively within the time period of the camera device capturing one pixel row, ensuring that the camera device can acquire pixel images corresponding to each light ray in each pixel row.

[0066] As an example, in step S203, the control device acquires a light source image corresponding to each ray based on the pixel image corresponding to each pixel row on the PCB board for each ray. For example, the control device can acquire a light source image corresponding to each ray by synthesizing the pixel image corresponding to each pixel row on the PCB board for each ray.

[0067] In this embodiment, based on the flicker frequency, the light source device is controlled to alternately emit at least two types of light onto the PCB board. The camera device is controlled to sequentially acquire pixel images corresponding to each pixel row on the PCB board for each light according to the first direction. Based on the pixel images corresponding to each pixel row on the PCB board for each light, the light source image corresponding to each light is obtained. This allows the camera device to acquire light source images corresponding to at least two types of light while capturing all pixel rows, i.e., capturing the entire PCB board. This reduces the number of inspection stations and shooting times, and improves the efficiency and cost of PCB defect detection.

[0068] In one embodiment, such as Figure 3 As shown, before step S201, that is, before controlling the light source device to alternately emit at least two types of light onto the PCB board based on the flicker frequency, the PCB inspection method further includes:

[0069] S301: Determine the PCB board's moving speed and the shooting frequency of the camera device shooting the PCB board in each pixel row.

[0070] S302: Determine the strobe frequency based on the movement speed and shooting frequency.

[0071] As an example, in step S301, the control device determines the moving speed of the PCB board and the shooting frequency of the camera device shooting the PCB board in each pixel row. Specifically, this can be done directly through user input or based on the sensor detection results.

[0072] As an example, in step S302, the control device determines the strobe frequency based on the moving speed and the shooting frequency. For instance, let the moving speed be V, the number of times the camera operates within the shooting period T1 of each pixel row be n, where n ≥ 2, and the shooting frequency f1 of the camera device be... The control device controls the light source to alternately emit n types of light onto the PCB board, such as white light and infrared light. The physical distance d between the pulses of white light and infrared light is then given by... Based on the pulse physical distance d between white light and infrared light, the time period for the white light and infrared light to be lit alternately is determined. Based on the time period for the white light and infrared light to be lit alternately, the flicker frequency is determined to ensure that the camera device can capture a clear image of the light source at this flicker frequency.

[0073] As an example, such as Figure 5The diagram shows the pulse signals controlling the camera and light source during the scanning of one pixel row cycle. Trig1 represents the pulse signal during one pixel row scan, Lighting1 represents the pulse signal corresponding to infrared light, and Lighting2, Lighting3, and Lighting4 represent the pulse signals corresponding to the RGB channels of the RGB lights. Trig1 represents two high-level events occurring within one pixel row scanned by the camera, corresponding to the exposure time. During the first exposure, the light source generates infrared light; during the second exposure, it generates white light. Based on the flicker frequency, white and infrared light alternately illuminate until the corresponding light source images are acquired.

[0074] In one embodiment, the pixel image corresponding to each pixel row on the PCB board for each ray is acquired sequentially, including:

[0075] The camera device is controlled to take at least two pictures of the PCB board in each pixel row, and each picture captures a pixel image corresponding to a certain light in one pixel row.

[0076] In this embodiment, the camera device is controlled to take at least two pictures of the PCB board in each pixel row. Each picture captures a pixel image corresponding to a certain type of light in a pixel row, so that the camera device can capture a pixel image corresponding to a certain type of light in each picture of the PCB board in each pixel row. Thus, the light source image corresponding to each light can be captured at the same time as all pixel rows are captured.

[0077] In one embodiment, the emission time of each type of light is less than the exposure time of each shot.

[0078] In this embodiment, the emission time of each light ray is ensured to be less than the exposure time of each shot, so that the camera device can capture a clear pixel image each time it takes a shot, thereby ensuring the clarity of the light source image.

[0079] In one embodiment, such as Figure 4 As shown, in step S103, the PCB file includes Gerber images; each light source image is aligned to obtain an alignment image corresponding to each light source image, including:

[0080] S401: Based on the Gerber image, align each light source image to obtain the first affine transformation matrix corresponding to each light source image.

[0081] S402: Obtain the alignment image corresponding to each light source image based on the first affine transformation matrix corresponding to each light source image.

[0082] As an example, in step S401, feature extraction is performed on the Gerber image and each light source image, for example, using a feature point detection algorithm. Feature point matching is then performed on the extracted feature points to obtain feature point pairs. Based on the feature point pairs, a preset affine transformation function is used to perform an affine matrix transformation to obtain the first affine transformation matrix corresponding to each light source image. Optionally, the feature point detection algorithm includes SIFT, SURF, and ORB, etc.

[0083] As an example, in step S402, a corresponding alignment image is obtained based on the first affine transformation matrix corresponding to each light source image. In this embodiment, each light source image is transformed according to the first affine transformation matrix, for example, by scaling, rotating, or translating, to obtain the corresponding alignment image, thereby ensuring the accuracy of the alignment image.

[0084] In this embodiment, each light source image is aligned according to the Gerber image to obtain the first affine transformation matrix corresponding to each light source image. Based on the first affine transformation matrix corresponding to each light source image, the alignment image corresponding to each light source image is obtained, so as to ensure the accuracy of the alignment image through affine transformation processing.

[0085] In one embodiment, defect detection is performed on the alignment images corresponding to at least two light source images to obtain PCB detection results, including: using a defect detection algorithm corresponding to the target defect type to perform defect detection on the alignment image corresponding to each light source image to obtain PCB detection results corresponding to the target defect type.

[0086] As an example, target defect types include circuit defects and pad defects. If the target defect type is a circuit defect, edge detection and inflection point detection are first performed on each light source image to determine the circuit lines in the alignment image. Then, blob analysis is performed on the circuit lines to obtain the PCB inspection results corresponding to the circuit defect.

[0087] As another example, if the target defect type is a pad defect, then each pad in each light source image is individually aligned to determine the position of each pad in the alignment image. Then, based on the position of each pad in the alignment image, a separate blob analysis is performed on each pad to obtain the PCB inspection result corresponding to the pad defect.

[0088] In this embodiment, a defect detection algorithm corresponding to the target defect type is used to perform defect detection on the alignment image corresponding to each light source image, and obtain the PCB detection result corresponding to the target defect type, so as to perform targeted detection for different target defect types and improve the accuracy of PCB detection results.

[0089] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0090] In one embodiment, a control device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the control device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data generated during the processor's execution of the PCB inspection method. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a PCB inspection method.

[0091] In one embodiment, a control device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the PCB detection method described in the above embodiment. To avoid repetition, it will not be described again here.

[0092] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the PCB inspection method described in the above embodiment. To avoid repetition, it will not be described again here.

[0093] This embodiment provides a computer program product, including a computer program that, when executed by a processor, implements the above-described PCB inspection method.

[0094] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0095] This embodiment provides a PCB inspection device, such as... Figure 6 As shown, the PCB inspection equipment includes a light source device, a camera device, a conveying device, and a control device in the above embodiments; the conveying device is used to convey PCB boards; the light source device and the camera device are arranged opposite to the conveying device; the control device is connected to the conveying device, the light source device, and the camera device.

[0096] For example, the light source and camera can be positioned above the conveying device to detect the front side of the PCB board on the conveying device, and the light source and camera can be positioned below the conveying device to detect the back side of the PCB board on the conveying device. Alternatively, the light source and camera can be positioned both above and below the conveying device to simultaneously detect both the front and back sides of the PCB board. Figure 6 The light source and camera equipment shown can be positioned above the conveyor. It should be noted that, depending on actual needs, the light source and camera equipment can also be positioned below the conveyor, and connected to a control device to inspect the back of the PCB board.

[0097] In this embodiment, the control module can perform defect detection by combining the alignment images corresponding to the light source images under different lighting conditions. By using different lighting effects, the camera device can capture light source images containing different defect information under different lighting conditions, thereby enabling the control device to perform defect detection using light source images containing different defect information, ensuring the accuracy of PCB defect detection.

[0098] In one embodiment, the light source device includes RGB lights and infrared lights. In this embodiment, the light source image obtained by using white light generated by RGB lights can be used to detect common defects on the surface of the PCB board, while the light source image obtained by using infrared light generated by infrared lights can be used to detect internal defects under the ink on the PCB board, such as minor scratches, foreign objects, and broken lines, thereby improving the accuracy of PCB defect detection.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0100] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A PCB detection method, It is characterized in that include: Control the light source device to emit at least two kinds of light to the PCB board; Controlling a camera to shoot the PCB board to obtain a light source image corresponding to each light; Aligning each of the light source images to obtain an alignment image corresponding to each of the light source images; Defect detection is performed on the alignment images corresponding to at least two of the light source images to obtain a PCB detection result.

2. The PCB detection method according to claim 1, It is characterized in that The controlling the light source device to emit at least two kinds of light to the PCB board comprises: Determine a stroboscopic frequency, and control the light source device to alternately emit at least two kinds of light to the PCB board according to the stroboscopic frequency; The controlling the camera device to shoot the PCB board to obtain a light source image corresponding to each light, including: Control the camera device to sequentially collect pixel images corresponding to each pixel row corresponding to each light ray on the PCB board according to the first direction; According to the pixel image corresponding to each pixel row corresponding to each light ray on the PCB board, the light source image corresponding to each light ray is acquired.

3. The PCB detection method according to claim 2, It is characterized in that The step of determining the stroboscopic frequency comprises: Determine the moving speed of the PCB board and the shooting frequency of the camera device shooting the PCB board in each pixel row; The stroboscopic frequency is determined according to the moving speed and the shooting frequency.

4. The PCB detection method according to claim 2, It is characterized in that The sequentially collecting pixel images corresponding to each pixel row corresponding to each light ray on the PCB board includes: The camera device is controlled to shoot the PCB board at least twice in each pixel row, and each shooting acquires a pixel image corresponding to one of the light rays in one of the pixel rows.

5. The PCB detection method according to claim 4, It is characterized in that The emission time of each light is shorter than the exposure time of each shooting.

6. The PCB detection method according to claim 1, It is characterized in that The step of aligning each of the light source images to obtain an alignment image corresponding to each of the light source images includes: According to the Gerber image, align each of the light source images to obtain a first affine transformation matrix corresponding to each of the light source images; According to the first affine transformation matrix corresponding to each of the light source images, an alignment image corresponding to each of the light source images is obtained.

7. The PCB detection method according to claim 1, It is characterized in that The performing defect detection on the alignment images corresponding to at least two of the light source images to obtain a PCB detection result includes: A defect detection algorithm corresponding to the target defect type is used to perform defect detection on the alignment image corresponding to each of the light source images to obtain a PCB detection result corresponding to the target defect type.

8. A control device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the computer program, the PCB detection method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the PCB detection method according to any one of claims 1 to 7 is implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the PCB detection method according to any one of claims 1 to 7 is implemented.

11. A PCB testing device, It is characterized in that The PCB detection device comprises a light source device, a camera device, a transmission device and a control device as claimed in claim 8; The conveying device is used to convey the PCB board; The light source device and the camera device are arranged opposite to the transmission device; The control device is connected to the transmission device, the light source device and the camera device.

12. The PCB testing device as claimed in claim 11, It is characterized in that The light source device includes an RGB lamp and an infrared lamp.

Images